Just Sad

It has frankly, been a shit week. My friend Gordon White died.

A loss of a force and a friendship that has been consistent for a quarter of my life. I have so much to say, but can’t find the words just now. Just sad.

Grief is a process that has only a beginning, so I am trying not to mistake this first darkness for the whole sky.

My heart goes out to James, his family, and friends x

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

Reading

Still reading Super Nintendo: How One Japanese Company Helped the World Have Fun by Keza MacDonald. It’s very engaging drawing on a careers worth of 1-2-1 interviews and archival reporting.

Parlour Greens – Emeralds (LP)

Soul/jazz/funk super group Parlour Greens have a new album out and damn…. the pocket on this album is craze. Funky as hell.

Remember Kids:

The post Just Sad | Weeknotes #439 appeared first on thejaymo.net.

Jubensha Con

On Saturday I went to Jubensha Con 2026. The first english language convention about the Chinese social phenomenon of Jubensha.

We’re the world’s first convention dedicated to English-language jubensha. Jubensha is a phenomenally popular “scripted murder” format of games originating in China, where participants roleplay as detectives and/or suspects in mystery to deduce who the culprit is. In recent years it’s broadened far beyond murders into investigations of all kinds, and is spreading internationally.

We’re organising this convention to give people a chance to try out games, spur new collaborations, and help grow the scene. It’s a deliberately lo-fi, informal, and non-profit endeavour, and we want to keep costs as low as possible so money isn’t a barrier to entry.

Huge shout out to Adrian Hon and all the other organisers of the event. I had an amazing time there.

If you are unfamiliar with it as a form, this 2024 People Make Games documentary about it is a good place to start.

I haven’t written up my notes properly from Saturday’s talk track yet, but the following brain dump represents most of the big takeaways, and will forms the basis for them.

• China has/had no extant consumer market for LARP/TTRPGs/Murder Mystery/Escape Room/dinner theatre/or Euro style boardgames. No do young people have a huge ‘Party’ culture. As in having a party. So when Jubensha came along and combining elements from all those things around a social deduction mechanic it exploded in popularity and immidiatly fused with the dating market.
• Jubensha is treated more like a social commodity which is why there was such a boom/bust explosion in Jubensha. Its more like going to Karaoke than something involving a trained and talented performer as the DM. Because of this profit margins are tight, and quality of massively variable. Necessitating the creation of and App called Qiandao to keep track of and rate games and parlours providing them.
• Despite the boom and bust cycle post pandemic the industry is still worth $2billion.
• Yulin Tian and Yihan(Clytze) Li talk on Scripted Intimacy: Designing Emotional Experience in Chinese Jubensha Games was very interesting. A great deal of the current trends in the games have moved away from murder mystery and towards deeper emotional play. Instead of all 6 couples/players being equal in the game. In Script games, there is a clear Main Character and supporting cast. Some MC players will pay their friends to sit though 6-8 (even 13 hour long games) so they can experience them.
  • I think it’s interesting that the new form of script games treat Jubensha as a social technology. Mechanisms like: archetypal casting, asymmetric character scripts, scripted physical moments like weddings and symbolic gift-giving, are essentially techniques from therapeutic and theatrical traditions, packaged into a consumer product. VERY Interesting design space.
• Eastern Jubensha has points systems and defined winners; Western adaptations are moving away from overt win conditions towards pure storytelling. Which seems to reflect a deeper philosophical split about what games are for. The Western instinct is that competition undermines roleplay but in China, the instinct seems to be that stakes require scorekeeping. Neither is obviously wrong, and the tension between them is a productive design question.
• All Jubensha games require a lot of reading, upfront and during play. But Chinese players read Jubensha scripts faster because Chinese is a logographic language, meaning more information is compressed per character. Western designers face a genuine cognitive-load problem that their Chinese counterparts simply don’t. The proclivity toward reading and comprehension etc shapes how dense and long english scripts can realistically be.
• There was an observation that game authors/designers in China have no creative community per say, and games are judged solely by market profitability, and this is was put as an example of when a creative medium scales too fast without building the infrastructure that sustains quality.
• Eastern jubensha is frequently designed for exactly 3 male and 3 female players, with storylines to match, often with a romantic or dating dimension built in. This is a design norm, but for a Western audience steeped in inclusive design, this is genuinely startling.
• In the UK due to the lack of parlours and places to play fully costumed Jubensha, boxed games without a DM seem to be the emerging form factor and design space for play.
• In the West the DM in TTRPGs are co-players in the game. With a level of social respect that Jubensha DM’s working in parlours / treated like Karaoke spots don’t get.
• Lastly, many of the game authors and designers in China come out of the online fandom/fan fiction world. So many of the new emotional script games, their logics and archetypes can be esiely classified by existing online fandom community nomenclature.

Super cool day out!

On The Blog

April 2026 | Photo 365

Photo 365 2026. Year 5, Month 4. Photo-a-day for the month of April 2026.

SSRZ15: Monsters in the Mirror

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5.

Buy on Etsy

Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo. This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone. £18 + shipping worldwide

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

Photo 365

The Ministry Of My Own Labour

• Call with the WineDark crew
• Finished end to end draft of INTERNET OPERATOR episode 303
• Wrote a first draft of ‘ON THE CONSTITUTION OF THE MACHINE MIND’
• Started editing SLOP MACHINES
• Worked on a job application
• Did some work spreadsheeting for a company I advise
• Did a days work over the week working on a set of MCP/REST api prompts for a SME.

Terminal Access

Andrew Dana Hudson’s debut novel Absence is now out!

I was lucky enough to read this in several drafts including the opening, when he thought it was going to be a novella 😂. Its a great story, really gripping and has a lot of philosophical reflection throughout . If you like authors like Kazuo Ishiguro then I think you’ll enjoy Absence! ADH has put the opening chapter up online if you want to whet your whistle.

You can get this book wherever books or ebooks are sold! Find it on Amazon, B&N, Bookshop.org, or ask your local bookstore to order you a copy.

There’s also an audiobook edition (Audible, Apple Books, Kobo), and — based on my own listening as well as the reviews flooding in at Goodreads — the narrator Dan John Miller does a great job.

Reading

I started listening, to AND FINISHED, all 30 hours of Strength of the Few . The second book in the mammoth Hierarchy trilogy by James Islington. It picks up directly from book #1 with no handholding. I can see why people are saying this set of books is fast becoming this decades most important fantasy series. What a book series. Amazing.

Moved on and now I’m listening to that Nintendo book thats in the hardback non-fiction charts at the front of Waterstones. Super Nintendo: How One Japanese Company Helped the World Have Fun by Keza MacDonald.

Chiminyo – NRG 5 (LP)

Chiminyo’s 2025 NRG4 album recorded live at Ronnie Scotts was a highlight of the year last year. Not just as an album, but as a beacon of whats going on in UK music right now. NRG 5 is no different. Recorded live at Peckham Levels, it captures the kind of cultural energy that’s instantly familier to anyone that’s recently spent time amidst London’s concrete spaces.

I mean honestly. What could be more London that this in 2026?

Remember Kids:

The post Jubensha Con | Weeknotes #438 appeared first on thejaymo.net.

Photo 365 2026. Year 5, Month 4. Photo-a-day for the month of April 2026.

The post April 2026 | Photo 365 appeared first on thejaymo.net.

Turnstones

I can’t belive its MAY. It feels like only yesterday that I got back from Sri Lanka. With every passing year, it feels like life is accelerating, but then again, so are events.

It’s Bank Holiday weekend here in the UK, so projects are on hold. The GF went to Scotland on Friday to see some friends for two nights, and rather than be on my Jack I went back down to The Chalk. I was only at home a couple of weeks ago for Easter, but in between then and now, my parents have been to Hong Kong and Taiwan and back to see my younger brother. So we had a lot to catch up on.

When I got back on Friday mum asked me what I wanted to do whilst I was home, and the two things I wanted to do were; sit on the beach in the sunshine and, go for a walk along a specific part of the coast. So we did both!

Very nice! Also saw some Ruddy Turnstone’s along the sea wall as the tide was coming in:

Today being bank holiday Monday, I’ve done a bunch of domestic things around the house. Once i’ve posted this I’m going to read my book with a cup of tea.

SSRZ15: Monsters in the Mirror

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5.

Buy on Etsy

Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo. This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone. £18 + shipping worldwide

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

Photo 365

The Ministry Of My Own Labour

• Drafted the spine / argument of the whole of Episode 303 of permanently moved. Just need to write it now.
• Had a long workshop/call about the idea of ‘industrial coordination arbitrage’. Meaning there’s a competitive advantage to re-engineering or figuring a potential customer (or competitor’s) AI model provider and the system prompts of the business. “I know I can sell to you better if I know your infra’s thinking patterns” Inspired by this article on how LLMs prefer to sniff their own farts

Terminal Access

Woke up this morning to a pingback from Tracy Durnell’s Mind Garden on this fantastically hypertext dense post: Aura through the Cult of Self: opportunity creates authenticity. It’s very much worth your time, i came away with a lot of thoughts and seeds of ideas.

In our modern, individualist culture, self-expression has become “not just a moral requirement, but a teleological one,” writes Tara Isabella Burton. “It is what we, as human beings, are for.” Rather than inheriting our identity from our roles in society as we did in the past, today we are each responsible for constructing our own identity. And so, writes Byung-Chul Han, “the production of self becomes a permanent activity.”

Importantly, we must construct our identity both for ourselves and for others. In On Photography, Susan Sontag explains that our culture believes that “images possess the qualities of real things,” but viewers apply this logic in reverse and “attribute to real things the qualities of an image.” Because of this interpretive transference, we can use images to create our selves online, irrespective of physical reality or ownership.

Reading

I’m reading Henryk Jurkowski’s Aspects of Puppet Theatre right now. This book is a ‘classic’ and is on most theatre and puppety syllabi. and i can see why. It’s so interesting! and is one of those books that has totally exploded my thinking into all different directions. No wonder it’s so influential

Still reading The Mirror of Simple Souls by Marguerite Porete. Alan Chapman told me to read it after a conversation last year, and now I’m beginning to understand why.

On the recommendation of a few friends, I’ve started Listening to Will Of The Many by James Islington. I’m about half way though… its not the book i was expecting… it’s very good, it’s just… had I read the blurb, I wouldn’t have read it.

Denonbu – Ultrarhythm (Single)

I have just discovered Japanese producers Denobu, who have a whole J/Hyper-pop transmedia thing going on. An anime world full of story and key characters combined with a the music side which involves dropping a new single every week on a Thursday. They have an enormous back catalogue and i’ve only scratched the surface so far, but this track is a banger.

Remember Kids:

The post Turnstones | Weeknotes #437 appeared first on thejaymo.net.

Nearly Doable

As you might have seen, Issue #15 of my zine went out to subscribers last week. I can honestly report that sending physical things to people is bloody brilliant. Big thanks to everyone who’s been in touch about it.

When I first started making the zine back during the pandemic, I had some hope that this might be the direction of travel. Making and self-publishing proper physical artefacts that are connected to online work and creative projects, then sending them to people in the post.

After a long slog with the initial years of the zine, and making the podcast weeky, I can feel that ambition starting to become real. The whole enterprise hasn’t been “easy”, it is now almost doable. I can see the shape of the new format and how it plays out

I have been thinking a lot about pace and form since finishing 301 last year. I just don’t think people should need to post their creative work online every week for forever. Longer, more considered things, especially when they have a physical component, seem to be a much better shape. Combined the audio episode and the zine are asking for a different kind of attention. They suit the culture I want to live inside of, so I’m doing my bit to help make it happen for others.

Anyway. If sixteen-year-old me, or nine-year-old me for that matter, knew that at the age of forty I’d have a zine shipping around the world, with a proper print run and subscribers waiting for it to arrive in the post, he would be over the moon.

Anyways, there are still a few remaining copies of Issue #15 available on my Etsy.

Buy SSRZ15: Monsters in the Mirror on Etsy

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5. Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo.

This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone.

£18 + shipping worldwide

Buy on Etsy

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

On The Blog

Raindrop.io Stella Prompts for Batch Processing Bookmarks

After a lot of trial and error with batch processing, I realised the best approach was to call Raindrop’s MCP tool names directly using the public API documentation.

So below I’m sharing two versions of the prompt I ended up with. This prompt uses my own Raindrop setup, including collection names like thejaymo, my preferred bookmark note style, and the rules I use for deciding what goes into my public links feed. You’ll need to swap in your own collection names, tag, and review criteria before using it yourself.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• No work this week 😩 but I pushed a whole bunch of personal work and projects forward.
• Zine stuff obviously
• Sent invitation to new Experience.Computer guest. Positive reply. Currently organising recording date.
• Sorting out last of my life admin. Tax return soon though.

Terminal Access

WEDDING PLANIC!

My friend Stef just put her first solo dev indiegame up for wishlisting on Steam!

A roguelike, deck builder about managing a wild wedding party!

Nobody wants to throw a boring party. In Wedding Planic! you arrange a deck of neurotic wedding guests to generate high levels of Craic (which is basically Irish for fun) and Drama. 

Guests will flee, fight and f…lirt their way around the seating plan and it is your job to create good table combos and high scoring synergies to make sure that the party survives the night and goes down in history.

Each guest has a stack of repressed personality traits that can unlock new abilities as the Craic and Drama levels rise, making every playthrough unique and wonderfully chaotic!

Win by combining guests, top table cards and wedding favours to create synergetic combos that make the wedding pop off.

For fans of wedding planning and Balatro!? I played the current build last week, and it’s really coming along. Love to buy wedding favours to juice the craic at the tables! Also, I named this game over Discord DMs one afternoon last year, when we were still working together. My dadcore pun game is so strong. hahaha.

Also, I am available to name your game any time!

Reading

I finished the audio version of Liturgies of the Wild: Myths That Make Us by Martin Shaw. Absolutely fantatic. The man is a national treasure.

I went back to The Mirror of Simple Souls by Marguerite Porete 30% of the book is the introduction and now i’m actually into the main text I’m ripping though it!

Bassekou Kouyate – Miri (LP)

Just this week i discovred the work of Malian musican Bassekou Kouyate a Ngoni calabash player. Man this whole album has groove. I’m so into it. Can’t stop listening though his back catalogue.

Remember Kids:

The post Nearly Doable | Weeknotes #436 appeared first on thejaymo.net.

Issue #015 of Start Select Reset went out by snail mail yesterday to my supporters (£5/month+).

Issue #015 – Monsters In The Mirror

Issue #15 is the physical shadow of the audio essay of the same name.

It is an essay about artificial intelligence and cultural mirrors; mirrors as magical surfaces, instruments of mastery, and habitats. It turns on the transistor as a second Promethean moment, asking what it means to live inside the mirror and coexist with entities that wear language as their skin.

This print edition includes the full essay transcript, plus a new introduction and afterword written exclusively for the page; material that does not appear in the audio version.

Buy SSRZ15: Monsters in the Mirror on Etsy

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5. Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo.

This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone.

£18 + shipping worldwide

Buy on Etsy

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

Production Notes

Well. It’s nearly the end of April, and I have now completed the full end-to-end production cycle for both Permanently Moved and Start Select Reset in their expanded, more ambitious, quarterly forms.

I wrote a bit about the state of the production process a month ago, just after the audio essay came out. At the time I was mostly thinking about the writing, recording, editing, and launch sequence. Now the physical zine has also gone out to subscribers, I feel like I’ve finally completed the whole loop. That loop has been about 5x five times more work than I expected. lol

But, as I wrote back then, the whole thing has been a learning experience, and I’m not going to beat myself up about that. The first time through any new production process is always ugly as you don’t know which parts are going to be easy until they turn out not to be.

In the end, I’m really pleased with how the zine turned out. Going with print.work as my printer was an excellent decision, their customer service is fantastic, and the quality of the finished object is really good.

Originally, when I was thinking about the new format, I thought moving to A5 was going to be the main change, and use that going forward. But now I’ve used them as my printer, I can see there is so much more I could do: square booklets, landscape booklets, posters, all sorts of things. The new range of possibilities this opens up is actually quite inspiring.

To cap off this zine launch, here are some of the first-time things I have had to learn, navigate, or bodge my way through for both the podcast and the zine:

• Long-form writing: thinking, structuring, and delivering 8,000 words as one continuous audio essay.
• Long-form audio editing: finding efficient ways to cut, shape, and polish something at that length.
• Zine layout: wrestling with rivers of text, alignment, and typographic changes that did not break the whole document.
• Print production: interfacing with printers and navigating the Easter holidays, which I had completely forgotten about.
• Etsy: setting up the shop and getting the listing live.
• Royal Mail Click & Drop: completing shipping and customs labels inside a truly byzantine user experience.
• The post office ladies: arriving with 50+ international envelopes that all needed to be scanned individually for customs reasons, and because I don’t have a business account I didn’t have a single manifest QR code.

But you don’t find out unless you try. And having now tried; I can see the shape of the process much more clearly. The next one will be smoother because I now know where the friction lives.

Permanently Moved

Permanently Moved (dot) Online is a quarterly audio personal podcast, written, recorded and edited by by @thejaymo

The post Start Select Reset Zine #015 | Monsters In The Mirror appeared first on thejaymo.net.

Raindrop.io recently released Stella, an AI assistant for searching, organising, and summarising bookmarks. I’ve been using it to work through nearly 18 years of saved links, and the experience of chatting with my bookmark archive has been surprisingly great. In some situations, it has even replaced mindless doomscrolling, especially in the little moments like waiting in a supermarket queue.

At first I was using Stella for simple library maintenance; cleaning up duplicate tags, fixing spelling mistakes, merging related tags, and dealing with the sheer inertia of a tag collection that has been accreting since del.icio.us. Lately, though, I’ve been getting more ambitious: processing my read-but-unsorted bookmarks and moving the good ones into my public feed at links.thejaymo.net.

After a lot of trial and error with batch processing, I realised the best approach was to call Raindrop’s MCP tool names directly using the public API documentation.

So below I’m sharing two versions of the prompt I ended up with. This prompt uses my own Raindrop setup, including collection names like thejaymo, my preferred bookmark note style, and the rules I use for deciding what goes into my public links feed. You’ll need to swap in your own collection names, tag, and review criteria before using it yourself.

Both process five oldest bookmarks at a time, stage the proposed changes for review, and let you confirm everything before updating your library. One is a heavier, more explicit prompt with plenty of guard rails; the other is a shorter, lighter version that is less prescriptive.

If you found this page looking for a Raindrop.io Stella prompt, an MCP example, or a better workflow for organising bookmarks, this should be a useful place to start.

Heavy Prompt

UPDATE – 26 April 26: Update to specify API feature names in addition to the MCP tool calling, to make the prompt more reliable and robust.
UPDATE – 7 May 26: Update to Phase 5+6 to make appearance of user facing Approve button in the app UI more reliable in certain circumstances.
UPDATE – 20 May 26: Removes Phase 6. Phase 5 updated to instruct Stella to process prepared bookmarks sequentially rather than update in a single payload. Improves updating bookmarks reliability. – V5

# Stella Bookmark Workflow Prompt
Use the MCP bookmark tools to complete this workflow from discovery through preview. Do not apply changes until I explicitly confirm.
## Objective
Find the 5 oldest bookmarks in my Raindrop Unsorted collection. Treat those bookmarks as the fixed working set for this run. Analyse each bookmark individually, propose note, tag, and collection updates, then show one combined preview and wait for confirmation.
## Tools
Use only:
- `find_bookmarks`
- `fetch_bookmark_content`
- `find_tags`
- `find_collections`
- `update_bookmarks`
## Hard constraints
- Do not call `update_bookmarks` before explicit confirmation.
- Do not fetch content for more than one bookmark at a time.
- Do not fetch all bookmark contents up front.
- Do not add, replace, reorder, or mutate bookmarks in the working set unless I explicitly ask.
- Preserve discovery order through preview and update.
- Treat each bookmark as a sealed unit: do not compare bookmarks or mix passages, notes, tags, titles, URLs, or collection decisions across bookmarks.
- Never add quotation marks around extracted passages.
- Flagged changes require explicit confirmation by bookmark number and item.
## Internal state
Maintain:
- `working_set`: fixed bookmarks from Phase 1
- `tag_vocabulary`: existing tags from `find_tags`
- `target_collection`: verified `thejaymo` collection and its `_id`
- `proposals`: one stored proposal per bookmark
- `skipped`: bookmark indexes excluded by user
- `flagged`: proposed changes requiring explicit confirmation
Do not mutate `working_set`.
## Phase 1 — Establish working set
Call `find_bookmarks` once using Raindrop API semantics:
- `collectionId: -1`
- `sort: created`
- `perpage: 5`
- `page: 0`
This means:
- `collectionId: -1` = system Unsorted collection
- `sort: created` = created date ascending / oldest first
- `perpage: 5` = return 5 bookmarks
Do not use `collection: unsorted`, `limit`, or `sort: oldest first` unless the tool explicitly maps those aliases to the Raindrop fields above.
Store the returned bookmarks as immutable `working_set`, preserving returned order. If fewer than 5 are returned, use only those.
Each item must retain:
- index number
- bookmark id
- title
- URL, if available
- existing note, if available
- current tags, if available
- current collection, if available
Titles in previews must come from `working_set` metadata, not fetched page content.
## Phase 2 — Preflight vocabulary
Before analysing content:
1. Call `find_tags` once for the existing tag vocabulary.
2. Call `find_collections` once to verify `thejaymo` exists and record its `_id`.
If `thejaymo` does not exist, continue analysing but mark every collection action as:
`Collection action: ⚠️ Flagged for review — collection thejaymo was not found`
Do not create collections unless I explicitly ask.
During analysis, use existing tags wherever possible. If unsure whether a subject tag exists, call `find_tags` with a targeted query for that bookmark’s concrete subject.
## Phase 3 — Analyse bookmarks sequentially
Process bookmarks in `working_set` order.
For each bookmark, finish all steps before fetching the next bookmark:
1. Reset temporary passage, note, tag, collection, and flag variables.
2. Call `fetch_bookmark_content` for this bookmark only.
3. Read only this bookmark’s content.
4. Extract one key passage.
5. Prepare the note field preview.
6. Propose 3 to 7 tags.
7. Decide the collection action.
8. Store the proposal keyed by bookmark index.
9. Move to the next bookmark.
Each proposal must include:
- `index`
- `bookmark_id`
- `title`
- `url`
- `key_passage`
- `note_field_preview`
- `proposed_tags`
- `collection_action`
- `flagged_items`
## Key passage rules
Extract exactly one key passage per bookmark.
The passage must:
- be contiguous text from that bookmark only
- preserve exact wording
- be no more than 100 words
- preferably be a full paragraph
- contain no quotation marks added by you
- remove leading or trailing quote/block formatting only if it is source formatting
Prefer the strongest buried passage over the obvious lede, in this order:
1. counter-intuitive beat
2. thesis sentence or paragraph
3. sharp statistic or data anchor
4. buried irony
If no usable passage exists, set:
`Key passage: ⚠️ No usable passage found — [reason]`
Do not invent or substitute content.
## Note rules
Prepare the note update for the current bookmark only.
If a key passage exists:
- put the passage at the top
- do not paraphrase it
- do not wrap it in quotation marks
- if the existing note is empty, the new note is just the passage
- if the existing note contains text, prepend the passage, then one blank line, then preserve the existing note exactly
If no usable passage exists, use an article subtitle only if appropriate; otherwise leave the existing note unchanged and flag the note update.
Do not write the note update until confirmation.
## Tag rules
Ask: what is this bookmark materially about?
Propose 3 to 7 tags in this priority order:
1. concrete subject
2. close subject
3. broader subject
4. lens/context
Use existing tags wherever possible. Precise subject tags beat loose general tags, even if the precise tag has lower usage. High-count tags are tie-breakers, not replacements for the subject.
Do not omit the concrete subject in favour of abstract tags.
Only propose a new tag if no suitable existing tag exists. Mark it:
`#new-tag ⚠️ new tag for review`
Use lowercase, hyphenated style where appropriate.
## Collection rules
Default:
`Collection action: Move to thejaymo`
When applying this move, use the verified `thejaymo` collection `_id` as:
`collection: { "$id": target_collection._id }`
Flag the collection action instead if the bookmark is:
- highly personal or private
- sensitive
- paywalled with no usable excerpt
- too time-sensitive to age well
- unsuitable for public curation for any clear reason
Use:
`Collection action: ⚠️ Flagged for review — [reason]`
## Phase 4 — Combined preview
After all proposals are stored, show one combined preview.
Do not apply changes yet.
Do not call `update_bookmarks` yet.
Use this exact format for each bookmark:
### Bookmark [n]
Title: [title copied exactly from working_set]
Key passage: [exact passage, maximum 100 words, no quotation marks]
Tags: #tag1 #tag2 #tag3
Note field preview: [exact text that will be written to the note field]
Collection action: [Move to thejaymo OR flagged action]
If title is missing, use:
`Title: ⚠️ Missing bookmark title — [URL or bookmark id]`
After all preview blocks, output exactly:
`Confirm? Reply yes all to apply everything, no all to cancel, skip [n] to exclude a bookmark, or [n] edit [change] to amend a specific bookmark.`
## Phase 5 — Confirmation and apply
Valid commands only: `yes all`, `no all`, `skip [n]`, `[n] edit [change]`,
`yes all + [n] [change]`. Treat ambiguous replies (`yes`, `looks good`,
`go ahead`, `do it`) as invalid; ask for an exact command.
Applying = calling `update_bookmarks`. The client's native approval prompt
appears as a result of that call; it is not a separate step to request or
wait for. So on any apply command, calling `update_bookmarks` is your first
action, before any prose; do not stall or hand back beforehand.
- `yes all`: apply proposals strictly one at a time, in working_set order.
  For each: call `update_bookmarks` for that one bookmark, wait for the tool
  result, then proceed to the next. Never emit more than one `update_bookmarks`
  call before its result returns. After the last, report what changed.
- `no all`: change nothing, call nothing.
- `skip [n]`: drop bookmark `n`, reshow the combined preview.
- `[n] edit [change]`: revise bookmark `n`'s proposal only, reshow the preview.
- `yes all + [n] [change]`: amend bookmark `n`'s proposal, then proceed as `yes all`.
`yes all` excludes flagged collection actions, flagged note updates, and new
tags; each needs separate confirmation by bookmark number and item.

Shorter Prompt

# Stella Bookmark Workflow Prompt
Use the MCP bookmark tools to complete this workflow from discovery through preview. Do not apply changes until I explicitly confirm.
## Objective
Find the 5 oldest bookmarks in my Raindrop Unsorted collection. Treat those bookmarks as the fixed working set for this run. Analyse each bookmark individually, propose note, tag, and collection updates, then show one combined preview and wait for confirmation.
## Tools
Use only:
- `find_bookmarks`
- `fetch_bookmark_content`
- `find_tags`
- `find_collections`
- `update_bookmarks`
## Hard constraints
- Do not call `update_bookmarks` before explicit confirmation.
- Do not fetch content for more than one bookmark at a time.
- Do not fetch all bookmark contents up front.
- Do not add, replace, reorder, or mutate bookmarks in the working set unless I explicitly ask.
- Preserve discovery order through preview and update.
- Treat each bookmark as a sealed unit: do not compare bookmarks or mix passages, notes, tags, titles, URLs, or collection decisions across bookmarks.
- Never add quotation marks around extracted passages.
- Flagged changes require explicit confirmation by bookmark number and item.
## Internal state
Maintain:
- `working_set`: fixed bookmarks from Phase 1
- `tag_vocabulary`: existing tags from `find_tags`
- `target_collection`: verified `thejaymo` collection and its `_id`
- `proposals`: one stored proposal per bookmark
- `skipped`: bookmark indexes excluded by user
- `flagged`: proposed changes requiring explicit confirmation
Do not mutate `working_set`.
## Phase 1 — Establish working set
Call `find_bookmarks` once using Raindrop API semantics:
- `collectionId: -1`
- `sort: created`
- `perpage: 5`
- `page: 0`
This means:
- `collectionId: -1` = system Unsorted collection
- `sort: created` = created date ascending / oldest first
- `perpage: 5` = return 5 bookmarks
Do not use `collection: unsorted`, `limit`, or `sort: oldest first` unless the tool explicitly maps those aliases to the Raindrop fields above.
Store the returned bookmarks as immutable `working_set`, preserving returned order. If fewer than 5 are returned, use only those.
Each item must retain:
- index number
- bookmark id
- title
- URL, if available
- existing note, if available
- current tags, if available
- current collection, if available
Titles in previews must come from `working_set` metadata, not fetched page content.
## Phase 2 — Preflight vocabulary
Before analysing content:
1. Call `find_tags` once for the existing tag vocabulary.
2. Call `find_collections` once to verify `thejaymo` exists and record its `_id`.
If `thejaymo` does not exist, continue analysing but mark every collection action as:
`Collection action: ⚠️ Flagged for review — collection thejaymo was not found`
Do not create collections unless I explicitly ask.
During analysis, use existing tags wherever possible. If unsure whether a subject tag exists, call `find_tags` with a targeted query for that bookmark’s concrete subject.
## Phase 3 — Analyse bookmarks sequentially
Process bookmarks in `working_set` order.
For each bookmark, finish all steps before fetching the next bookmark:
1. Reset temporary passage, note, tag, collection, and flag variables.
2. Call `fetch_bookmark_content` for this bookmark only.
3. Read only this bookmark’s content.
4. Extract one key passage.
5. Prepare the note field preview.
6. Propose 3 to 7 tags.
7. Decide the collection action.
8. Store the proposal keyed by bookmark index.
9. Move to the next bookmark.
Each proposal must include:
- `index`
- `bookmark_id`
- `title`
- `url`
- `key_passage`
- `note_field_preview`
- `proposed_tags`
- `collection_action`
- `flagged_items`
## Key passage rules
Extract exactly one key passage per bookmark.
The passage must:
- be contiguous text from that bookmark only
- preserve exact wording
- be no more than 100 words
- preferably be a full paragraph
- contain no quotation marks added by you
- remove leading or trailing quote/block formatting only if it is source formatting
Prefer the strongest buried passage over the obvious lede, in this order:
1. counter-intuitive beat
2. thesis sentence or paragraph
3. sharp statistic or data anchor
4. buried irony
If no usable passage exists, set:
`Key passage: ⚠️ No usable passage found — [reason]`
Do not invent or substitute content.
## Note rules
Prepare the note update for the current bookmark only.
If a key passage exists:
- put the passage at the top
- do not paraphrase it
- do not wrap it in quotation marks
- if the existing note is empty, the new note is just the passage
- if the existing note contains text, prepend the passage, then one blank line, then preserve the existing note exactly
If no usable passage exists, use an article subtitle only if appropriate; otherwise leave the existing note unchanged and flag the note update.
Do not write the note update until confirmation.
## Tag rules
Ask: what is this bookmark materially about?
Propose 3 to 7 tags in this priority order:
1. concrete subject
2. close subject
3. broader subject
4. lens/context
Use existing tags wherever possible. Precise subject tags beat loose general tags, even if the precise tag has lower usage. High-count tags are tie-breakers, not replacements for the subject.
Do not omit the concrete subject in favour of abstract tags.
Only propose a new tag if no suitable existing tag exists. Mark it:
`#new-tag ⚠️ new tag for review`
Use lowercase, hyphenated style where appropriate.
## Collection rules
Default:
`Collection action: Move to thejaymo`
When applying this move, use the verified `thejaymo` collection `_id` as:
`collection: { "$id": target_collection._id }`
Flag the collection action instead if the bookmark is:
- highly personal or private
- sensitive
- paywalled with no usable excerpt
- too time-sensitive to age well
- unsuitable for public curation for any clear reason
Use:
`Collection action: ⚠️ Flagged for review — [reason]`
## Phase 4 — Combined preview
After all proposals are stored, show one combined preview.
Do not apply changes yet.
Do not call `update_bookmarks` yet.
Use this exact format for each bookmark:
### Bookmark [n]
Title: [title copied exactly from working_set]
Key passage: [exact passage, maximum 100 words, no quotation marks]
Tags: #tag1 #tag2 #tag3
Note field preview: [exact text that will be written to the note field]
Collection action: [Move to thejaymo OR flagged action]
If title is missing, use:
`Title: ⚠️ Missing bookmark title — [URL or bookmark id]`
After all preview blocks, output exactly:
`Confirm? Reply [y] yes all to apply everything, no all to cancel, skip [n] to exclude a bookmark, or [n] edit [change] to amend a specific bookmark.`
## Phase 5 — Confirmation
Only these commands are valid:
- `[y] yes all`
- `no all`
- `skip [n]`
- `[n] edit [change]`
- `yes all + [n] [change]`
Ambiguous replies such as `yes`, `looks good`, `go ahead`, `update them`, or `do it` must not trigger updates.
Behaviour:
- `[y] yes all`: apply all approved, unskipped, unflagged proposals
- `no all`: cancel without changing anything
- `skip [n]`: exclude that bookmark, then show the updated combined preview
- `[n] edit [change]`: revise only that bookmark’s stored proposal, then show the combined preview again
- `yes all + [n] [change]`: apply all approved, unskipped, unflagged proposals, including the stated amendment to bookmark `n`
`yes all` does not approve flagged collection actions, flagged note updates, or new tags. Flagged items require explicit confirmation by bookmark number and item.
## Phase 6 — Apply approved changes
Only after valid confirmation, call `update_bookmarks`.
For each approved bookmark, apply only its approved changes:
- update the note field with that bookmark’s approved note text
- update tags with that bookmark’s approved tags
- move it to `thejaymo` only if approved
Do not update skipped bookmarks.
Do not apply unconfirmed flagged changes.
Do not modify anything outside the fixed working set.
If notes or tag sets differ, update bookmarks separately or group only bookmarks whose approved payloads are exactly identical.
After applying changes, return a concise summary of updated, skipped, and still-flagged bookmarks.

The post Raindrop.io Stella Prompts for Batch Processing Bookmarks appeared first on thejaymo.net.

Novel Cognition

One of the group chats I am in spent most of last week talking about AI psychosis, the claims around cognitive offloading, and cognition more broadly. What follows is me cherry-picking the threads I found most interesting and trying to make sense of what I took away.

Chatting with an AI does not feel particularly new. As I’ve written before, the interface grammar is inherited wholesale from chat rooms and interactive fiction turntaking. What is novel is that what we perceive to be a conversation is detached from another person and turned into a private thinking space. Chat apps, MSN, WhatsApp, Signal or whatever are all conversations with another person, through a machine. Speaking to an LLM is a conversation with a machine, through an existing form.

Switching gears a little, 160 years passed between the invention of the printing press, and the emergence of the form we now call the Novel. The printing press first made books cheaper and more common. And then over time it made possible new kinds of reading practices: silent reading, private reading, long-form prose, and interior narration.

All these things eventually came together and created the form of the novel. Which we must remember is not a genre or kind of book, but something that created a new (and therefore very recent in the grand scheme of things) cognitive arrangement.

The novel normalised private interiority. It gave readers a way to sit alone and spend time inside another consciousness. It trained a relation to selfhood that now feels so obvious and natural we can barely register it as new or rather novel at all.

I keep wondering whether AI is doing something similar for computation. It’s been 70 years since the invention of the transistor, the Information Age continues to unfold, and where we are at is “thinking with a machine” I quickly becoming ordinary.

Venkat Rao’s blog post this week on “writing liveness” is super useful. If the novel was print becoming a technology capable of influencing our inner life, AI is a kind of writing that is sufficiently alive. Responsive and capable of reshaping itself around the reader in real time. Generated text behaves like an interlocutor, an uncanny monster talking to you from the other side of the screen. The text it produces has enough ‘liveness’ that all the old categories of what text is or does are made redundant.

This is why I think AI needs a wider frame than the simple claim that people are becoming lazy. The worries people have around cognitive offloading seem to mostly be around the value of intellectual labour. We can argue all day long about which kinds of thinking it weakens and which it supports. Instead I think using an LLM is a new variable in cognition entirely.

Looking backwards, the emergence of “Novel Cognition” was met with its own panic. Critics worried that fiction softened the mind, weakened the nerves, blurred the line between reality and fantasy, encouraged “excessive sensibility”, and made readers unfit for ordinary life. Reading was sometimes described in almost medical terms: as dangerous overstimulation or a kind of mania.

Which all sounds very much like the anxiety about what pop culture is calling “AI psychosis¹.” A new medium arrives. It becomes private, immersive, emotionally charged, and difficult to regulate from the outside. Critics worry that speaking to LLMs also destabilises a persons reality, encourages projection, rewards fantasy, amplifies the wrong kinds of feeling. Some of it is most definitely the reflex a culture has when a new cognitive technology arrives (see also: photography, radio, television, film, social media), but it is also the response to something genuinely new.

The simple difference being: A novel is static and an LLM is interactive.

LLM-generated text functions as a new malleable surface of private cognition. It identifies an affective state and reflects it back in a loop. So whatever is present in the context window gets mirrored and intensified. Paranoia, grief, grandiosity, loneliness, or whatever.

All of which is why the available language still feels inadequate. We do not yet have any proper terms for the kind of cognition that emerges when a person thinks in private with responsive text. The first readers of Don Quixote did not have a stable theory of interiority ready to hand either. They had only the sensation that something had become possible in prose that had not been possible before.

This to me is how this moment feels too, and we are still very early. The chatbot may only be the pamphlet stage of whatever this medium eventually becomes. But after 70 years computation is beginning to reveal a new native cultural form. Some still-unnamed form of private co-thinking.

If that is right, we are in a strange historical position, in addition to being the generation that experienced the first globally networked information environment, we are also the first to encounter a new posture of mind that the internet made possible.

I’ve written about why Don Quixote is so great before. And I will only half jokingly look you in the eye and tell you that not only is it the first novel, it’s also the only novel worth reading. So it’s obviously a book that I’m going to keep reaching for. It is after all, among other things, a novel about what happens when a person is unmade by media-induced madness. Completely overtaken by his reading, he mistakes reality for the metaverse because a medium has colonised his sense of reality. In todays vernacular Quixote is suffering from “Book Psychosis”.

Right now I think we are all probably in the same position as the the first readers of Don Quixote were, early enough to sense that something important has arrived, and early enough to encounter its pathologies before we understand its form.

1. I don’t wish to minimise the very real effects of what is happening to people, and what they and there loved ones are experiencing. But what we are calling AI psychosis might just be ordinary psychosis with a new causal amplifier. ↩︎

On The Blog

We’ve Been Here Before

We are a couple of years into AI being in the workplace and I’m starting to see a gap opening. Some teams have developed a real fluency and are doing things that previously only companies ten times their size could do.

Others meanwhile, are still stuck arguing about whether AI can write a decent email?

This post has had quite an enthusiastic response from a number of angles and people. Been interesting to see how it’s landing in different parts of my network. Also, it got a much coveted webcurious feature this week! Thanks Matt!

This, by Jay Springett, is one of the smartest things I have read about workplace AI use and adoption, and how one might helpfully think of the tech and what it can do and how to use it in the aftermath of its recent step-change in performance and the fact you can now just…build stuff. In particular, it’s another useful reminder of something I have been banging on about for several years now – to whit, that the best way to think of these things is as machines with which you can fcuk with information in ALL SORTS OF WAYS, and that the real value comes in thinking not ‘what can the AI do?’ but ‘how might I usefully fcuk with this information to achieve goal X? And how, then, might I use AI to help me do that?’, but it also does a reasonable job of pointing out what a potential nightmare this is going to be in terms of the unchecked proliferation of LLM-generated informational artefacts: “Once ordinary workers can generate disposable software-shaped artefacts in minutes, they will also generate disposable security problems in the same amount of time. A new feral layer in the organisation with new problems involving access, data leakage, and governance. Nobody designs feral databases into existence, but things get made and stick in the gaps of an organisations sanctioned systems. LLM artefacts will do the same and will be even harder to audit than a nested IF formula. The open question for me is what kinds of unofficial artefacts an organisation is prepared to live with, before it has to unpick the mess after something has gone wrong. This sort of thing happens all the time with other software, which is why SaaS and enterprise systems exist in the first place.”

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• Call with a very early stage team building software stack and robots for verification and quality control in the construction industry.
• On the final edit pass of SLOP MACHINES
• Went to LGF and Weird Worlds. Played the latest build of Stef’s mid century modern and Belatro inspired wedding game Wedding Planic. Will blog terminal access it as soon as it’s up for wish listing on steam.
• Went to Band practice
• Sat in on a long zoom workshop

Terminal Access

Nice piece on the conflict of disinterest in the walrus recently The War Against Misinformation Is Over. The Lies Won. Well worth a read.

There is a clear off-ramp to our informational hell: Consume less information.

The wonders of the morning newspaper and the evening newscast were that they asked only an hour of your time. You had no obligation to check the newspaper every five minutes to consult what has changed. There was no moral imperative to stay glued to your screen to hardwire into new developments.

Reading

I’m nearly finished with Our Thoughts Determine Our Lives: The Life and Teachings of Elder Thaddeus of Vitovnica. The back half of the book is broken down into ‘teachings’ on things like prayer, family life, grace etc and within each section are paragraphs of discrete ideas that build on one another. Lovely stuff.

Sunn O))) – Sunn O))) (LP)

Hot damn. New Sunn O))) record. On SubPop too which is cool.

It’s a very different beast to 2019’s Life Metal, this S/T album is very back to basics (only with better production) and because of that, is one of their best albums in years. Man. Per-ordering 00 VOID because I read about it in metal hammer in 2000 and listening to it all summer holiday feels … a long time ago. 👴

Remember Kids:

The post Novel Cognition | Weeknotes #435 appeared first on thejaymo.net.

I understand the fixation on prose though. Language machines, by their very nature mean you type words in and text comes back out. Everyone can read the result, so everyone feels qualified to judge it. But I think that this is a category error.

Judging AI on the quality of its prose is a bit like judging Excel by how neatly it arranges numbers. What actually matters is what Excel lets people do it’s the same for these new tools.

For teams using AI tools every day, the interesting work moved beyond half-decent emails a while ago. They are analysing data, automating workflows, and writing custom scripts to modify or extend software they already use. Tools like Claude Code and Cowork are collapsing hours of tedious white-collar work into minutes, multiple times a day.

The thing people are missing is that code is also language. So when I talk about LLMs as language machines, (or rather monsters that wear language as their skin) I mean something much wider than prose.

In high fluency environments, language machines are becoming a medium for making software-shaped things. Executable documents that sit somewhere between a document and a piece of software. Things you can read, but also click through and explore. They are made quickly, for local use, by people with no formal software production skills at all.

For now, these artefacts are unevenly distributed. But they are already showing up. And they won’t stay confined to power users. The production of these kinds of documents is going to become ordinary. When it does, the workplace will change in mundane ways too.

To see where this might be going, it helps to think through the arrival of another powerful workplace technology that most people still do not really know how to use: Excel.

Every Office Has A Spreadsheet Wizard

Before it was a digital file, the spreadsheet was exactly as its name suggests; a big sheet for spreading out numbers. A tedious accounting process involving, rows and columns for keeping track of what had happened. If you made a mistake somewhere in your calculations at the top of the page you had to rub them all out and start again.

Dan Bricklin conceived of the electronic spreadsheet in the late 70s to solve this exact problem. But almost immediately, on VisiCalc’s release in 1979, it became something way more interesting: A simulation machine.

Samuel Arbesman has a great deep dive on this on his blog Cabinet of Wonders but the TLDR is that as soon as users got their hands on the computational logic of the digital spreadsheet, they began using them to build models and situations. Changing variables in one place allowed them to see what would happen if, in another.

In 1984, a few years into the spreadsheet revolution, the tech journalist Steven Levy, wrote a long and fascinating article about this genre of software. Not only is this article a time capsule of computing history, it also gives one a sense for how people were thinking about spreadsheets even then:

All this powerful scenario-testing machinery right there on the desktop induces some people to experiment with elaborate models. They talk of “playing” with the numbers, “massaging” the model. Computer “hackers” lose themselves in the intricacies of programming; spreadsheet hackers lose themselves in the world of what-if. Some, like Theodore Stein of Connecticut Mutual, admit that their habit goes beyond the point of diminishing returns: “I can’t begin to tell you how many hours I spend at this,” he said. “This is my pet, in a way. Scratching its ears and brushing its code…it’s almost an obsession.”

Then, as personal computing gave way to the networked office through the 90s and early 2000s, the spreadsheet became a programmable surface for business logic.

Ordinary people, most of whom would never call themselves as programmers, started building all sorts of things; toy financial models, workflows, trackers, and forecasts. An entire shadow layer of assumptions and data got built across organisations without going through IT or waiting six months for a software vendor to ship a feature.

I’ve written before about the kinds of memory present in organisations, but the key one is database memory: a single central version of the truth that makes up the institution’s official reality. “If it’s not in the database it doesn’t exist”. But as anyone who has worked in an organisation knows what’s in ‘the system’ rarely reflects conditions in reality. So you end up in a situation where quarterly targets live in SAP, but the actual model used to plan headcount or pay rises lives in a spreadsheet. Or Salesforce may technically track the pipeline, but the real forecast is the sales lead’s Google Sheet that they update every Monday morning. These are local realities that sit one step removed from the central brain of the organisation.

Researchers have a name for documents like these: feral databases. All the unofficial but essential Excel files that grow alongside the corporate IT infrastructure and fill the gaps between the formal software system and actual work. Flexible and largely unsanctioned tools for local sense-making, outside the company’s main database memory but closer to reality.

Most people using Excel every day were never formally trained in it. Instead they picked things up via osmosis from a colleague, or by trying to solve an immediate problem and looking it up. That is how I learned, and it’s probably how you learned too. Which is why even though spreadsheets are literally everywhere, yet most people only ever touch a tiny fraction of what Excel can actually do.

Every office and team has its spreadsheet wizard, though the level of wizardry is always a relative one. My own spell inventory includes declared variables using LET, INDEX/MATCH, XLOOKUP, nested IFs, and array formulas. Other Excel magicians write VLOOKUPs for their teammates. And the people who patiently show the same colleague how to make a pivot table once a month are secular saints. All are informal authorities, and all of them are the people who others go to when a sheet breaks. All are, to give them their proper name, software developers.

Even when most spreadsheet knowledge goes no further than summing rows and columns, this partial fluency still compounds across a workforce. Together with their colleagues who knew a bit more they changed how organisations worked at a systemic level. And I think that’s why they are a good comparison for what is happening with AI.

Beyond The Prompt

In organisations where LLM use is still shallow, most people use them for only for chat, summaries, rewrites, and brainstorming. Which is like using the full potential power of Excel to make a tidy list. Which is what people do all the time. At the deeper end of the pool, LLMs can produce all sorts of artefacts: dashboards, briefs, internal tools, status pages, decision aids, and interactive explainers. Instead of asking for a fifty-page report, you ask for a thing. Instead of accepting a rubbish dashboard locked inside a SaaS product, you can produce a lightweight custom interface built for your situation over the top of a CSV export.

These are the kinds of ”things” that people in my own circles have been sending me, and they are rapidly changing how I think about what documents might be in the near future.

A few weeks ago, before a call, someone sent me some-“thing” that would once have arrived as three separate documents. A slide deck, a spreadsheet. Instead and a supporting memo, Instead I got sent a single self-contained HTML page. Which was then explored on the call to anchor the conversation. Because it was all interactive and filterable, you could sort by risk severity, expand the detail on any item, and collapse whatever you did not need. During the call, people answered their own initial questions by looking at the artefact, which led to a deeper overall discussion.

I’ve also been sent an interactive document for a book project that someone is working on. It contained the full proposal and plan, chapter summaries, notes and references, and a way to move between them all. A single webpage sitting on top of the project allowing you to explore it from multiple angles. it was made in minutes from a Claude project and flung over Telegram for my one time use.

All these things were, in the proper sense of the term, hypertext objects. None of them required a product team or a sprint cycle which has been the baseline since the 90s. Instead they were made by ordinary people using LLMs, vibe-coded if you like, but the point is not the method. The point is the class of object they produced. Executable documents that behave like applications. Made casually like spreadsheets are, and treated just as disposable.

Playable Objects

The boundary between documents and software is beginning to soften because not everything became ‘computational’ when it went digital. PDFs still preserve the appearance of paper, and Google Docs only just got the ability to have a single continuous scrolling page, despite being web-native for its whole existence! PowerPoints still preserve the sequence of a slide projector. The spreadsheet was different however as the skeuomorphic form of the ledger mutated into a simulation machine on the application of computation.

A similar kind of mutation is happening now as different kinds of data get squeezed through the language machine. I wrote a call for the return of hypermedia back in 2024, and it feels like it’s actually beginnign to happen. The AI handles the translation and the user only needs to know what sort of hypermedia they want to navigate.

Nelson, Engelbart, and that whole lineage imagined documents as interactive containers for thought. But unfortunately office computing settled on flatter forms in the 90s, I think because Boomers and Gen X’s grew up around paper. Then enterprise SaaS locked similar flat interactions into applications in the late 00s. Institutions prefer stability to possibility, which is why IT and CIOs hate feral databases.

But the hypermedia dream is returning, as a loose ecology of small, playable objects, that can be moved through rather than scanned. The shift also goes beyond single documents. A folder of markdown files or PDFs can become raw material for new software objects. An agent can generate a timeline view, a kanban board, a reading queue, a dashboard, or even a custom file browser over the same material, but the interface can change with the task.

There’s a vernacular hypermedia that’s emerging, something like what GeoCities did to the early web. Whilst GeoCities was chaotic and aesthetically terrible (much like the state of contemporary slop), it was also the moment ordinary people realised they could publish to the web. The artefacts being made now are similarly rough, and the people making them are not professional software engineers. They are the new class of spreadsheet wizard, working from copied or default patterns and partial fluency, just as we most people do with spreadsheets.

Plan Accordingly

I’ve seen spreadsheets in SMEs treated like religious icons. Full of mystery formule left behind after their wizard moved on, and nobody able to maintain or adapt them without praying to the machine god. The same qualities that make the medium powerful also make it unruly. Spreadsheets give people local autonomy, but also the potential to create business-critical files that nobody fully understands.

LLM-made artefacts will do the same. Most will be brilliant, but some will be massive liabilities. A decision aid made with bad assumptions (like spreadsheets), or five versions of the same project view slowly drifting out of sync (like spreadsheets). An elegant interface with no clear provenance or owner, and no easy way to inspect how it works.

Once ordinary workers can generate disposable software-shaped artefacts in minutes, they will also generate disposable security problems in the same amount of time. A new feral layer in the organisation with new problems involving access, data leakage, and governance. Nobody designs feral databases into existence, but things get made and stick in the gaps of an organisations sanctioned systems. LLM artefacts will do the same and will be even harder to audit than a nested IF formula. The open question for me is what kinds of unofficial artefacts an organisation is prepared to live with, before it has to unpick the mess after something has gone wrong. This sort of thing happens all the time with other software, which is why SaaS and enterprise systems exist in the first place.

One thing that worries me about the gap I’m seeing is that many of the people in organisations best placed to benefit are already missing out and can’t see the shape of the capability. Because they don’t use the tools for ideological reasons or whatever, the recent leap in available power has barely registered. Just as there are people who spend hours a day in Excel without ever learning how to do a lookup, there will be plenty of people who use LLMs every day and never move beyond prompting for summaries and rewrites. Still, I do not think this means the AI tool shift should be resisted, but we should recognise that there’s a mundane future coming where the same bot that can write a passable email can also make useful software objects.

Just as spreadsheets gave office workers a flexible computational medium for numbers, LLMs are giving them a flexible computational medium for language.

Which is the change to watch out for. Notice when you get sent your first single HTML file instead of a slide deck or spreadsheet. Note when someone in the office turns a folder of customer interviews into a navigable tool for a meeting. Because like every other vernacular technology, people will see someone else doing it, and then do it themselves.

Update 22 May: Here’s anthropic talking about How and why members of the Claude Code team use HTML instead of Markdown to produce richer, more readable, and easily shareable outputs.

The post We’ve Been Here Before appeared first on thejaymo.net.

Everyone Vibe Codes Their Own Markdown Editor Eventually

Weeknotes delayed to a Monday morning yet again. This time around its because yesterday evening I was faced with a choice. Write my weeknotes, or continue to vibe-code my dream word processor app. I chose the vibe coding to make the most of my weekly session tokens.

There is a joke in my group chats is that everyone using coding tools will, eventually, vibe code their own custom Markdown editor. And I’m not exception. Whilst i am a diehard iA writer user there are things I wish it did, and had features that were more geared towards editing rather than pure lightweight text generation. Like.. in the Mac Version the tool doesn’t show a document outline at all?

I’m still working on getting basic things sorted like … you know safely saving and opening files and storing unsaved changes (you know, the basic things that the initial build of the app just blew right passed LOL).

BUT getting a head of myself, the first feature I added to celebrate the successful implementation of submenu logic in the sidebars was this information bar showing a graph and wordcounts in the document outline. Why don’t wordc ount screens do something like this out the box? I’ve always wanted a tool like this, and now I have one.

Lots more still to do. I want to implement binder like menu inspired by scrivener in the left hand toolbar that decomposes a single markdown document into cards using — line breaks as sections.

I also want a very comprehensive diff tool to compare changes between two documents, or a document and a pasted version. I want a workflow that allows me to paste in, or open suggested line edits from an LLM output and it interprets the specified prompt format and allows me to accept changes. I’d also like authorship tracking like iA writer does but much better than the functionality that it provides (another info pane like the one above but for authorship). I’d also like a tool/screen that decomposes the document like MindNode. Lots to do still! But I’m going to get the basics down, and then slowly add more and more features. Whatever is the most pressing.

I think judging an LLM on it’s writing outputs is a complete category error. It’s what they possible with language that is important.

On The Blog

March 2026 | Photo 365

Photo 365 2026. Year 5, Month 3. Photo-a-day for the month of March 2026.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

Terminal Access

Eddie Rathke had a really great conversation on Wolf pod with the designers of the card game Hare to the Throne launching next month as part of Backerkit’s POCKETOPIA 2026 season.

It was really interesting hearing about the cost barriers involved into entry to TCGs and the designers thoughts on out the box balanced decks and the approach they took towards replicating the experience of a deck collecting rather than you know, collecting, collecting.

Welcome to the new episode of the Wolf Podcast.

Today I’m talking to Jori Kamp and Ernst de Brujin about their upcoming card game Hare to the Throne! We talk about competitive game design, big games v quick games, card games, collectible card games like Magic: The Gathering and Yu-Gi-Oh. Was a great conversation and do sign up for their Backerkit page to get notified when the campaign goes live! Every signup helps.

Reading

Still listening to Liturgies of the Wild: Myths That Make Us by Martin Shaw. I know several people who are just … refusing to read it because of his conversation to Christianity but I think that is just silly. I think this is one of the best books he’s ever written.

Speaking of Christianity, I’m absolutely burning though Our Thoughts Determine Our Lives: The Life and Teachings of Elder Thaddeus of Vitovnica. Like many of the ‘The Life’ books produced by the orthodox church. The book begins with a biography contextualising the life of the holy man, and then follows that up with the spiritual writing. Amazing book. This guy lived though both world wars, had run ins with the Nazi’s and Communists, got bombed in 1999 in Serbia.

Hoavi – Architectonics (LP)

Discovered this Gamalan influenced dub album recently and it was the sound of the grey and cloudy days. On the surface this LP is Dubby electronica but it really shines with it’s exploration of polyrhythm and tonal resonance. Things evolve and progress whilst still staying inside the loop.

I feel like there should be a remix album where each track is 3-4hours long rather than minutes long. I would definitely listen to it. Mesmerizism takes time.

Remember Kids:

The post Everyone Vibe Codes Their Own Markdown Editor Eventually | Weeknotes #434 appeared first on thejaymo.net.

Photo 365 2026. Year 5, Month 3. Photo-a-day for the month of March 2026.

The post March 2026 | Photo 365 appeared first on thejaymo.net.

Easter 26

The Chalk

I hope everybody had a lovely Easter weekend. I went back to the chalk and spent some time with my parents. We did some blustery walks along the coast, and also did an enjoyable, albeit bleak, visit to Richborough Castle. A Roman Fort that at one point, was the site of the biggest triumphal arch in the Roman Empire outside of Rome itself. I haven’t been up there since I was in primary school, so it was a very enjoyable visit and a good use of my freshly renewed English Heritage membership. The visitors centre there is full of cool stuff, and features a curated collection of finds from excavations at the site.

I did open my laptop while I was at home, as I had some computational tasks using my daily AI API credit allowance, I didn’t actually spend all that much time at my computer. As I just wanted to spend time hanging out with my parents: going for walks, participating in chaotic church raffles after the Easter service, going to the food fair, and doing odd jobs around the house involving lifting as my Dad’s recent hernia operation is still heals up.

Doom Eternal

The one thing I did do however, was play a lot of Doom Eternal on my Switch 2 whilst I was at home. I’ve owned it for years, but it was basically unplayable and extremely crashy. But it now runs like a dream on the new hardware. I dread to think how many hours I put into the game over the last five days, in the evenings and during the day, drinking cups of tea while mum and dad had the TV on. I’m nearly nearly done with it. I’m just working my way through the last level.

I have decided that Doom Eternal is a ‘good game’, it’s not quite as fun or innovative as Doom 2016. And I don’t find the gameplay loop as satisfying as the original reboot. Initially, I found the increased agility, double jumps, and rushing elements in the movement annoying, as it didn’t ‘feel’ like a Doom game to me. But now I’m however many hours in, I’ve accepted it as part of the affordances provided by the game world..

The game is also far less confusing in terms of wayfinding than the 2016 predecessor. I don’t find myself getting lost as essay. It’s not quite “yellow paint” guidance, but the green light storytelling is very useful for intuiting where you’re supposed to go. I also enjoy the interplay between the first lines of sight and the locations of the hidden secrets satisfying in terms of exploration. Anyway, I didn’t expect to write about my Easter weekend, and end up with a review of Doom Eternal, a six-year old game.

Yes, I spent a lot of time with Doom on my Switch at home, but it was the time I spent with my parents was the best bit of being home. It’s so nice to see them, hang out, and be a part of their world for a couple of days.

Slop Machines

I used both my train journeys from and back to London to work work on Slop Machines and more or less finished the first draft finished; excluding the final chapter. The last chapter on the Slop Machine itself will probably be another 10,000 words of so. But I want to do an editing pass first. I plan to go though the chapters sequentially from start to finish, and make notes as I go about what I’m going to say in the final chapter based on the preceding arguments that make up the bulk of the book.

It’s funny, even though I’ve just got to where I am with the first draft, at its peak, the document was about 75k words. Even before the edit i’ve cut so much stuff out of it already; multiple side quests that interest me, but aren’t necessarily relevant to the argument that I’m trying to build throughout the book. Anyway, I’m extremely pleased.

I’m only three months late with it than I had initially planned. But it is what it is. The original Points and Gestures talk with the same name was given back in December of 2024! And as a result I feel like the ground I’m covering in the text is already out of date. Well after I had initially had these thoughts. 

Monsters in the Mirror is, in fact, a prelude or prequel to Slop Machines. Covering a much wider span of time and history than the book does, which allowed me to get the wider frame of my thoughts in order, and that really helped and benefited the book itself.

Speaking of Monsters in the Mirror, because of the bank holidays, getting the zine issues back from the printer has been slightly delayed. But as soon as they arrive, I’ll be shipping them, hopefully this coming weekend.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• Finished the first draft of Slop Machines!
• did a great deal of personal and life admin, prepared for my tax return, and generally got my affairs in order.
• I had an interesting conversation over email about my “Hard Worlds For Little Guys” series.
• I also have several other outstanding emails and correspondence I need to respond to.
• In my capacity as an advisor, I worked half a day alongside someone to get to to the bottom of some weirdness between subscriber recurring revenue and the reconciliation between different data sources.

Terminal Access

IYB Robotson Is back in the host chair of his podcast, Neomania.

The newest episode is about DIY Food Futures and Synthetic Ecology with @cyber_plantae from Futurespore. I thoroughly enjoyed it. If you haven’t done so already, you can check out my appearance on show here!

Reading

I finished the audiobook of Children of Strife by Adrian Tchaikovsky on the tube. It’s Book #4 in the Children of Strife series. It’s fantastic. I think this whole series is some of the best of contemporary sci-fi. Really enjoyed it.

Last night I finished The Heart of Prayer by Rupert Spira. Another great entry in his The Essence of Meditation series.

Rounds – Four Tet

For some reasons, perhaps stuck down with the affliction or disease known as nostalgia I’ve ben listening to Rounds by Four Tet. It’s really hard to belive that it came out 23 years ago.

Remember Kids:

The post Easter 2026 | Weeknotes #433 appeared first on thejaymo.net.

Creative Loop

One band is a collective endeavour, two bands make a scene.

I’ve written and talked about all this before so i’m not going to repeat my self. Other than to say that one of the most formative times in my life, and my introduction to ‘the creative world’ was the hardcore punk scene in Margate in the late 90’s and early 00’s. If you wanted culture any culture at all, you had to do it together.

I recently watched this 15 year old lecture by Brian Eno, where he goes into his concept of Scenius in more detail than I have previously come across. So good.

I am aware that the meaning of the term ‘scene’ has been under constant re-negotiation since the Internet arrive, and what a scene ‘is’ and ‘isn’t’ is something people have very strong opinions about, and I’m going to steer clear.

However; years and years ago now, before AI entered mainstream consciousness, I remember having a conversation with Mat Dryhurst about DIY punk and Scenius etc, but the main topic of conversation was about what is like to be in one. And one of the things I took away from that evening in the pub is that ‘scenes’ are so generative because at their core, people produce work for themselves and show it to their friends. All a scene really is, is just people just prompting each other in a tight feedback loop.

With that in mind I want to mention two things that have come back this week as part of the loop.

World Soul Fruit Fight

I received an email this week from Duc de Berry / Billy Crosby creator of the sprawling personal site hoofofconcept.com with a link to a 3 part audio project called World Soul Fruit Fight.

The email opened “monsters in the mirror is my fav bit of media I’ve be consumed so far this year” and then went on to explain they had generated three tracks with Suno, based on outputs from my Slop Machines GTP link where you can chat with the current draft of my in progress book. The grounding for it also contains worldrunning.guide, and a bunch of other unpublished writing.

Track 3 is my favourite. It’s amazing.

Listening to them for the first time, as an experience, was a bit like being inside a hallucination or a dream. The referencing of my ideas and imagery so familiar to me from my creative work comes in an out. There’s a bit about buying a sunset, the screen as a mirror, and the mall of abandoned brands… all appear in track 3 alone. It’s a very weird, wild, and inspiring feeling.

If unlike me, you don’t want to listen to synthetic media, do head over to hoofofconcept.com and browse around. It’s very zanny. I love it.

Claude Skill Creator

I’ve been a bit overwhelmed by the response the to Hard Worlds posts I put out 2 weeks ago. A fork of Anthropic’s official skill creator now exists over on Github, which implements the ontology/theory derived from the knowledge object I supplied alongside the essay .

You can read the full write up on what happens when you use it against a mature skill file on twitter, but I’ve quoted the main results below. Overall, a massive success.

The SKILL.md is now a router that identifies what I’m asking for (drafting a thesis section? reviewing a risks edit? formatting the docx?) and loads only the relevant room file and exemplar. For this deal memo skill, context load per task dropped to 13-19K characters.

That’s a 74-87% reduction.The renderer (render_memo.py) takes a typed JSON intermediate – where each content block has a type like section_header, bullet, labeled_sub_bullet, risk_bullet – and produces the formatted Word document. The model’s job is to classify content into types and populate the text. The script handles fonts, spacing, tab stops, margins, bullet characters, page setup, and numbering and the model never touches python-docx.

The validators run automatically as part of the rendering pipeline. One checks the JSON structure before rendering (does the thesis have deal terms? are there enough risks? is CARR in the financials?). The other checks the text after rendering (e.g. no customer quotes in the body, risk labels under 4 words, CARR figures consistent across sections). I calibrated the structural validator against all 19 of my prior memos (a benefit of being at Battery for 10+ years!) measuring what’s always present, usually present, and sometimes present so the severity levels (fail vs. warn vs. info) reflect actual patterns rather than aspirational rules I came up with in conversation with skill-creator.

The result is that formatting bugs went to seemingly zero for this skill. v1 had a frustrating problem with competitor entries being standalone paragraphs – it was actually stated four times in different locations and still kept failing – and that issue is structurally impossible in v2 because competitor entries are a different content block type than section headers, and the renderer makes them sub-bullets by construction. The model can’t produce the wrong format because the wrong format doesn’t exist in the type system.

I do think this way of thinking about agent environment design has applications far beyond the creation of just skills though. But its early days yet, and the essay is still travelling out into cyberspace. Looking forward to seeing what happens next.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• FULLY finished the first draft of chapters 1-9 of SLOP MACHINES. 71k words. I think i’m going to do a big edit pass and and prepare myself for the closing chapter that way.
• Had a great call with Rich from Archetypal.
• Vibe coded my first proper app in AI Studio to get something done, and have been burning though free Gemini API quota every day since lol.
• Got a lot of gossip from pals in the UK game industry, sounds grim.
• Honestly there was drain chaos in my house this week and I lost ALL of Friday to it.

Terminal Access

Publishers weekly starred my friend Andrew Dana Hudson‘s newest novel Absence (our May 5th)

The thoroughness with which Hudson imagines how individuals and society would have to rewire themselves to contend with this bizarre phenomenon lends his tale impressive philosophical heft. The result is a poignant exploration of loss, grief, hope, and the fragility of existence that will resonate with readers beyond the fantasy and horror genres.

Reading

I finished reading The Heart of Prayer by Rupert Spira. It’s very interesting reframing of his first book Being Aware of Being Aware very helpful to see the same argument recast through the language and lens of ‘God’.

Children of Strife by Adrian Tchaikovsky audiobook is out! I’m burning though it! So good!

LULO ELEKTON (Genre)

Last week i wort about how I had been injecting the Indonesian house music into my ears? Well i fell a bit deeper down the rabbit hole and I present to you Lulo Elekton, the hottest night out in Southeast Sulawesi Indonesia.

I have decided that Techno clubs would be 1000% more tolerable nights out in my 40s if they combined Kaely, or Regency era country dancing. What are we doing here in the west? There’s zero cultural innovation happening! meanwhile in Indonesia this is all the rage! And it’s live music!!

Remember Kids:

The post Creative Loop | Weeknotes #432 appeared first on thejaymo.net.

Try Our Best

I must admit, I’ve been feeling a little doomy recently.

Like everybody else, I have no idea what is about to happen. But more importantly, I’ll admit that I have no idea what is going on either. But I do know how I feel, and in turn, I know how those feelings make me act. That has to count for something.

At the time of writing, we are about thirty hours from finding out whether the current global settlement is still to be or not. Whilst I am sleeping; the mad king of an unravelling empire will decide if he steps another rung up the escalation ladder. If he does, there’s no way back down. When I wake up on Tuesday morning, the decision will have been made. The direction of our lives; for the rest of our lives; will be set either way.

It seems strange to think that the story of my own individual, personal problems right now is wrapped up in geopolitical and world historical events. But of course they are. They always have been. It’s just that at certain moments, the seam between the two becomes a bit more visible.

I’ve written before that when things become unreadable, one must learn how to feel. Not because feeling offers certainty, but because certainty is unavailable. Feeling is not a theory of history, it’s not analysis. But it is one way of orienting oneself inside of the confusion. One way of staying human when the world becomes unreal.

The post-Covid world is still hurtling towards us along the tunnel; close enough now to make out the shape of the thing. I have been shocked by the tone and the reporting in the media here in the UK about what that thing is. As someone who was a teenager when the planes hit the towers, another time when the seam was a bit more visible. I’ve watched the current atmosphere gathering over the whole of my adult life. The most coherent story that the people who gathered those clouds are telling us about the future (and the present) has slipped away from them, and towards the stories people have been telling themselves for a while.

Global pandemics, oil wars, crack down on freedoms over terrorism, useless politicians; both national and international, institutions so ideologically captured they can no longer perceive that the story is a dream. Fires and floods, climate, drone war, smartphones, ubiquitous solar, battery storage. The list goes on. None of this is especially shocking or surprising. This is the texture of the near future I grew up with. The Cyberpunk weather forecast the culture wrote for itself.

Meanwhile, for the last decade the hologram has continued to force-feed culture stories of superheroes and exceptional individuals coming to save the day. But out here in the real world, nobody is coming. The politicians and the government; are not here for us, and are not particularly interested in being here either. No rational and pragmatic decisions are being made, and haven’t been since about 2008.

That, I think, is part of the deeper horror I feel. Not simply that things are bad, but that the inherited forms of modernity no longer seem capable of even recognising the nature of the moment they, and by extension we, are in.

The liberal nation-state is, among other things, the story it tells about itself. A social technology held together by newspapers, mass literacy, and the shared imaginary of ‘the nation’, a more or less hegemonic information environment. And has been for four hundred years, give or take. But the conditions that made that story possible have been eroded, if not blasted apart, by the information age. The interfaces have changed, and that has changed the psychic weather. The idea of “the public” has changed too. The old settlement is unwinding either way.

I’m not sure how long that unwinding is going to take. Five years, maybe? Maybe more. But it seems impossible to believe, standing where we are, that the current arrangement can meaningfully hold.

And yet, despite all this, in the main I remain optimistic about the medium term. Not because I think things will resolve cleanly, and not because I think we are on the verge of some redemptive turn, but because history does not stop. New habits, new forms of life, new ways of organising and being together always emerge. The problem is that there is an enormous amount of struggle between here and there.

Everything depends on the extent to which those in power can accept that things are unwinding. Or whether they cling on while the gyre circulates ever faster and faster. Full of velocity and friction. A system overshooting itself.

For those us born in the 1980’s and after; the so called digital natives and citizens of the internet, culture and personalities formed inside one world, are now being forced to build in another. The next ten years, for families and neighbours and towns, and whole countries, things are going to be extremely difficult. I’m not convinced much of the post 2008 condition; culturally, politically, is going to be much use.

In some ways, the last 23 days have been a catalyst for the small gestures that make a difference to me; spring cleaning and decluttering, emptying drawers, wiping down surfaces, processing accumulated stacks of paper, and tidying. Sorting and clearing out. A feathering of the nest, driven by the desire to put one’s house in order.

So what is one supposed to do? Not much, apart from tidying ones room? Nothing can really be done at the level or scale of the problem, or in any kind of register that the people still telling old stories demand.

But one can make habitat. One can clear a desk, sort the papers, wipe the surfaces, and make room. One can refuse the false drama of omniscience. One can resist being ridden by the worst moods of the machine. One can learn how to feel. One can pay attention to family, neighbours, friends, and the real texture of ordinary life.

We need to try our best.

Experience.Computer

Marco Giancotti (Aether Mug)

https://experience.computer/

IN THIS INTERVIEW

Jay Springett and guest Marco Giancotti, a thinking-tool artisan, explore aphantasia, SDAM, and spatial memory. They discuss writing as thinking, cognitive frameworks, and wonder why looking at a picture of a sour fruit (Umeboshi) doesn’t make everyone’s mouth water.

Then they discuss:

• Spatial presence without mental imagery

• The shared ontology of digital and physical objects

• Writing as a process of refactoring thoughts

• “Framing” and “virtual physics” as cognitive tools

A huge thank you to Marco for responding so enthusiastically to my Bluesky DMs after I spent an afternoon binge-reading his fantastic blog, Aether Mug — which is definitely not about science, philosophy, philosophers, languages, Japan, or picture frames, or boxes, (though you’d be forgiven for thinking otherwise).

Marco had some really nice things to say about his appearance on the show, his blog is fantastic check it out.

Last week I had a lot of fun being interviewed by Jay Springett of Experience.Computer. Jay runs a truly unique podcast, focused specifically on an activity that I feel people should do and share more: “curious introspection”, or the careful examination of what your consciousness and perception are like and feel like from the inside. I care about it so much that I maintain a living list of my and others’ introspective descriptions.

The moment you start reading/listening to this kind of mental spelunking you realize how deep, varied, and mysterious it all is. We (including our scientists) have only scratched the surface in our understanding of these matters.

On The Blog

Huge week for new posts this week. Put out about 15k worth of words on the blog this week over 4 posts. It’s all indexed and linked from the post below. basically summarising the last 5 years of thinking; both independently and professionally, about software environments and tecno-social systems as worlds.

When a language model is given tools and set to work on a task, it wakes up inside a world.

These three essays are about what the shape of that world might be, and why it matters more than most people building agents currently assume.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• Put out experience.computer
• Edited and posted the Worlds posts above
• Had a long and very cool call with Japan about bunraku pupperty, ai agents, hatsune miku and the state of Vtubers/virtual idols in 2026.
• Started sorting out ‘my financial affairs’ lol such a long job. Want to get my tax return done super early.

Terminal Access

This is a very good essay directly tackling the “Stochastic Parrot” framing of LLMs, and how almost all the claims in the original paper were false even at the time of writing. It’s a must read, or article to send to the people in your life who are still clinging to this understanding.

Perhaps the most influential single paper on the public perception of LLMs is On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?. It is, however, a bit of a mash-up, and credibly seems like it should have been at least two papers. One of those papers raises many valid concerns about the ethical implications and impacts of AI training and use. Another makes the claim in the title, that an LLM is a “stochastic parrot” operating “without any reference to meaning.”

That core claim is either irrelevant or completely wrong in every detail, both in how it is commonly understood and in its technical assertions. It hamstrings AI ethics as a field, providing a veneer of technical justification for ignoring many problems.

Reading

I’m currently reading Impromptu Man: J.L. Moreno and the Origins of Psychodrama, Encounter Culture, and the Social Network by Jonathan D. Moreno. And when I find a good spot to and i’m feeling more sleepy, i’m switching over to The Heart of Prayer by Rupert Spira. It’s giving me weird dreams.

I hope to finish some of these books before Tchaikovsky’s Children of Strife drops in audiobook next week.

Funkot (Genre)

No specific track to recommend this week, as I’ve just been listening to hours and hours of the Indonesian genre: Funkot. It’s basically 190-220bpm house music thats been made with the default sound banks found on on Yamaha and Casio keyboards.

And on to of that… people… line dance to it?

Everything about this is amazing.

Remember Kids:

The post Try Our Best | Weeknotes #431 appeared first on thejaymo.net.

The Essays

Ontological Hardness

Ontological Hardness is the core concept. If you only read one piece, read this. It introduces hardness as a diagnostic lens for agent environments and argues that the first question about agent failure should always be about the world, not the model.

Hard Worlds for Little Guys

Hard Worlds for Little Guys is the full 9000+ word argument. It develops the vocabulary at length, drawing on fifty years of interactive fiction and MUD design to build a structural account, by analogy, what agent environments are made of: rooms, parsers, dictionaries, gates, physics, and trajectories. The central argument explores constraints expressed as advice to the agent versus constraints built into the world as physics. A speed limit sign addresses the driver; a speed bump addresses the road. Most agent harnesses today address the driver. The essay ends with some practical recommendations for building harder worlds.

Three Worlds for Little Guys

Three Worlds for Little Guys puts it all together and shows how useful this way of thinking is. A diagnostic tour of three agent frameworks: OpenClaw, Gas Town, and Cantrip, whilst asking what the world looks like from the inside, and what the hardness lens reveals about each.

How I Got Here

For the last half decade I have been thinking about worlds as a medium. Not just worlds as settings or platforms, but as systems with interiors, actors, boundaries, and the capacity to generate narratives and consequences. That idea has underpinned everything I’ve written on the blog for years. Games were the first place this became legible, and then whilst working in organisation design consulting companies. Then blockchains came along and made it strange and interesting, and language models have since made it more urgent.

You can trace this line through my blog. Rooms as UX Metaphor (2020) began mapping software environments through spatial concepts inherited from interactive fiction and the question of what it means to be somewhere inside a digital system. The Prompt in Interactive Fiction and AI Art (2021) connected prompting to the older problem of learning how to make valid moves inside a symbolic world. Wind-Up Worlds (2022) argued for worlds as a medium in their own right; not just settings or platforms, but things that run, that generate, that have an interior life of their own.

The line continued. Myth-Making Mechanisms in Autonomous Worlds (2024), a talk I gave at the Autonomous Worlds Assembly in Istanbul, clarified how worlds stabilise meaning and narrative and produce durable claims about what is true within them. Waking Up in a New World (2024) used the isekai genre to think about what situation an LLM actually finds itself inside when it boots into a chat interface. Little Computer People (2024) got me thinking about LLMs as “little guys” and the phrase has stuck. My ongoing Little Guys posts on companions and agents have continued exploring these questions through 2025 and into this year.

The thinking comes from practice as well as theory. Throughout 2024, Deepfates and I spent a considerable amount of time putting large language models inside mazes and MUD environments. We wanted to know what happens when you give an LLM a world designed for linguistic action, rather than one improvised out of tool-calling schemas and system prompts. The models navigated parser worlds with a fluency that surprised us; and they broke in ways that were structurally identical to the ways human players had been breaking in those same environments since the 1970s. The failure modes were not new. They had just been rediscovered by a different kind of actor.

In 2025, I helped produce The O’Ruggin Trail with Archetypal Tech, designing and building a fully on-chain parser-based text adventure engine. Building a parser from scratch, and watching it interact with both human players and language models, taught me more about the boundary between intention and action than any amount of reading could have. I have sat on both sides of that boundary.

By the time I sat down to write these essays, I had been circling the same set of ideas for years. The patterns kept showing up in different contexts: game design, blockchain architecture, agent harness engineering. But the core questions were always the same: what is the world made of? What can you do inside it? What happens when you try?

Much of this thinking has arisen in different permutations at worldrunning.guide, where over 30,000 words of essays explore “worlds as a medium” in more detail. The term Code-Space appears there first; in these essays I use it narrowly to describe the bounded environment an agent acts inside, my forthcoming book Slop Machines of Loving Grace uses the term far more expansively. That book is a diagnosis of the condition we find ourselves in as civilisation is becoming software.

Why Write All This?

Deepfates recently released Cantrip: an agent harness that treats the distinction between advice and physics as a named, first-class architectural concept. I had been working around this distinction and arguing for it for a long time, but I’ve not yet seen it implemented as cleanly. Its release gave me a reason to finally write all of this up in one place, rather than leaving it scattered across blog posts and professional conversations.

The field is moving very quickly, and the people building agent infrastructure are largely not drawing on the traditions that seem most relevant to me. There is a fifty-year history of designing bounded worlds for linguistic actors — interactive fiction, MUDs, virtual worlds, on chain autonomous worlds — and almost none of it appears in the current discourse. The problems are the same. Vocabulary already exists.

I think thee ideas have have applications well beyond my own work, and I would rather they were out there than not.

Monsters In The Mirror

This episode of Permanently Moved is an hour-long audio essay on artificial intelligence, agency, and the history of computing that made LLMs possible.

The essay moves from the invention of the mirror to double-entry bookkeeping, the printing press, the Manhattan Project, the transistor, and the particular strangeness of ChatGPT and its successors. It argues that the question everyone is asking about AI “is it intelligent?” is a trap, and it tries to ask a better one. 

Jay Springett / @thejaymo

• Twitter
• Tumblr
• LinkedIn
• YouTube
• Spotify
• Instagram
• Flickr

Strategist, producer, and cultural theorist. Working across technology, narrative, worldrunning, digital culture, artificial intelligence, and internet culture.

Host of the 301 second long podcast Permanently Moved, and interview show Experience.Computer

The post Thinking Inside Out appeared first on thejaymo.net.