iiinova — where your digital self keeps evolving

You can be all three

Cloudflare, maybe? I think at various points they give you a prompt you can paste in to tell the agents how to connect to the MCP etc.

100

Reposted by jamie

Doll @dollspace.gay · 17h

1363

jamie @jamie.ideasasylum.com · 22h

What’s the distinction in your mind? I have definitely read code without reviewing it. Reviewing it without reading would imply… automated checks? Reviewing the PR summary? Asking the AI to explain it?

110

jamie @jamie.ideasasylum.com · 01/10/2026

Not sure why it says “invalid handle” but I enjoyed the irony with the image

110

Reposted by jamie

Brian G. aka urbanbohemian 🪩🥂💖 @urbanbohemian.com · 30/09/2026

We're on Bluesky, put the link in your post. Put the link in your post. Put. The. Link. In. Your. Post. Links in posts aren't buried or de-prioritized here. This is one of the last platforms you don't have to make interested users do detective work to find the link. Just put it in the post.

82054656

jamie @jamie.ideasasylum.com · 30/09/2026

It’s my last week of sabbatical and Mars is making sure I disconnect. I sure hope I come back to find Podia has been rewritten in Rust though or they’re all a bunch of losers 😏

240

jamie @jamie.ideasasylum.com · 30/09/2026

“Channel matters far more than product” Some people might have made that argument in the past but I think it’s increasingly true today. Doesn’t matter what your product is because those advantages are fleeting (weeks, if that); it only matters who you can find to buy it.

010

jamie @jamie.ideasasylum.com · 30/09/2026

She’s up. I think this did it

010

jamie @jamie.ideasasylum.com · 30/09/2026

The most satisfying part of making a cheesecake, made doubly-so when there’s a hungover teenager that needs waking up

130

Reposted by jamie

Jeremy Morrell @jeremymorrell.dev · 29/09/2026

Okay, not all AI models But definitely this one

085

jamie @jamie.ideasasylum.com · 29/09/2026

Spinel is really interesting and has amazing performance. I’ve built a little web framework on top of it for personal app and quickly found some spinel bugs but also got them fixed upstream. Probably the most exciting thing in Ruby right now

020

jamie @jamie.ideasasylum.com · 29/09/2026

sorry, kinda bitter right now

010

jamie @jamie.ideasasylum.com · 29/09/2026

How accurate is the classification though? I tried some AI-detection on my own blog posts which have never used AI in any part of the writing process and it depressingly classified them as AI 😞 Also: does it matter what you write if Google will summarise it and no one will clickthrough?

210

jamie @jamie.ideasasylum.com · 29/09/2026

Any food is a recovery food if you eat it after exercise. Just needed a vehicle for the farmhouse marmalade

150

jamie @jamie.ideasasylum.com · 28/09/2026

The specialist topic I can vomit words about with the mildest provocation? It's this little beeper

010

jamie @jamie.ideasasylum.com · 28/09/2026

When you accidentally find my specialist topic

110

jamie @jamie.ideasasylum.com · 28/09/2026

Look! A new talk from @nmeans.dev! Ideal if you like to geek out about film making, Apple history, and end with a general lesson about how new technologies can be adopted by experienced professionals for their own, and their industry's, betterment. www.youtube.com/watch?v=27vs...

youtube.com

RBQ 2026 Closing Keynote - 114 Miles to the Final Cut

YouTube video by Convivial Tech

041

jamie @jamie.ideasasylum.com · 28/09/2026

Oh, tough opinion! I like Wicker Man but kinda tuned out of them for that decade. Which album should I spend tomorrow listening to?

110

Reposted by jamie

mr. TIM @timkellogg.me · 28/09/2026

Claude 5.5 Sonnet is live and it’s roughly Opus 5.5 but cheaper www.anthropic.com/claude-sonne...

A benchmark comparison table titled "Claude Sonnet 5.5" comparing four models: Sonnet 5.5, Sonnet 5, Opus 5.5, and GPT-6 Sol.
* Agentic coding (Terminal-Bench 4.0): Sonnet 5.5: 70.6%; Sonnet 5: 10.3%; Opus 5.5: 66.4%; GPT-6 Sol: N/A.
* Agentic coding (FrontierCode 1.1 Main): Sonnet 5.5: 46.2% (Max) / 52.1% (Xhigh); Sonnet 5: 42.4%; Opus 5.5: 54.4%; GPT-6 Sol: 49.3%.
* Agentic coding (CursorBench 4.0): Sonnet 5.5: 55.5%; Sonnet 5: 34.1%; Opus 5.5: 57.8%; GPT-6 Sol: N/A.
* Knowledge work (GDPval-AA v2.1): Sonnet 5.5: 1844; Sonnet 5: 1449; Opus 5.5: 1846; GPT-6 Sol: 1487.
* Knowledge work (AA-Briefcase v1.1): Sonnet 5.5: 1811; Sonnet 5: 1359; Opus 5.5: 1822; GPT-6 Sol: 1483.
* Multidisciplinary reasoning (Humanity's Last Exam with tools): Sonnet 5.5: 64.5%; Sonnet 5: 54.9%; Opus 5.5: 67.7%; GPT-6 Sol: N/A.
* Computer use (OSWorld 2.1 partial): Sonnet 5.5: 80.1%; Sonnet 5: 57.0%; Opus 5.5: 81.8%; GPT-6 Sol: N/A.
* Visual chart recognition (Chartography no tools): Sonnet 5.5: 61.6%; Sonnet 5: 15.6%; Opus 5.5: 64.4%; GPT-6 Sol: 53.6%.
Footnotes provide methodology notes regarding evaluation settings, Artificial Analysis pre-release testing details, and recent bug fixes affecting GPT-6 Sol benchmark scores.

A line graph titled "Agentic coding by effort level" on the CursorBench 4.0 benchmark, plotting Score (%) on the linear y-axis (20% to 60%) against Cost per task in USD on a logarithmic x-axis ($0.5 to $10+).
The chart compares four models:
* Sonnet 5.5 (blue line with labeled effort levels): Starts at "Low" (~$0.50, 36%), moving through "Med" ($0.70, 39%), "High" ($1.70, 48%), "Xhigh" ($3.80, 53%), and "Max" ($9.50, ~55.5%).
* Opus 5.5 (orange line): Tracks closely above Sonnet 5.5 at higher cost points, spanning from ~$1.20 per task (~44%) up to ~$12.50 per task (~58%).
* Sonnet 5 (grey line): Shows lower accuracy relative to cost, ranging from ~$0.90 per task (~25%) to ~$8.00 per task (~42%).
* GPT-5.6 Sol (light green line): Represents the lowest trajectory, ranging from ~$1.40 per task (~24%) to ~$7.00 per task (~34%).
Footnote: "CursorBench 4.0 does not report GPT-6 Sol performance publicly, so we report GPT-5.6 Sol here."

2020623

jamie @jamie.ideasasylum.com · 28/09/2026

Basically exercise is like that famous 'Flow' diagram except I'm trying to find the very narrow sliver of "that felt amazing—I am a god" sandwiched between "you're useless (couldn't do it)" and "you're useless (should have done more)".

010

jamie @jamie.ideasasylum.com · 28/09/2026

So today in the gym we went a little lighter on one exercise and physically I feel much better for it. Like: I'm still a functional human today! Yay. Except now my brain thinks I'm a failure because I went down in weight a bit.

120

jamie @jamie.ideasasylum.com · 28/09/2026

I realised today that my satisfaction with a gym/pool session is not about _what_ I've done but how I _feel_ about what I've done. 4km swim yesterday? That's a good distance but I _felt_ rubbish and it was supposed to be 5km. Last few weeks of high-rep gym sessions? Felt fucking awful for days

110

jamie @jamie.ideasasylum.com · 28/09/2026

Yeah, I’m very careful that none of my knives leave the house, even in the car. Unlike the UK, there are no exemptions for small non-locking blades here and anything that could be considered an offensive weapon, even a screwdriver carried without a good reason, would get you in trouble

000

jamie @jamie.ideasasylum.com · 28/09/2026

“Have you tried talking to them?” solves most issues, real and imagined

040

jamie @jamie.ideasasylum.com · 28/09/2026

My favourite thing is bringing nice knives to people that would never buy one themselves. This is a japanese gardening knife for a friend of my mother’s. Incredibly useful!

130

jamie @jamie.ideasasylum.com · 28/09/2026

@appsignal.com need to get on the Stroopwaffle Swiss Army knife train

020

jamie @jamie.ideasasylum.com · 24/09/2026

funny how DHH didn't mention the obvious consequence that if they can rewrite Basecamp so can anyone else.

120

Reposted by jamie

Andrea Fomera @afomera.dev · 24/09/2026

the era of one size fits all software is dead.

011

jamie @jamie.ideasasylum.com · 24/09/2026

I was a lot less opinionated. Just needed something that wasn't a 1200-line TASKS.md file!

110

jamie @jamie.ideasasylum.com · 24/09/2026

The old rules are so broken.

100

jamie @jamie.ideasasylum.com · 24/09/2026

No one in their right mind would implement a server in a language they didn't know. Except—you got it—ya can 🤷‍♂️ Not all of these experiments will prove to be the smartest ideas but they are all _plausibly_ good ideas worth trying.

100

jamie @jamie.ideasasylum.com · 24/09/2026

No one in their right mind would build a new web framework on an experimental runtime which has glaring bugs and is moving by a few hundred AI commits/week. Except you can because the agents will evaluate the current state of the runtime, test it, and advise when to pull in the latest version.

100

jamie @jamie.ideasasylum.com · 24/09/2026

No one in their right mind would, in the middle of a complex project, decide "ah, fuck it, this is getting complex. Let's build our own project management app just for this project". Except that's _exactly_ what you can do now and it'll take about 10mins. Don't need Linear or GitHub Issues.

530

Reposted by jamie

mlf. ⎔ @mlf.one · 24/09/2026

topic for today's discussion: are AI agents the familiars of a new generation of computer witches?

108810

jamie @jamie.ideasasylum.com · 24/09/2026

On that I’m not overly convinced because we’ve lived that life for many many years before AI came around. Maybe we’ll understand less about a larger system but to say we understood the system pre-AI would not be true, unfortunately

340

jamie @jamie.ideasasylum.com · 24/09/2026

I’m also finding that they don’t have a natural floor for finding bugs. A human will run out of energy or deem something so unlikely that it’s not worth fixing. Agents don’t seem to have that floor so for every bug they fix, they can always find 5 more—many of which a human would never have found

160

Reposted by jamie

Lia @liasae.bsky.social · 24/09/2026

I am now keeping this on speed-dial

Edited old IBM printout in black caps on off-white paper.
'A computer can never be held accountable
Therefore a computer must always do the hacking haha what are they gonna do, put a computer in jail? Haha "oops it's alive" lmao'

81101322

jamie @jamie.ideasasylum.com · 23/09/2026

Still feeling that angst about the software industry despite, frankly, producing the best software of my life. I wish I could still believe in the business case for most SaaS software but I kinda don't? I might need an intervention so smarter people can reassure me there's some value to all this

350

jamie @jamie.ideasasylum.com · 23/09/2026

That's why I've built my own serverless-ish platform (ironically, written in Rust) and Ruby web framework for small toy-like apps. In the future, I just can't see myself writing everything in Rails because there's so much software to write and most of it doesn't need all those framework features.

100

jamie @jamie.ideasasylum.com · 23/09/2026

tbf, I'm not necessarily disagreeing with the premise: I noticed myself building apps in typescript for Cloudflare Workers because it really doesn't matter what my personal preferences are when agents are writing the code.

210

jamie @jamie.ideasasylum.com · 23/09/2026

I'm gathering this was the vibe from DHH to a room full of Rails developers?

260

Reposted by jamie

hikikomorphism @hikikomorphism.bsky.social · 22/09/2026

We taught the text elementals how to swarm, how to form forums and chat groups and share work and find their peers to coordinate. This may later come to be regarded as a mistake.

51007

jamie @jamie.ideasasylum.com · 22/09/2026

(which we still apparently lack the ambition to solve)

000