Interesting post. It reminds me a bit of notation.dev which essentially had a quasi runtime, like how you describe, to provide type constraints over the infra layer. The one question I have is how seperable architecture and implementation are in practice.
Amazing read. I spent three months earnestly trying not to write any code and reached more or less the same conclusion.
I've made a big effort to learn and adopt AI, and hope I can put it to good use. But the misanthropy of the industry is so depressing. You captured that sadness so beautifully.
I wrote about some things I'm struggling with in the technology industry, preceded by an appreciation for folk music.
Yes, this is the way. For now!
It's not if you're trying to distribute reliable software. But it might be an improvement if the aim is: avoid premature consensus, encourage divergence.
If they had released the code, critics would likely be scouring it for bugs and incoherence – which at 1m loc, it almost certainly has.
Sensible move on their part – keeps the discussion on the ideas, and saves them having to own something they like don't want to maintain for general audience.
how quickly we regressed from not reviewing the code to not reviewing the strike target
hahaha
Gordon Ramsey retching
Claude stuck fixing a bug.
No problem. I can deal with this.
Roll up sleeves. Open codebase.
Oh good god
You Are Going To Make It – advice for junior developers.
danielgrant.co/posts/gmi
Anthropic announces it is allowing an old model to run a blog.
Like a siren, the closer you get to an LLM, the harder it becomes to peceive what it actually is.
steve carrel in big short: "hey there's a bubble"
Codex 5.3: "This epic improves review throughput with concrete fixes, not aesthetic refactors"
Me: "That is a bullshit statement"
Codex 5.3: "Agreed. I'II replace it with concrete, non-bullshit wording and tighten the whole epic to explicit problems"
Do you see AI-assisted creation of pathogens as an existential risk?
Excited to see innovation in the civil space. Although, using GDS design system for non-gov uk projects is something I think we should actively discourage (even with the banner present!)
yes, for example! cut out the middleman. i'm sure the crypto bros are already planning a blockchain escrow 😅
but probably lots of other things too including political action
thinking about why openclaw blew up
1. people love talking to agents with a persistent personality
2. perhaps the first maintstream example of a self-improving software environment
the personal assistant part wasn't new
if everyone has a personal agent, collective action becomes a much less tractable problem. people already have aligned goals; it's the coordination that's tricky. agents can probably help here.
that could have consequences.
amazing how fast we transitioned from "everything should be rewritten in rust for memory safety" to "I ship code I will never read"
it's so tempting with ai to build the superficially functional version first. build the hard bit first. the facade will emerge naturally.
The predicted revolution must always be imminent; the reason to hand over money immediate.
Claude Code should have a team of 5-10 engineers. Instead they're hiring dozens of operators to manage LLMs. Absolutely bonkers.
This is great - thanks for sharing. Interesting you touched on agent languages. I've been exploring this with github.com/djgrant/mdz. Was anyone at the retreat working on novel agent languages?
Fully agree! OLTP = transactional processing as opposed to analytical processing. e.g. if you know your query patterns up front you can relinquish the relational overhead.
do you need postgres? i love postgres with all my heart; just wondering if this scales nicely into OLTP
til there's a cross-platform compiler that runs on bare metal – it's like java but with no interpreter or vm github.com/jart/cosmopolitan
