It's partly a problem because the narrative is still "rewrote Bun in Rust in 11 days". And they didn't do that, if you consider quality of code. And now people look and see "look what you can do with an LLM in 11 days"
Been there done that. My point is that even with Fable being a big improvement, it still needs constant feedback.
The loops themselves are a lot better, but it still needs judgement calls, and Fable will often take an odd direction, and if you don't catch it, that odd choice will compound as it continues to layer on top.
The problem is the _way_ AI will solve an AI bug. I've seen the loop countless times. There's a creeping complexity and brittleness that creeps in over time as more and more complexity is left purely to the LLM agent. It will become unsustainable without a human understanding and making course corrections at some point.
> What is explicitly not done yet — this is the active roadmap, in order:
> CPython test suite (cpython-full): the standing grind; failures are clustered and burned down per wave.
I was trying to say "not confident at all" but hedged a bit too much.
I see this as a case of the "quick to get to a POC that falls apart after sustained development for the same reasons it didn't work pre-Fable" problem.
I hate to be that guy, but... one week old project, clear signs of vibing. I will be shocked if the remaining work listed (cpython test suite) proceeds in any reasonable timeline.
This is a pretty hard problem to just solve in a week.
EDIT: and man, these kind of comments LLM created comments are really starting to grind my gears as my job slowly turns into reviewing LLM PRs:
> Known gaps at the language level are burned down through the ratcheted floors above — the committed floor files, not this README, are the authoritative compatibility baseline.
I love postgres, but the complexity of using it for everything starts to get pretty high, compared to more tailor-suited tools. We should probably use it for _more_, in general, but the cost of "everything in postgres" is generally higher than I see acknowledged in articles like these.
I'm not wading into the schizophrenia part, but inner monologue doesn't necessarily imply constructing a fully formed sentence you then repeat to yourself.
Cursor, from my companies perspective at least, seems to be handling charming leadership to get enterprise AI contracts in place, compared to the alternatives. That's feeling like the moat from my first-hand experience. Easy single contract that covers a lot of AI cases that management wants to say they have in place.
I had a similar experience, I was working on a jupyter notebook, and Claude knew that it could write code that would use a DSN with read-only database access so I could run it. Opus just plugged along. First Fable session with it, it tried to go looking for that DSN so it could get the connection string and run a query itself. Luckily the auto classifier caught and stopped it.
The jobs AI crisis is me being stressed and overworked as management demands more AI, showy (but shallow) "look I made a skill" presentations grab attention, and my PR review queue grows every day as people generate more code than ever.
But to keep this out of a low-value vent, my experience has been that the _threat_ of it is there, but in my small corner of the world/industry, lots of layoffs that would have happened anywhere may just be categorized as "AI" layoffs, but the wild manpower reducing benefits aren't really there. The larger an org gets, the more of your job is dedicated to human stuff, and you can just get some of the code part done a little more quickly.
Would be interesting if we could measure how much effort is put into agentic coding harnesses, frameworks, and theory, vs labor saved using them.
Agreed, and it's the same in software. Probably the biggest time-sink right now as a tech lead is people going from idea to fully-fleshed-out PR, and then having to go back to have a discussion of "was this the right thing to do". It causes frustration all around (being a "no" much more, and having someone tell you your finished work isn't valuable).