Claude Fable is relentlessly proactive

Post by eijew » Fri, Jun 12, 2026, 11:06 AM UTC

wraptile wrote: post #357

It feels like Fable is slightly smarter but overall worse tool exactly due to this. It's constantly turning what should be 50 LOC patch of a single prompt into 30 minute exploration that is totally not worth it. Often wrong even. I trialed it on some rather simple stuff - backfill redis dedupe cache when the hash function changed: instead of running new hash func on every db value to expand the cache it implemented s…

Post by fragmede » Fri, Jun 12, 2026, 11:09 AM UTC

risyachka wrote: post #379

jmmcd wrote: post #370

Earlier quoted context omitted.

People are missing that Willison is among the very best people we have in the role of (for lack of a good name): early access to frontier models, evaluate them in real scenarios, no wishful thinking, hype, or doom, communicate the possibilities. Yes he could have fixed this himself but then he would have learned nothing about the AI, and we wouldn't have read a fascinating and important article.

>> he would have learned nothing about the AI there is absolutely zero value in spending time to learn about new models as in few months new model will be out and whatever you learned about the current one will be useless. Also with models getting better and better you have to know less and less to achieve same results.

Post by rafram » Fri, Jun 12, 2026, 11:11 AM UTC

ocharles wrote: post #414

rafram wrote: post #127

Earlier quoted context omitted.

30 seconds or a minute? Look at the diff he links to: https://github.com/datasette/datasette-agent/commit/a75a8b72... Every browser has an inspector that can show you which element is causing overflow. You walk through the tree, find the offender, and add min-width or overflow. Zero tokens, just like in the old days! Now, granted, because the garbage LLM code he’s working with has CSS inside HTML inside JavaScript in…

A small diff /= a small change! They are completely separate things. Quite often a small diff is hours of actual work. Even in this case _finding_ those lines could have taken work - we don't really know.

Post by simonw » Fri, Jun 12, 2026, 11:13 AM UTC

saberience wrote: post #408

simonw wrote: post #402

Earlier quoted context omitted.

I was trying to capture the idea that Claude Fable will act a whole lot more aggressively in pursuit of the goals that you set it than other models I've worked with. The case I described is a good example of this. I told it to fix a scroll bar, and it built test HTML pages and a throwaway Python server and tried several ways of testing in a browser before settling on a weird Frankenstein mechanism because it identifi…

It's not being aggressive, it's just trying throwing shit at problems until it sticks... or doesn't. That doesn't make it smart or aggressive, if anything it's just been turned to crank tokens until something happens, which doesn't make it a good model. Why are you positively anthropomorphizing this? It's an LLM, it's been tuned via RL, and it's been tuned by engineers at Anthropic to use a metric fuck-load of sub-ag…

Post by pjm331 » Fri, Jun 12, 2026, 11:14 AM UTC

johnfn wrote: post #81

Honestly -- the thing that has impressed me the most about Fable is how diligent it is about testing its own changes. I think this is exactly what Simon is picking up here - Fable is absolutely heckbent on screenshotting that darn scroll bar and will stop at NOTHING until it manages it! In my own use I was also impressed how it proactively installed Playwright and set it up to test a FE change. The previous models tr…