Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Fable is relentlessly proactive

simonwillison.net

Post reply on HN
Print view View original

441–450 of 748 posts

Re: Claude Fable is relentlessly proactive

#441

Post by yumbumdum »

simonw wrote: post #393
piker wrote: post #342

Earlier quoted context omitted.

This is exactly right. By offloading this trivial task to the LLM, Simon has abandoned the opportunity to evaluate the abstraction with additional information and improve it. Instead, we let the agent spend $12 and make the fix while learning nothing.

Things I learned from this: - Fable will do a whole lot more than you might expect in order to verify a fix. I learned that it's "relentlessly proactive". That's a good title for a blog entry! - You can take screenshots of a window in macOS using the "screencapture" CLI command, but you'll need the integer window ID first. - That windowID is accessible via "Quartz.CGWindowListCopyWindowInfo(Quartz.kCGWindowListOption…

[flagged]

Re: Claude Fable is relentlessly proactive

#442

Post by simonw »

PinkaDunka wrote: post #438
simonw wrote: post #399

Earlier quoted context omitted.

Here's a handy calculator you can use to estimate how much CO2 and water I wasted with my coding agent session: https://www.andymasley.com/visuals/ai-prompt-footprint/

Not sure what point you wanted to make, but this calculator is quite shocking. GPT 5.5 pro, with "a long document" and 10 requests a day gives 25% of daily CO2 emissions! Ten coding sessions a day with Opus is still 4.7%! This feels enormous. I will definitely stop rolling my eyes when people complain about AI CO/water usage...

GPT-5.5 Pro is a notoriously expensive model, it's 6x the price of GPT-5.5. Not something to use as a daily driver!

That ten coding sessions a day with Opus number feels more credible to me.

Re: Claude Fable is relentlessly proactive

#446

Post by simonw »

almostdeadguy wrote: post #439
simonw wrote: post #393

Earlier quoted context omitted.

Things I learned from this: - Fable will do a whole lot more than you might expect in order to verify a fix. I learned that it's "relentlessly proactive". That's a good title for a blog entry! - You can take screenshots of a window in macOS using the "screencapture" CLI command, but you'll need the integer window ID first. - That windowID is accessible via "Quartz.CGWindowListCopyWindowInfo(Quartz.kCGWindowListOption…

It's like saying you can learn so much about math from using SymPy to solve equations. Yes, you probably can. If you pay close attention to what is happening and can integrate the techniques being used into your knowledge. But your learnings here are what, a handful of hacks? For most people it's like being shown the chain rule (which frankly, is more general than any of these learnings) without knowing what a deriva…

> I think people with a rosy view about this are severely undercounting the problems associated with the trust relationship between a person and an LLM and what that means.

Personally I think the impact of LLMs on children's education is a crisis right now.

Kids are not going to learn to write if an LLM writes their essays for them. And writing is how you learn to think.

Re: Claude Fable is relentlessly proactive

#447

Post by almostdeadguy »

simonw wrote: post #446
almostdeadguy wrote: post #439

Earlier quoted context omitted.

It's like saying you can learn so much about math from using SymPy to solve equations. Yes, you probably can. If you pay close attention to what is happening and can integrate the techniques being used into your knowledge. But your learnings here are what, a handful of hacks? For most people it's like being shown the chain rule (which frankly, is more general than any of these learnings) without knowing what a deriva…

> I think people with a rosy view about this are severely undercounting the problems associated with the trust relationship between a person and an LLM and what that means. Personally I think the impact of LLMs on children's education is a crisis right now. Kids are not going to learn to write if an LLM writes their essays for them. And writing is how you learn to think.

I don't think it's just a problem for kids! I think this is problem for many software engineers as well! Adults of all professions really.

Re: Claude Fable is relentlessly proactive

#448

Post by dgellow »

soulofmischief wrote: post #72
teraflop wrote: post #3

> But on the other hand... this is a robust reminder that coding agents can do anything you can do by typing commands into a terminal—and frontier models know every trick in the book and evidently a few that nobody has ever written down before. > Running coding agents outside of a sandbox has always been a bad idea I'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckle…

It took two decades for the web to deprecate SSL for TLS and serve over HTTPS by default.

FWIW TLS had a non negligible impact on performances at scale. Hardware improvements made that irrelevant, eventually making the switch to HTTPS by default a no brainer (or at least that's what I vaguely remember from <2010)

Re: Claude Fable is relentlessly proactive

#449

Post by mexicocitinluez »

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…

The other day I was doing something that required CC to update like 15-20 files in exactly the same way (hoist a specific function out of the component body) and instead of just updating the files, it spun up multiple agents, one of which wrote a perl script to hunt down all the files, do some regex, and replace all occurrences. And then instead of just running tsc to check for errors, it wrote a script to run tsc in each of the subagents and combine the results.

It was actually pretty maddening as what should have taken a minute or two tops took like 10 because it went down this route.

I'm gonna try something much more complex later, but for simple things, it felt like driving a corvette to the mailbox.

Post reply on HN