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

531–540 of 748 posts

Re: Claude Fable is relentlessly proactive

#531

Post by Aachen »

reverius42 wrote: post #303
Vachyas wrote: post #99

Earlier quoted context omitted.

$12 worth, it seems

Imagine telling someone in 2015 that you can just tell your computer to fix a 2-line CSS bug and it only costs $12

'only'? A web developer did not cost 12*30=360$ an hour in 2015, and that's assuming that going "ugh, whatever. I'll just hide the problem with overflow:hidden instead of finding the underlying cause" takes him or her 2 minutes and isn't already the dev's initial reaction

Another way of looking at it is using as much electricity as a normal person in a high-income country uses across ~3 days to add overflow:hidden in the end. Of course, the path to get there did a lot more, but you don't know that beforehand if you don't take a quick peek and make an architectural decision about what the solution should be that gets implemented

Re: Claude Fable is relentlessly proactive

#532

Post by sdesol »

snowwrestler wrote: post #487
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.

But Simon is not trying to get good at CSS debugging, Simon is trying to learn about AI systems and produce content about them. So giving the AI agent a trivial task to go crazy on is a feature, not a bug. For $12 implied cost, he got a front-page post on HN with 500 comments. What is that worth? :-)

> What is that worth? :-)

This is one of those double edge sword situations. It is on the front page and it stays because it will trigger a lot of people and he has to spend a lot of effort explaining himself. What is that worth?

His explanations would most likely be buried deep so the impression that others get might be worsened. What is that worth?

In my opinion, this is one of those find a harder problem and you would still have the same content...but it might not draw as much feedback and stay on the front page longer.

Re: Claude Fable is relentlessly proactive

#533

Post by simonw »

alecco wrote: post #527
simonw wrote: post #522

Earlier quoted context omitted.

What, because I talked about one of my projects? Help me out here: can you point to an article from someone's blog that showed up on Hacker News within the past few weeks that you wouldn't classify as "blogspam" and explain how it differs from the kinds of thing I write about?

Low effort content. You keep mention your product from the start over and over. There's not much useful information in the anecdotal post. It could've been a one-liner tweet. Good corporate tech blogs at least give something useful or insightful for the reader and only after that they dare plug their product/service near the end.

Hot damn, if I'm communicating less value than corporate tech blogs there really is no hope for me.

("You keep mention your product from the start over and over" - I don't think that's fair, I mention Datasette Agent once at the start to set the scene but I spend more time talking about AgentsView than my own projects in the bulk of the piece.)

Re: Claude Fable is relentlessly proactive

#534

Post by xnorswap »

snowwrestler wrote: post #487
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.

But Simon is not trying to get good at CSS debugging, Simon is trying to learn about AI systems and produce content about them. So giving the AI agent a trivial task to go crazy on is a feature, not a bug. For $12 implied cost, he got a front-page post on HN with 500 comments. What is that worth? :-)

To most of us that's worth a ton, whereas he's probably had enough front-page posts that there's less value to him, although still likely more than $12 worth.

Re: Claude Fable is relentlessly proactive

#535

Post by impalallama »

I won't say too much about the person posting this because they got a new toy and want to use it but man this is like a certain extreme of Parkinson's Law or something as far as using up compute resources.

You got a whole data center doing god knows how much compute running billions of matrix multiplications all to solve a trivial css overflow bug in a text box. And this includes the LLM itself writing custom web-servers programs and python scripts when the best estimate guess from a google search probably would have given you the same result.

Re: Claude Fable is relentlessly proactive

#536

Post by bentcorner »

penguinPhilosop wrote: post #246
0x6c6f6c wrote: post #237

Earlier quoted context omitted.

Honestly Claude straight up ignores my input sometimes, preferring to instead run commands for output and processing that and burning through a series of tokens when thinking hard about whether to ignore me. Like today, I told Claude exactly the name of the folder it had mistaken (it was supposed to be prod, not production), and it disregarded my input to then examine the directory itself. Small example of the kind o…

Almost if this was _intentional_... maybe related to Anthropic still not being profitable and burning thru wads of cash every day.

The conspiracy theorist in me says that LLM providers do this regularly (or at least, don't bother optimizing for it) beyond some arbitrary "$/task" metric. I am not sure of there is enough SOTA model competition to avoid this.

Re: Claude Fable is relentlessly proactive

#537

Post by kstenerud »

bryanlarsen wrote: post #11
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…

I'm also bemused by the number of people who think they've got an effective sandbox yet their sandboxed agent has access to all of their code, their github, and unrestricted web access.

> yet their sandboxed agent has access to all of their code, their github, and unrestricted web access.

Not in my sandbox. It gives no direct access to the workdir, no access to my github, my ssh keys, my security tokens or API keys. No access to my home dir or dotfiles. Nothing at all, except for what I explicitly tell it to give access to.

I can restrict network access. I can choose the isolation level: docker containers, Kata VMs, seatbelt, tart, even the new apple containers (which are VERY nice).

Not even ENV leaks through.

And it's FOSS: https://github.com/kstenerud/yoloai

Re: Claude Fable is relentlessly proactive

#538

Post by simonw »

criddell wrote: post #525
simonw wrote: post #103

Earlier quoted context omitted.

I'd have been pretty annoyed if I'd been paying full price, hadn't paid attention and that one prompt (screenshot plus a line of text) had cost me $12! On the discounted subscription I can tolerate it, it took a small bite out of my daily allowance but not enough that I regret anything. As an LLM researcher I have no regrets at all because watching it work around the environmental restrictions was fascinating.

Reading your description of what it did, $12 seems pretty inexpensive. That's a lot of work! If you knew up front it was a $12 fix, do you think you would have decided to just live with the scroll bar? Would have tried to fix it yourself? Do you think you would have been able to easily find and fix the problem?

If I wasn't in learning-about-the-new-model mode and knew in advance that it was going to cost me $12 in actual money then yes, I would have taken a stab at figuring it out myself.

Re: Claude Fable is relentlessly proactive

#539

Post by lossolo »

solenoid0937 wrote: post #459
saberience wrote: post #403

Earlier quoted context omitted.

And Fable is still worse than Codex. I use both and the only thing (as always) that I will use Claude for is UI design. Opus 4.8 and now Fable are still both worse at actually getting the job done than the Codex model. Claude models write FAR too much code when it's not needed, they burn far too many tokens, when they are not needed, write un-necessary tests, write plans which are 5 pages longer than are needed, etc.…

I don't know what problems you're working on but Fable is not just better, it is a step change from GPT 5.5 in my experience. It feels at least one major model generation ahead.

It doesn't for me. I use Fable to make plans, then give them to GPT 5.5 to review, and it always finds flaws and edge cases that Fable misses (some are really critical). It was the same with Opus 4.8. I'll admit it finds a bit fewer issues now, but Fable feels more like an incremental improvement than a major generation ahead.

Re: Claude Fable is relentlessly proactive

#540

Post by rco8786 »

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…

> If you pay attention to what it's doing you can learn so much!

I think your post is fair but it's worth pointing out that learning via watching is much less effective than learning via doing.

Post reply on HN