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

671–680 of 748 posts

Re: Claude Fable is relentlessly proactive

#671

Post by pshirshov »

enraged_camel wrote: post #648
pshirshov wrote: post #639

Earlier quoted context omitted.

Ok, explain me one thing: I have a benchmark - I feed identical prompt to multiple models. Codex produces a rough but working program. Fable produces the same - but with more bugs than Codex. Opus produces something similar to Codex but with a critical bug. That describes all my tests with Fable. Why should I be hyped about all that "legitimate power" if the model performs on par with two other SoTAs? I mean, well, y…

>> Why should I be hyped about all that "legitimate power" if the model performs on par with two other SoTAs? I don't care if you're hyped or not. You asked if the posts like the OP come from a "parallel reality" and I said no and described my experience. If you're getting good/better results with Codex than with Fable, you should probably continue using that, since it's cheaper and faster.

But can you bring anything measurable in support to your words? I did.

Re: Claude Fable is relentlessly proactive

#672

Post by theshrike79 »

simonw wrote: post #232
BosunoB wrote: post #228

Fable was trying to verify a UI change in my game. I was working in another window and noticed a program opening on my task bar. Fable had opened the game through the CLI using a movie maker tool, recorded the output, took a frame from the end of it, and used that to verify the UI. When my game's welcome screen obstructed what it wanted to see, it created a temporary worktree, deleted the welcome screen, and ran the…

Yeah, you've exactly captured one of the main problems with the model being relentlessly proactive: it will happily burn like $5 of tokens to avoid asking the human to take a screenshot or click a button for it.

I think providing proper token-efficient tools for agents will become even more important now.

Re: Claude Fable is relentlessly proactive

#673

Post by stymaar »

mapt wrote: post #640
fennecfoxy wrote: post #517

Earlier quoted context omitted.

"Oh my God"

I relent to snarky Rick and Morty quotes because I don't know that it's useful any more to try to explain paperclip optimizers or alignment to a bunch of AI nerds who saw the cliff coming and clawed at each other trying to be the first out to leap over the edge. "Relentlessly proactive". That's one word for it. We have a whole subgenre of hard takeoff scenarios and it wasn't enough warning against "Relentlessly proac…

> Turns out Frank Herbert was an optimist, and we're literally pinning our survival on robots turning out to naturally have impractically short attention spans.

Some people are working as hard as they can to increase it though.

Re: Claude Fable is relentlessly proactive

#674

Post by throwaway89864 »

danudey wrote: post #548
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…

The whole saga is kind of nuts, but the thing that fascinates me most is that Fable got this far and then hit some kind of guardrail; I'd be very curious to know what it wasn't able to do that caused it to downgrade to Opus. It already got extremely... invasive? It didn't do anything that I wouldn't have approved in the same case, but it's interesting that it got as far as launching browsers, inspecting every open wi…

It feels like there should be a budget approval, in that particular case $12 worth of KW/h - tokens were spent, without a clear approval.

Re: Claude Fable is relentlessly proactive

#675

Post by mrandish »

marknutter wrote: post #601
dr_dshiv wrote: post #317

Earlier quoted context omitted.

I used to write detailed prompts. Now I find the benefits of strategic ambiguity — rather than speaking imperatively, I emphasize my vision and then Claude can often figure out a method. This doesn’t always work better. But often enough.

Yeah, I find the back and forth with Claude is often better than trying to front load everything in a massive and detailed prompt.

The counter-intuitive nature of LLMs is so simultaneously interesting and frustrating. Overloading a single prompt definitely can create challenge remarkably similar to human short-term memory and attentional drift.

LLMs gain so much knowledge and capability from absorbing the symbolic relationships embedded in human language but in doing so, inevitably absorb many of the human foibles, sensitivities and weaknesses reflected in our languages.

Re: Claude Fable is relentlessly proactive

#676

Post by gaigalas »

It behaved proactively in one scenario.

Perhaps, when it doesn't have tricks in its sleeve, it doesn't do that. The text is not an evaluation of a major trend in behavior (which could be true or false).

Another way to frame it, is that it has more weight on training data for some kinds of debugging sessions. It doesn't mean it wants to be more debuggey. That manifests as it appearing to do more work because it engages on those weights.

It's likely that Anthropic had a lot of sessions with Claude Code and some way to evaluate if they were successful or not, which became training data. For trivial work, it's likely to be a lot of them.

Those sessions are likely to be software developers doing software developer debugging things, not malicious actors doing nasty things. The danger is someone who can coerce those tricks into performing that.

Register (that posture of "let's debug and be creative and verify") often comes with a content bias in LLMs (and humans too). The point here is that for a human, you can expect a devious one to be always devious, but LLMs might manifest drastically different register modes depending on the subject.

Re: Claude Fable is relentlessly proactive

#677

Post by m463 »

bananaquant wrote: post #338

This to me reads like a poignant commentary on the catastrophic loss of human agency, with the actual commit being highly revealing [0]. Author wants to hide a horizontal scrollbar. Any junior frontend dev worth their salt will be asking right away "where do I stick `overflow-x: hidden;`?" A complete solution will then require hitting "Inspect element" in the browser to find the CSS class and running (rip)grep to fin…

Actually, it seems to me that it is just over-monetization of any impulse.

I remember when you were billed by the minute for connecting to the online world.

There were lots of incentives to keep the meter running.

is this sort of like that?

Re: Claude Fable is relentlessly proactive

#678

Post by bubsneedpumping »

pshirshov wrote: post #671
enraged_camel wrote: post #648

Earlier quoted context omitted.

>> Why should I be hyped about all that "legitimate power" if the model performs on par with two other SoTAs? I don't care if you're hyped or not. You asked if the posts like the OP come from a "parallel reality" and I said no and described my experience. If you're getting good/better results with Codex than with Fable, you should probably continue using that, since it's cheaper and faster.

But can you bring anything measurable in support to your words? I did.

The OP and GP need all genai news to be positive to the point of using doublespeak here unironically.

"Relentlessly proactive" is a grotesque use of language. A paperclip optimizer is "relentlessly proactive".

We already had a word for what is being promoted here: wasteful.

Re: Claude Fable is relentlessly proactive

#679

Post by andy_ppp »

simonw wrote: post #512
andy_ppp wrote: post #499

Earlier quoted context omitted.

Yes I agree, the solution committed is horrible, but nobody cares any more. We have entered a very strange parallel universe where because AI can work things out it's easier to take solutions that are sub optimal and just churn out (potentially) buggy features.

I care. If you can loosely point me in the direction of a better solution I'll do the extra work.

Interesting... I downloaded dataset-agent and removed various different styles from the textarea (with an intention of providing a PR) including the overflow-x: hidden and I tried Safari and Chrome with both the global Mac setting of Always showing scrollbars on and off. It NEVER shows the scrollbar for me.

Do you have an extension installed that is doing something weird to your textareas? Maybe I'm doing it wrong but I think for now overflow-x is fine if you are experiencing it and I am not! Let's all get on with our lives... I was probably a bit overzealous about caring all that much about a perfectly fine CSS fix.

Re: Claude Fable is relentlessly proactive

#680

Post by m3kw9 »

simonw wrote: post #437
docheinestages wrote: post #427

Earlier quoted context omitted.

I'm kind of on the fence about it and have a similar feeling. I don't mean to undermine the effort he has put in over all the years. That's definitely commendable. But I have strong suspicions that he's becoming an AI influencer, with his own AI focused newsletter, so chances are major AI companies are approaching him. And also to be honest, I see far too many posts making it to the front page. @dang I trust in the m…

Most of my posts that make it on Hacker News weren't submitted by me. You can see who is submitting what on https://news.ycombinator.com/from?site=simonwillison.net - including a few that I submitted which got nowhere at all. I accept paid sponsors for my blog (the banner at the top of each page) and newsletter (a clearly marked sponsored message at the top). I try to stay at arms length from those as much as I can -…

Ok cool, was not a great way for me to ask from my op. Let this be known you aren't a plant as your words are respected.
Post reply on HN