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

281–290 of 748 posts

Re: Claude Fable is relentlessly proactive

#281

Post by ttoze »

Would be great to know if anyone is having success modifying these types of behaviour with CLAUDE.md files. In my project I’ve still been carrying some fairly old instructions from the Superpowers posts. Those emphasised behaviours that come across a bit strong if the model is actually retaining attention on them.

Between Opus 4.6 and 4.8 I’ve definitely toned them down, but Fable perhaps needs us to go the other way, and push it towards being less proactive rather than more. Some instructions like “we are colleagues…” may need emphasising more with Fable, along with guidance about when to ask to validate approaches.

In a related point I’m less and less sure that Red/Green TDD is a good use of tokens. In older models it seemed to work well to create regular feedback loops and catch the odd issue with drift from the goal, but I’ve not seen that really since about Opus 4.6 and now it’s starting to seem like (an expensive) ceremony, and tokens would be better spent on building tests further on in the process as part of test and review loops.

Re: Claude Fable is relentlessly proactive

#282

Post by Chu4eeno »

lelandfe wrote: post #184
satvikpendem wrote: post #118

Earlier quoted context omitted.

You can get 10x shit done without `rm -rf`ing your files. I don't see any correlation to getting things done with having a proper sandbox.

https://github.com/anthropics/claude-code/issues/13371 > Additional bypass examples that all execute without permission: > echo test ; git rm file.txt > rm --force --recursive /home (if "rm -rf" is blocked)

It really is vibecoded.

I never really dug into the leaked code, but calling that there a security layer is a joke.

(And I really don't get why they give it actual shell access either, implementing a "fake" one for something like a honeypot takes a couple of days, not much more if it needs to persist/map to actual files.)

Re: Claude Fable is relentlessly proactive

#283

Post by amichal »

Do we care that the bug here was a horizontal scrollbar showing and the fix after all this insane tool writing was to add a very obvious overflow-x: hidden to the element?

We dont mind because its so fast a writing these tools and tricks but step back and if a human tool took this path i would seriously question thief gras of fundamentals.

Re: Claude Fable is relentlessly proactive

#284

Post by nimonian »

dfee wrote: post #89

admittedly, i've not really cracked FE dev with LLMs at this point (and it's probably my big weakness). but, i'd heard somewhere that FE just isn't there yet - though i was suspicious of that claim. i'm torn about sending screenshots to an LLM for debugging - seems imprecise. seems lossy, especially compared to inspecting the dom. however, it's always proved good enough (e.g. when messing with ratatui.rs and tui-pant…

Fable is really good at front end (Opus 4.8 is decent too) but it really needs a verification loop - it can't always infer the output from the code alone. Give it Playwright to check its work, and it'll generally do a good job. Also if you're using a framework, add to your CLAUDE.md to always rtfm before making changes!

Re: Claude Fable is relentlessly proactive

#285

Post by rikschennink »

simonw wrote: post #272
rikschennink wrote: post #270

Earlier quoted context omitted.

I looked at the screenshot and for the rest of the article wondered if it would be as simple as `overflow-x: hidden`. And to my surprise it was. This would’ve take a frontend dev 10 seconds to deduce and another 10 seconds to confirm.

The thing that puzzles me is that I would expect overflow-x: hidden to result in text typed into that textarea being wider than the page and being invisibly truncated on the right hand side. But that's not what happens. And in fact, when you start typing in the textarea the horizontal scrollbar vanishes - it's only there when the textarea is empty. Am I misunderstanding anything here? Seems like it's some weird Safar…

It probably has to do with other styles assigned to the textarea, maybe the ::placeholder as it hides when typing (I assume on focus)

In any case. In the screenshot the scrollbar is inside the textarea as it aligns with the resize control on its right. This is basically all the info needed to deduce the textarea overflow is the culprit.

But could be that the overflow-x is just a bandaid hiding the issue causing the overflow in the first place, like crazy styles on the placeholder.

Re: Claude Fable is relentlessly proactive

#286

Post by fspoettel »

simonw wrote: post #83
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…

Which agent sandbox do you recommend?

nono works great with pi: https://nono.sh/

Re: Claude Fable is relentlessly proactive

#287

Post by customguy »

exitb wrote: post #233
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…

You’ve picked an interesting example, as driving a car, even with all safety precautions, is pretty much the most dangerous activity we do on a daily basis. Yet somehow we decide that the benefits outweigh the risks.

The example wasn't "driving a car". The benefits of putting your feet up on the dashboard do not outweigh the risks, at least not where there is actual traffic. I don't think I saw a single person doing that in real life, ever.

Re: Claude Fable is relentlessly proactive

#288

Post by mrandish »

harrall wrote: post #131
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 started doing it months ago and, to be honest, what the agent chooses to do isn’t unpredictable. The problem is that different people prompt so differently. For example, I may ask like “test different variations of this annotation on k8s pods of this service on this X cluster because it proves Y theory.” But you know what my coworker asks? “Test Y theory.” If you were to ask two different junior engineers that, one…

> But you know what my coworker asks? “Test Y theory.”

It still surprises me when I see people not prompting more specifically and clearly. It not only avoids problems, it's faster, costs less -and just works better.

I recently shared with a friend a multi-hour LLM chat session I'd done because it veered into a domain he's interested in. In the session I'd brainstormed and probed the feasibility of a novel concept for a new research direction. It traversed a half dozen domains diving into minute detail then zooming back out to survey an adjacent space, interspersed with intense skeptical probing of key assumptions, all while spewing tons of detailed citations, specific paragraph pulls, summarized data tables etc.

My friend is very experienced using LLMs for research so I was surprised when he called me shocked by the sheer velocity, precise targeting and signal/noise. I'd assumed everyone did it the same as I do. He attributed the different result solely to the way I crafted my prompts.

Re: Claude Fable is relentlessly proactive

#289

Post by Ucalegon »

simonw wrote: post #257
Ucalegon wrote: post #252

Earlier quoted context omitted.

[flagged]

I don't understand what you mean by "objective" here. You're welcome to believe that the pricing I quoted is low and enterprise companies pay more than that, despite the abundant evidence I've provided in this thread. It sounds to me like you think I'm biased towards Anthropic, despite me highlighting how their model charged $12 for a two line CSS change due to it being "relentlessly proactive". (I also called their…

[flagged]

Re: Claude Fable is relentlessly proactive

#290

Post by ragchronos »

simonw wrote: post #128
Ucalegon wrote: post #123

Earlier quoted context omitted.

[flagged]

I'm afraid I don't understand the question. Anthropic have prices they charge for their models. These prices are what you pay if you use the API, and they are also what you pay if you are an "enterprise" customer - generally any company with 150+ employees. I haven't seen Anthropic raise the prices of an existing model after it has launched. They sometimes raise prices when they ship a model - Fable is $10/$50 where…

So this is kind of related, which the other commenter be might be getting at. This might be obvious, but could even these API prices just be running at a loss for Anthropic themselves?
Post reply on HN