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

511–520 of 748 posts

Re: Claude Fable is relentlessly proactive

#511

Post by paganel »

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…

> to give agents full access to your machine

I was mesmerised at the author being away from his computer for a short-while and then, when coming back, seeing the AI agent having opened up a browser window. Meanwhile we all have to use the fricking 2FA almost anywhere now, plus the crazier and crazier rules when it comes to passwords. I'm mentioning the latter because these type of people were the same ones who were pushing 2FA down our throats around 2017-2019 (including on forums like this one), and look at them now.

Re: Claude Fable is relentlessly proactive

#512

Post by simonw »

andy_ppp wrote: post #499
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…

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.

Re: Claude Fable is relentlessly proactive

#513

Post by jon-wood »

epolanski wrote: post #316
_345 wrote: post #171

Earlier quoted context omitted.

In my case no, I actually saw worse performance with fable medium and switched back to opus high and xhigh

I find high+ unusable, it's way too slow and "thorough" on 99% of mundane task. Sure it's better at vibecoding whole tasks, it's clearly good at it, but give it a simple one, and it will still do way more than needed. It's way too fixated on validating even the simplest things, I find it an unproductive model unless you're implementing whole tasks and doing other things in the meantime.

Why are you deploying a bleeding edge, incredibly expensive, model to do the simplest things? Use Sonnet, hell, use Haiku, they'll get the job done and won't set fire to several rainforests in order to achieve the task.

Re: Claude Fable is relentlessly proactive

#514

Post by simonw »

bmusuku wrote: post #506

antigravity does this all the time, I do not see anything novel here.

Antigravity uses pyobjc-framework-Quartz to iterate through windows to find window IDs for taking screenshots with screencapture, and spins up CORS-enabled web servers so it can capture measurements in a regular (not Playwright/CDP-controller) browser window via a CORS fetch()?

Re: Claude Fable is relentlessly proactive

#516

Post by IshKebab »

swingboy wrote: post #76

Immediately I thought “isn’t this just an overflow issue?” Amazing how far these models still have to go and also how many people don’t know basic CSS.

Yeah pretty crazy capability from the AI but also sad that we're at the point where web developers don't know right click->inspect element, and scrolling overflow properties (one of the most basic and common parts of CSS).

Re: Claude Fable is relentlessly proactive

#517

Post by fennecfoxy »

mapt wrote: post #467
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 was only pursuing the goal you gave it - Keep Summer Safe.

"Oh my God"

Re: Claude Fable is relentlessly proactive

#518

Post by eqmvii »

onlyrealcuzzo wrote: post #484
not_kurt_godel wrote: post #482

> When I came back a few minutes later I saw my machine open a browser window in my regular Firefox and then navigate to the dialog in question. I had not told Claude Code to use any browser automation, and I was pretty sure it wasn’t possible for it to trigger mouse movements or keyboard shortcuts within a window, so how was it doing that? I continue to feel validated in my refusal to use terminal-based LLMs on my l…

I'm shocked they don't come with a way to run them in a sandbox. Shouldn't this be relatively easy for a $1T company to set up? Isn't this trivial compared to the entire harness?

That's more or less what Claude Cowork is.

Every serious engineer I've seen try to use it ran away screaming, because of limitations in the sandbox.

I've also seen people set their coding agents up entirely within containers -- that may be the better way going forward, but it's an extra stop and a lot of extra plumbing to maintain.

Re: Claude Fable is relentlessly proactive

#520

Post by simonw »

IshKebab wrote: post #516
swingboy wrote: post #76

Immediately I thought “isn’t this just an overflow issue?” Amazing how far these models still have to go and also how many people don’t know basic CSS.

Yeah pretty crazy capability from the AI but also sad that we're at the point where web developers don't know right click->inspect element, and scrolling overflow properties (one of the most basic and common parts of CSS).

What's your theory on why the bug was present in Safari on macOS but absent in Chrome, Firefox, and WebKit for Playwright?
Post reply on HN