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

651–660 of 748 posts

Re: Claude Fable is relentlessly proactive

#651

Post by tomjakubowski »

nullbio wrote: post #464
lionkor wrote: post #454

When prompted like this: > What could be the reason for a horizontal scrollbar appearing inside a ? Come up with a single likely fix path. Keep it terse. ChatGPT instantly responded with some speculation and then the same exact fix, with zero access to the code or a browser or anything. It also included ways to fix it by removing code, saying: > Likely cause: the textarea is rendering long unbroken text while horizon…

Still don't know why people use Claude. Maybe because they don't know what they're doing.

You can get the same result as the grandparent comment with the "weaker" Anthropic models. Probably 80% of my AI usage these days is with smaller models like Haiku and Sonnet. I prompt them like I'm posting a question to StackOverflow, without much project context.

Re: Claude Fable is relentlessly proactive

#652

Post by artemisart »

flexagoon wrote: post #227
simonw wrote: post #83

Earlier quoted context omitted.

Which agent sandbox do you recommend?

If you're on Linux, the easiest way IMO is to just run the agent in bwrap I do it like this https://github.com/flexagoon/dotfiles/blob/main/dot_config/f... But I'm sure it's simple enough that you can just ask the agent itself to make you a command for it with proper bwrap configuration

bwrap is builtin in claude too, activate with /sandbox command.

Re: Claude Fable is relentlessly proactive

#654

Post by PoignardAzur »

Sharlin wrote: post #458

I remember back in the 2010s the debates between "oracle" and "agent" AGIs, and the arguments that AGIs that only answer questions would be safe and certainly nobody would ever be stupid enough to just let an AGI out of a sandbox, never mind to the greater internet, and give it tools to do whatever it thinks is needed to reach a goal. Us circa 2026: "Hold my beer"

Yeah, I really miss the "nobody would ever be stupid enough to [_____]" days of AGI safety discourse.

Re: Claude Fable is relentlessly proactive

#655

Post by l72 »

ghrl wrote: post #435
antonvs wrote: post #159

Earlier quoted context omitted.

I've had agents run `rm -rf`, but it's been on directories that did actually need to be removed. To a certain extent I think the existence of `rm -rf` as a command that runs blindly without any understanding of what it's deleting is the problem.

Yeah, spot on. I had an agent delete some files it shouldn't have as well, similarly to me making the same mistake. I think system prompts should default to using `trash` over `rm`. For now that's just in my AGENTS.md, and gets honored most of the time.

You can always use something like this [1], which will make sure any file removed on the command line via rm (or other utilities, like git rm) ends up in the trash instead

[1] https://github.com/faratech/trashd

Re: Claude Fable is relentlessly proactive

#656

Post by nevertoolate »

8note wrote: post #582
nevertoolate wrote: post #497

Earlier quoted context omitted.

> I was trying to find the root cause of a crash in a Python module which left no errors in the log or console. Fable wrote a test harness that simulated clicks in the UI, then bisected my code until it found the point where it started crashing Does this need an agent though is my question? Maybe generating a test case and a loop doing git bisect but why on earth would we want to run it through the internet and gpus…

everyone is discovering everyone else's practices? its handy to have that run locally yeah, but thinking of that as being the way is not straightforward

I think it is fine to create the scripts with the cloud based llm but it is definitely not a fable / opus level thing, and running the bisect loop itself has nothing to do with an agent, it is a simple shell script.

Re: Claude Fable is relentlessly proactive

#657

Post by vadansky »

byproxy wrote: post #586
biztos wrote: post #345

Earlier quoted context omitted.

They might also ask why a bunch of static CSS inside a bunch of JavaScript is hiding inside __init__.py[0] - hopefully before trying to fix some detail of the CSS. (I'm surprised to see it actually, since my own use of Claude has mostly yielded well-structured code. But I'm not doing proper vibe-coding, more like friendly Socratic arguing with another engineer who happens to be a robot.) [0] https://github.com/datase…

> friendly Socratic arguing with another engineer who happens to be a robot Ha! Same! Still feels like the best way to go about it, really. I know the dream is to one day remove humans from the loop... but I'll enjoy the dialectic while it still seems the most productive!

Same, I like to call it rubber duck coding (now the duck talks back!)

Edit: Now I want an LLM connected rubber duck with a speaker/microphone that sees your screen

Re: Claude Fable is relentlessly proactive

#658

Post by justusthane »

pjungwir wrote: post #529
justusthane wrote: post #451

Earlier quoted context omitted.

That’s a really interesting and pretty neat approach. How do you communicate with it? Just su to that user? Or tmux? Although I can’t help but think that a VM is still more convenient, more flexible, and more secure.

Yes, I su to the user. Typically I have it run a tmux session for each "project". That makes it easy to get more windows without su'ing over and over. Also its tmux sessions all get a yellow status bar (in ~claude/.tmux.conf), so they are easy to recognize. To me it is more convenient than a VM, since everything is on the host. And it can launch its own VMs without an extra layer. I don't really know which is more se…

You could look into Podman as well - it's rootless by default, and often can be a drop-in replacement for Docker.

Re: Claude Fable is relentlessly proactive

#659

Post by l33tman »

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…

[dead]

Re: Claude Fable is relentlessly proactive

#660

Post by slopinthebag »

jen729w wrote: post #116
etdznots wrote: post #40

Earlier quoted context omitted.

Example of whats been shipped?

Okay. I rebuilt my website in ~a month with the help of Opus 4.7/.8 and it would have taken me, unaided human, at least 6 months. Link's in my bio if you care. Satisfied now? Will you stop asking this question? Thought not.

I could have written this site plus the browser to render it in six months...
Post reply on HN