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

171–180 of 748 posts

Re: Claude Fable is relentlessly proactive

#171

Post by _345 »

conradkay wrote: post #69
jampa wrote: post #8

Fable feels like a version of Opus running on a harness that won't let it halt until it's sure the issue is fixed, which makes sense if what you want is a model that's better at benchmarks. It's a very good model, but it comes at a huge premium: not only do the tokens cost more, but the model itself really wants to spend them all. For example, working with React Native, Fable never just says "okay, I did the thing, t…

Does low/medium effort fix it for you? Seems like Fable 5 low can outperform Opus 4.8 high/xhigh often, and uses a lot fewer tokens

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

Re: Claude Fable is relentlessly proactive

#172

Post by esjeon »

jampa wrote: post #8

Fable feels like a version of Opus running on a harness that won't let it halt until it's sure the issue is fixed, which makes sense if what you want is a model that's better at benchmarks. It's a very good model, but it comes at a huge premium: not only do the tokens cost more, but the model itself really wants to spend them all. For example, working with React Native, Fable never just says "okay, I did the thing, t…

> the model itself really wants to spend them all

In fact, Opus does the same. It finishes the job, and redo it from scratch before presenting the result to the user. This happens even for simpler writing tasks especially when I instruct it to create a text file.

Re: Claude Fable is relentlessly proactive

#174

Post by matltc »

SoftTalker wrote: post #126
ghshephard wrote: post #28

Earlier quoted context omitted.

Worst case it gets access to gmail. And Github. And the Internet. I'm increasingly appreciating the importance of a physical finger-press on Yubikey to trigger the FIDO2 + OIDC Auth. I don't think there is an easy way for it to hack a new session.

It should run as a separate user account with its own home directory. Not with access to your personal browser profile.

What does setting this up look like? Qemu vm and run there? How do you interface with version control and deployment?

Re: Claude Fable is relentlessly proactive

#175

Post by simonw »

Ucalegon wrote: post #173
simonw wrote: post #154

Earlier quoted context omitted.

Which claim are you talking about here?

[flagged]

I have genuinely no idea what you are talking about at this point.

I said that my session would cost $12.11 at standard Anthropic prices, based on using AgentsView to calculate cost against tokens used. I further asserted that Anthropic charge enterprise customers those rates.

You kicked off a lengthy thread which I tried to follow but eventually lost track of the point you were making and/or the questions you were asking.

And now you're talking about bias and I don't know where that came from either.

Re: Claude Fable is relentlessly proactive

#176

Post by kelsier_hathsin »

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.

Seriously a month? I could write a SSG itself to produce this site in a month.

Re: Claude Fable is relentlessly proactive

#177

Post by spunker540 »

SepiaSapient wrote: post #139
jen729w wrote: post #116

Earlier quoted context omitted.

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'm looking at something fairly standard that can be made with a SSG. The "Written by humans" footer gave a good chuckle tho.

[dead]

Re: Claude Fable is relentlessly proactive

#178

Post by lstodd »

antonvs wrote: post #159
qurren wrote: post #130

Earlier quoted context omitted.

I haven't yet had an agent rm -rf files. I've had one f up an account by placing 2000 limit orders at the wrong price, but that's another story.

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.

the answer is rm -f `which rm`, yes?

Re: Claude Fable is relentlessly proactive

#179

Post by eranation »

Am I the only one who slightly miss the pelican on a bike? It was a nice novelty... of course I could make one myself, but I became conditioned to expect one for every new model. Other than his great writing on AI, it became part of the package. Some small fun quirk to distract us from the non stop ping pong between the extremes of "omh are you still writing prompts you should use loops / 200k github stars, for a markdown file / someone just open sourced _ and it changes everything!" vs "haha the AI told me to walk to the car wash / it can't recognize and upside down cup"
Post reply on HN