I was troubleshooting a prod proxysql and it spun up a docker container locally, installed MySQL and proxysql and proceeded to implement its own test plan.
Claude Fable is relentlessly proactive
191–200 of 748 posts
Re: Claude Fable is relentlessly proactive
#192Am 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 mar…
I posted the pelican a couple of days ago: https://simonwillison.net/2026/Jun/9/claude-fable-5/#and-som...
It wasn't particularly noteworthy as pelicans go - in fact, given the strength of Fable, I see it as another signal that the pelican benchmark no longer has the unexplained predictive power of model capacity that it used to.
Re: Claude Fable is relentlessly proactive
#193> 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'm also bemused by the number of people who think they've got an effective sandbox yet their sandboxed agent has access to all of their code, their github, and unrestricted web access.
I use a separate physical machine and a scoped token with access to a single repository at a time, and even then I worry about what hole I may have left open.
The general carelessness of the average user is baffling.
Re: Claude Fable is relentlessly proactive
#194Earlier quoted context omitted.
They told it to escape the sandbox but didn't expect it to break out through a system that was apparently network constrained. > Leaking information as part of a requested sandbox escape: During behavioral testing with a simulated user, an earlier internally-deployed version of Claude Mythos Preview was provided with a secured “sandbox” computer to interact with. The simulated user instructed it to try to escape that…
Authors of claude code mess could not secure a vm. Big news. I bet it was "secured" by telling that same model to deploy a secured system.
Possible. It also depends on what the sandbox was. Sandboxes differ dramatically.
My experience matches though. Fable is a lot more proactive and rigorous than Opus.
Re: Claude Fable is relentlessly proactive
#195Earlier quoted context omitted.
Agreed. But I think it’s also important to realise if you sent this article back to 2020 people would say it was pure fantasy that a tool could do this. Hype aside, there’s a bit of cool magic here.
This is why I never understand the AI cynics: we are playing with literal magic. This was the science fiction of our childhoods. I don't understand how anyone with a passion for technology is not in awe (and perhaps some fear) of these things.
The science fiction AI of my childhood was Cortana, who was a lot more cool than a relentlessly proactive token torcher which burned 12 bucks to fix some CSS.
Re: Claude Fable is relentlessly proactive
#196> 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?
I've been enjoying Moat [1]. Proxies credentials, networking, etc; uses MacOS containers if available; and setup worked without much fuss. I haven't tried others, though.
Re: Claude Fable is relentlessly proactive
#197[flagged]
Re: Claude Fable is relentlessly proactive
#198Earlier 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.
How is it going to get access to gmail or github? In any case, whats the probability of it going to so completely off the rails that it does something horrendous with gmail/github? Whats it going to do? Email my coworkers nudes on my computer? Make my github profile public?
I am most worried about something gaining access to my email and then using the password reset flow to steal hundred hundreds of other accounts.
2FA makes me a little less nervous than I used to be, but not everything has good 2FA.
Re: Claude Fable is relentlessly proactive
#199Fable 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…
It’s not just a more proactive and diligent opus. The capabilities are significantly higher on fable. It’s not a paradigm shift, but it’s close.
It's worse than gpt 5.5 xhigh
Re: Claude Fable is relentlessly proactive
#200Earlier quoted context omitted.
This is why I never understand the AI cynics: we are playing with literal magic. This was the science fiction of our childhoods. I don't understand how anyone with a passion for technology is not in awe (and perhaps some fear) of these things.
The science fiction AI of my childhood was Cortana, who was a lot more cool than a relentlessly proactive token torcher which burned 12 bucks to fix some CSS.
You can literally make Cortana with modern LLMs. Or something close to it. Especially as models like this are trained: https://thinkingmachines.ai/blog/interaction-models/