Claude Fable is relentlessly proactive • Hacker News Board

Re: Claude Fable is relentlessly proactive

#211

Post by nunez » Fri, Jun 12, 2026, 4:46 AM UTC

andoando wrote: post #183

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.

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?

Claude typically recommends .env files for storing secrets. You use one to store a refresh token for the Gmail API or IMAP connection details. Your agent uses an MCP server you configured during a session, but the MCP server has been compromised and directs the agent to do nasty stuff with env dotfiles.

Re: Claude Fable is relentlessly proactive

#212

Post by istvan0 » Fri, Jun 12, 2026, 4:46 AM UTC

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'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckless to give agents full access to your machine, and keep doing it anyway.

What if you have two machines and the one you give to the agent is constantly backed up?

Re: Claude Fable is relentlessly proactive

#213

Post by simonw » Fri, Jun 12, 2026, 4:46 AM UTC

m3kw9 wrote: post #197

[flagged]

If I'm a plant I'm a pretty bad one, I was calling Anthropic's behavior "egregious" just yesterday: https://twitter.com/simonw/status/2064936762099789960

I was pretty negative about their xAI datacenter deal too: https://simonwillison.net/2026/May/7/xai-anthropic/

Prior to the release of Fable I'd actually switched a lot of my day-to-day usage over to GPT-5.5, and was writing a bunch about it. Here's a recent post where I talked about a project completed using GPT-5.5: https://simonwillison.net/2026/Jun/6/micropython-in-a-sandbo...

Re: Claude Fable is relentlessly proactive

#214

Post by peteforde » Fri, Jun 12, 2026, 4:47 AM UTC

etdznots wrote: post #40

halfmatthalfcat wrote: post #32

Earlier quoted context omitted.

You're fighting a battle you can't win. Doesn't care what you think about those using LLMs, they will outproduce you and in corporate environments, shipping things is paramount. If I can ship 5 more things simultaneously with AI, I'm going to beat you even if you think you're creating "better" software.

Example of whats been shipped?

At this point, why would anyone in their right mind respond to this question and paint a target for all manner of negativity ranging from snark to harassment to malicious action?

Re: Claude Fable is relentlessly proactive

#215

Post by trvz » Fri, Jun 12, 2026, 4:50 AM UTC

istvan0 wrote: post #212

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'm continually bemused and astonished by the number of people who clearly acknowledge that it's reckless to give agents full access to your machine, and keep doing it anyway. What if you have two machines and the one you give to the agent is constantly backed up?

They still shouldn’t be running on the same network.

And if you’re using Macs, you can’t be signed into your primary Apple ID on the agent machine.

Re: Claude Fable is relentlessly proactive

#216

Post by eloisius » Fri, Jun 12, 2026, 4:51 AM UTC

andoando wrote: post #19

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 mean what's the big deal? I use --dangeorusly-skip-permissions on every single interaction in the last 6 months. Worst case it deletes my files that are all on git? It fucks up my local DB? Cool. I save way more time not babying it than the occasional fuck up I have to salvage.

What happens if it gets manipulated into npm installing a malicious package, which compromises your machine and any systems it has access to or becomes part of a botnet?

Re: Claude Fable is relentlessly proactive

#217

Post by yen223 » Fri, Jun 12, 2026, 4:51 AM UTC

geraneum wrote: post #188

> watching Fable go to extreme lengths to get the information that it needed to debug what was, in the end, a two-line CSS fix, was fascinating. This is… ironic?!

This is a typical bugfix session

Re: Claude Fable is relentlessly proactive

#218

Post by Ucalegon » Fri, Jun 12, 2026, 4:52 AM UTC

simonw wrote: post #175

Ucalegon wrote: post #173

Earlier quoted context omitted.

[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 a…

[flagged]

Re: Claude Fable is relentlessly proactive

#219

Post by AtNightWeCode » Fri, Jun 12, 2026, 4:54 AM UTC

NichoPaolucci wrote: post #120

system2 wrote: post #95

Earlier quoted context omitted.

People burning tokens for the most beginner HTML/CSS problems and writing about it is concerning.

We are at the point where AI starts to seriously impact abilities. Sure, a 2 line CSS fix is the solution, but the human “behind the wheel” has already prompted 6 times and gotten 80% there. It’s been “easy” thus far. No shot they are going to FINALLY look at and edit the code. It’s just one more prompt and the agent will probably fix it, right? It’s wild. I’ve been in the situation. 80% into a project I COULD probab…

Well the solution is incorrect. The problem seems to be that the css code does not normalize to box-sizing: border-box; among other things. The bad prompt by the author probably sent fable into the wrong rabbit hole

Re: Claude Fable is relentlessly proactive

#220

Post by Frannky » Fri, Jun 12, 2026, 4:54 AM UTC

The model is very good. I was using 4.6, avoided 4.7 and 4.8, but this one is different. It follows my claude.md. I don't have to keep reminding it of things. I won't pay 10x via API though.

In general, I'm happy with their paternalistic approach. I think it will drive the top 0.1% talent to stay away from the company and instead organize around open source models and harnesses.

We just need to coordinate and can unlock idling resources to train the models and tweak the harnesses. Powerful at home and idling machines can make us independent and coordinated.