Earlier quoted context omitted.
“et AI, Brutus!"
Yon Claude has a lean and hungry look.
An LLM by any other name would hallucinate the same
Hardening Firefox with Anthropic's Red Team
41–50 of 188 posts
Re: Hardening Firefox with Anthropic's Red Team
#42Anthropic feels like they are flailing around constantly trying to find something to do. A C compiler that didn't work, a browser that didn't work, and now solving bugs in Firefox.
I think OpenAI is flailing around too-- we're making an AI-generated shortform video app, we're rescinding restrictions on porn, we're making a... something... with Jony Ive-- but only Anthropic is flailing in a way beneficial to society instead of becoming a trillion dollar heroin dealer.
Re: Hardening Firefox with Anthropic's Red Team
#43> Firefox was not selected at random. It was chosen because it is a widely deployed and deeply scrutinized open source project — an ideal proving ground for a new class of defensive tools. What I was thinking was, "Chromium team is definitely not going to collaborate with us because they have Gemini, while Safari belongs to a company that operates in a notoriously secretive way when it comes to product development."
its just a different attack surface for safari they would need to blackbox attack the browser which is much harder than what they did her
What? The js engine in Safari is open source, they can put Claude to work on it any time they want.
Re: Hardening Firefox with Anthropic's Red Team
#44Anthropic feels like they are flailing around constantly trying to find something to do. A C compiler that didn't work, a browser that didn't work, and now solving bugs in Firefox.
What was Anthropic's "browser that didn't work"?
Re: Hardening Firefox with Anthropic's Red Team
#45[dead]
Re: Hardening Firefox with Anthropic's Red Team
#46Part of that caught my eye. As yet another person who’s built a half-ass system of AI agents running overnight doing stuff, one thing I’ve tasked Claude with doing (in addition to writing tests, etc) is using formal verification when possible to verify solutions. It reads like that may be what Anthropic is doing in part. And this is a good reminder for me to add a prompt about property testing being preferred over st…
Can you give me an example (real or imagined) where you're dipping into a bit of light formal verification?
I don't think the problems I work on require the weight of formal verification, but I'm open to being wrong.
Re: Hardening Firefox with Anthropic's Red Team
#47[flagged]
Re: Hardening Firefox with Anthropic's Red Team
#48Part of that caught my eye. As yet another person who’s built a half-ass system of AI agents running overnight doing stuff, one thing I’ve tasked Claude with doing (in addition to writing tests, etc) is using formal verification when possible to verify solutions. It reads like that may be what Anthropic is doing in part. And this is a good reminder for me to add a prompt about property testing being preferred over st…
Can you give me an example (real or imagined) where you're dipping into a bit of light formal verification? I don't think the problems I work on require the weight of formal verification, but I'm open to being wrong.
To be clear, almost (all?) of mine do not either and it's partially due to the fact I have been really interested in formal methods thanks to Hillel Wayne, but I don't seem to have the math background for them. To the man who has seen a fancy new hammer but cannot afford it, every problem looks like a nail.
The origin of it is a hypothesis I can get better quality code out of agents by making them do the things I don't (or don't always). So rather than quitting at ~80% code coverage, I am asking it to cover closer to 95%. There's a code complexity gate that I require better grades on than I would for myself because I didn't write this code, so I can't say "Eh, I know how it works inside and out". And I keep adding little bits like that.
I think the agents have only used it 2 or 3 times. The one that springs to mind is a site I am "working" on where you can only post once a day. In addition, there's an exponential backoff system for bans to fight griefers. If you look at them at the same time, they're the same idea for different reasons, "User X should not be able to post again until [timestamp]" and there's a set of a dozen or so formal method proofs done in z3 to check the work that can be referenced (I think? god this all feels dumb and sloppy typed out) at checkpoints to ensure things have not broken the promises.
Re: Hardening Firefox with Anthropic's Red Team
#49Earlier quoted context omitted.
This makes sense - they are demonstrating the capability of their core product by doing so? They dont make browsers, c compilers, they sell ai + dev tools.
Capability of a product that makes non-working outputs at a premium? I can hire an intern for that.
Will cost you a lot more ;)
Re: Hardening Firefox with Anthropic's Red Team
#50Earlier quoted context omitted.
This makes sense - they are demonstrating the capability of their core product by doing so? They dont make browsers, c compilers, they sell ai + dev tools.
Seems like a poor advertisement for their product if their shining example of utility is a broken compiler that doesn't function as the README indicates.
Impressive that it made a c compiler though? Or do we judge all programmers by their documentation now?