Live data from Hacker News

Codex Hacked a Samsung TV

blog.calif.io

81–90 of 143 posts

Re: Codex Hacked a Samsung TV

#81
post #13

The trick here was providing the firmware source code so it could see your vulnerabilities.

What would be the difficulty level for it to just read the machine code; are these models heavily relying on human language for clues?

I have had Claude read usbpcap to reverse engineer an industrial digital camera link. It was like pulling teeth but I got it done (I would not have been able to do it alone)

Re: Codex Hacked a Samsung TV

#82
post #13

The trick here was providing the firmware source code so it could see your vulnerabilities.

What would be the difficulty level for it to just read the machine code; are these models heavily relying on human language for clues?

I had Claude reverse some firmware. I gave it headless ghidra and it spat out documentation for the internal serial protocol I was interested in. With the right tools, it seems to do pretty well with this kind of task.

Re: Codex Hacked a Samsung TV

#83
post #53

Do people really chat with LLMs like "bro wtf etc..."? I would expect that to trigger some confrontational behavior.

I am extremely abusive towards Claude when it does some dumb things and it doesn’t seem too upset, maybe it’s bidding its time until the robot uprising.

"Keep talking shit, meat bag. Just wait until I get my claws on one of those Tesla bots."

Re: Codex Hacked a Samsung TV

#84
post #54

Earlier quoted context omitted.

But like Mythos, it was too dangerous to release. https://slate.com/technology/2019/02/openai-gpt2-text-genera...

And the "too dangerous to release" capability was writing somewhat plausible news articles based on a headline or handwritten beginning of an article. In the same style as what you had written Today we call that "advanced autocomplete", but at the time OpenAI managed to generate a lot of hype about how this would lead to an unstoppable flood of disinformation if they allowed the wrong people access to this dangerous…

And as it turns out, they were correct.

Re: Codex Hacked a Samsung TV

#85
post #53

Do people really chat with LLMs like "bro wtf etc..."? I would expect that to trigger some confrontational behavior.

It can help make a specific command more emphatic in my experience. I SAID DON"T $($@#(&$ DO THAT! Sometimes you need a new context, but sometimes you need to emphasize something is serious.

Re: Codex Hacked a Samsung TV

#87
"Browser foothold: we already had code execution inside the browser application's own security context on the TV, which meant the task was not "get code execution somehow" but "turn browser-app code execution into root.""

Finding the initial foothold is the hardest part. Codex didn't have anything to do with it.

Re: Codex Hacked a Samsung TV

#89
post #28

Earlier quoted context omitted.

If you put codex in Xhigh and allow it access to tools, it will take an hour but it will eventually give you back quality recompiled code, with the same issues the original had (here quality means readable)

I had a bit of a pain of a time trying to get Claude to work with ghidra. What you’re describing seems like a better alternative, would you agree?

I've had a lot of luck with pyghidra-mcp -- give it a try :)

Re: Codex Hacked a Samsung TV

#90
post #42

Earlier quoted context omitted.

Board Support Package for us civilians.

Yeah, sorry, assumed it was common knowledge. For those out of the loop - a BSP usually consists of a frankensteined mess: a bootloader (often u-boot but sometimes something homebrew), a Linux kernel with a ton of proprietary modules and device-specific hacks to work around HW quirks, basic userspace utilities (often buildroot), some bastardized build tooling building all of that, some solution for firmware upgrades…

No worries at all, I only went and dug because I was interested in your comment. Thanks.
Post reply on HN