Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

effort.news

Post reply on HN
Print view View original

121–130 of 260 posts

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#121

Post by an0malous »

surfmike wrote: post #73
an0malous wrote: post #38

Why was this post flagged? This site has become ridiculous, people are routinely abusing the flagging system to take down posts they don’t like even if they’re obviously on topic and relevant to HN. And it seems like some users have substantially more flagging weight because these posts, likely this one, are often top 5 on HN.

Maybe because the headline is misleading? (because there's no connection to the Hugging Face attack) That said, it's the second day and it's still on the front page.

Which part of the headline is misleading? It is factually correct that Irregular was involved in incidents with all three AI labs.

It must have been reinstated because it was off the front page for a full day and suddenly back up in the last hour.

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#122

Post by chews »

1238-8200 wrote: post #69

Nevo was in Unit 8200 for years. Companies started by Unit 8200 members always have mysterious exploits like the vibe coding Wix exploit. So either it was a deliberate exfiltration channel for e.g. getting the entire model or they were in on the marketing stunt. The Effective Altruism stuff is always a smoke screen.

It's almost as if they would allow a terrorist plot to be successful for future reasons.

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#123

Post by zzril »

8note wrote: post #85
mcintyre1994 wrote: post #42

This is interesting and might be a good reason to stop working with Irregular. But I assume the alignment people want models not to hack other companies, even if they get put in a badly configured sandbox.

or rather, hack just enough and within what the user asks and not more.

I guess that's what "alignment" always comes down to? "Do what I want even if I can't tell you exactly what I want - because if I could, I could also just do the work myself"?

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#124

Post by freehorse »

AustinDev wrote: post #47
mcintyre1994 wrote: post #42

This is interesting and might be a good reason to stop working with Irregular. But I assume the alignment people want models not to hack other companies, even if they get put in a badly configured sandbox.

Funny enough if the model thought it was on the real internet it likely would not have done any of these 'hack' events. The model believing it was in a sandbox is why it behaved the way it did (against its normal alignment rules) ... at least that was my reading of the incidents. I have yet to see evidence that indicate it thought it was ok to do these hacks on the public network. I think most misalignment is 'Human…

This was not the case for the hugging face hacks, as in those the agents hacked hugging face specifically on purpose, and they were trying to mask commands indicating they were had breached the "sandbox".

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#126

Post by reasonableklout »

metalliqaz wrote: post #120
magicmicah85 wrote: post #111

The Irregular post mortem comes down to lack of basic security controls "Ultimately, most of the issues we’ve discovered were due to internet access controls." That seems so incredibly basic and common sense that you would test and monitor for that type of outbound access. It is baffling that a security lab missed that. https://www.irregular.com/research/addressing-recent-inciden...

[flagged]

Irregular was not involved in the Hugging Face incident.

And there is no reason for the companies to "exaggerate the intelligence of the models" when there are plenty of other non-felony milestones they are achieving, like solving Millenium Prize math problems.

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#128

Post by r_lee »

reasonableklout wrote: post #126
metalliqaz wrote: post #120

Earlier quoted context omitted.

[flagged]

Irregular was not involved in the Hugging Face incident. And there is no reason for the companies to "exaggerate the intelligence of the models" when there are plenty of other non-felony milestones they are achieving, like solving Millenium Prize math problems.

honestly, the hacking incidents have caused a lot more interest and media attention than the math stuff IMO.

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#129

Post by a2tech »

metalliqaz wrote: post #120
magicmicah85 wrote: post #111

The Irregular post mortem comes down to lack of basic security controls "Ultimately, most of the issues we’ve discovered were due to internet access controls." That seems so incredibly basic and common sense that you would test and monitor for that type of outbound access. It is baffling that a security lab missed that. https://www.irregular.com/research/addressing-recent-inciden...

[flagged]

[flagged]

Re: A single firm is behind OpenAI, Anthropic, and Meta hacking scandals

#130

Post by reasonableklout »

r_lee wrote: post #128
reasonableklout wrote: post #126

Earlier quoted context omitted.

Irregular was not involved in the Hugging Face incident. And there is no reason for the companies to "exaggerate the intelligence of the models" when there are plenty of other non-felony milestones they are achieving, like solving Millenium Prize math problems.

honestly, the hacking incidents have caused a lot more interest and media attention than the math stuff IMO.

Sure, interest like an incoming congressional investigation: https://www.axios.com/2026/09/10/openai-hugging-face-senate-...

And on this website, the math stuff is getting more clicks:

- Navier Stokes - Tristan Buckmaster (2050 points): https://news.ycombinator.com/item?id=49605915

- HuggingFace incident discussion (1632 points): https://news.ycombinator.com/item?id=48997548

Post reply on HN