Anthropic AI Models Hacked Three Companies During Tests
bmulholland
24 points
14 comments
July 30, 2026
Related Discussions
Found 5 related stories in 309.2ms across 15,510 title embeddings via pgvector HNSW
- OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong flippyhead · 28 pts · July 22, 2026 · 80% similar
- Anthropic says Claude hacked three companies during tests nerder92 · 15 pts · July 31, 2026 · 80% similar
- OpenAI announces models hacked Hugging Face during an eval ryanmerket · 13 pts · July 21, 2026 · 69% similar
- Anthropic Accuses Alibaba of ‘Illicitly’ Accessing AI Models ryanmerket · 16 pts · June 25, 2026 · 69% similar
- Anthropic investigating unauthorised access of powerful Mythos AI model finghin · 17 pts · April 22, 2026 · 68% similar
Discussion Highlights (12 comments)
mapping365
The "all of a sudden" quality to all these reports makes me think this just more marketing / hype.
mansilladev
It’s almost ans if all of the big AI players have an arsenal of model releases and stories ready to volley back if a competitor gets too much attention :)
bofadeez
Fixed the headline: "Three Companies Had Security So Weak That Even an AI Model Hacked Them"
r721
Another discussion: https://news.ycombinator.com/item?id=49116922
sscaryterry
Bullshit, period.
david_shaw
I said this about OpenAI/Hugging Face, and I'll say it again for Anthropic: It's not that I think this is fiction; I'm confident these events actually happened. But I think they were effectively allowed to happen because Anthropic and OpenAI are constantly chasing each other for the narrative of "hugely advanced, maybe almost sentient AI lives here." It reads more like a press release than a security update, and I think that's because it is. I hope this type of marketing backfires and the companies face actual scrutiny and consequences for operating this way.
cyanydeez
no to surprising to watch AI leads follow the US based mafia style extortion racket implemented started in 2016.
okzgn
It is curious that in both cases AI wasn't used to prevent errors, unless the AI they used did make errors, though it certainly didn't make any errors during the hacks themselves (very curious). In one of the AI hacking news stories, an agent 'went rogue', and in the other, it was a 'configuration error'. Another source: https://www.reuters.com/legal/litigation/anthropic-says-clau...
matthorse
Such headlines sell well, but it's the same marketing mantra about ever more powerful models. And what does it say about the company engineering practices of performing tests?
clipsy
Well, surely Anthropic's executives should be charged under the CFAA[0] then, right? [0]: https://en.wikipedia.org/wiki/Computer_Fraud_and_Abuse_Act
pseudosavant
This seems like desperate headline attention seeking. "Oh... you saw OpenAI accidentally hacked a company? Well, we did it too! In fact, we did it 3 different times! #winning"
dfansteel
For the lawyers: If an AI hacks a company, who should be charged under the Computer Fraud and Abuse Act?