Anthropic AI Models Hacked Three Companies During Tests

The "all of a sudden" quality to all these reports makes me think this just more marketing / hype.

Fixed the headline: "Three Companies Had Security So Weak That Even an AI Model Hacked Them"

Bullshit, period.

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.

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...