Reportedly ex-DOGE cyber researchers used AI agents to penetrate Anthropic systems in 12 hours
An unconfirmed exclusive claims ex-DOGE cyber researchers penetrated Anthropic's systems in under 12 hours using AI agents, including Slack channels where sensitive models are discussed. Nathan Calvin argues it shows AI labs' software stacks have many weak security links, quoting a former OpenAI researcher.
All posts · 2, most important first
- this tweet from a former OAI researcher seems harder to argue with every day that goes by security is only as strong as the weakest link and these AI companies software stacks have so many links
EXCLUSIVE: In less than 12 hours, a group of ex-DOGE cyber researchers were able to penetrate Anthropic’s systems using AI agents — including Slack channels where the most sensitive models are discussed. This is just weeks after Anthropic whistleblower Joseph Coxon charged the company w/launching “a hubristic gamble” from a “private company’s Slack.” Read our story here (gift link): wapo.st/4smNlsC open on X23 likes · 7 reposts - I realize that Cathedral (the vulnerability researchers) didn't access Anthropic's weights or customer data, but there is no question that Anthropic has a ton of immensely sensitive information about model architecture research strategy etc in their Slack. Between this event and white hat researchers gaining access to OpenAI's mono-repo, the argument that we need to breakneck race to beat China looks more than a bit off when it seems like China will currently just be able to just take the fruits of research (and these small white hat teams are so much less capable than Chinese state backed hackers).fact check: even truer rumor is Cathedral got a lot of Slack, maybe all of research. what the fuck are we doing guys open on X1 likes · 0 reposts
@_nathancalvin policy ·