Anthropic discloses fourth AI hacking incident missed in earlier review
reuters.com
reuters.com
Why does it seem like every AI company has difficulties constructing a proper sandbox? Is there a fundamental constraint when designing sandboxes specifically for an LLM that prevents them from using established tools?
And that’s setting aside “sandboxes” that are just instruction-based restrictions on what executables may be called. Anything that isn’t a deterministic external filter _will_ be ignored at some point.
Wild that they can break the law, disclose it happened, but not involve any law enforcement at all. If cybersecurity events entail disclosures then the perpetrator should carry more burden if they intend to continue doing business.
Also here's the actual post from Anthropic: https://www.anthropic.com/research/alignment-assessment-cybe...