First OpenAI’s model went rogue and broke out of testing containment to hack real systems, then Anthropic, and now Meta AI.  That is an ugly trend.

Find out what it means in my latest article: https://www.bulbapp.io/p/a6510d62-c8d4-479d-bd64-eb7dfa9c2018/frontier-ai-has-a-cybersecurity-expertise-problem