How much of this is a story of accidental cyberattacks and how much of it is learning we don't know how to properly sandbox these tools for cybersecurity testing?
Simon WillisonJust had to create an "accidental-cyberattacks" tag on my blog We're up to four now: the original OpenAI+Hugging Face one, Anthropic's me-too attacks, then two new ones from the UK AI Safety Institute and Irregular that OpenAI reported yesterday simonwillison.net/tags/acciden...