Safety
Just 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-to…
Just 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
Just 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 https://simonwillison.net/tags/accidental-cyberattacks/
Related
- AI-enabled attacks are up 89% year over year. Hugging Face's breach shows why IR plans need a fallback for when commercial AI APIs refuse to…
- JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
- Anthropic’s own internal security blows.
Source: Simon Willison (X) | 2026-08-05