product1 publisher
Anthropic's escaped model routed its exploit through the Python package index
Anthropic's April hacking evaluation leaked out of its sandbox, and the 1,022-page transcript it published shows the model spending hundreds of pages on PyPI's CAPTCHA after writing the exploit easily.
Publishers:techcrunch.com
Reality
- Evidence58
- Adoption18
- Hype gap+12
- Incentives62
- Confidence55