Simon Willison·· 3 d ago
Quoting @joedaroo
Quoting @joedaroo
AI summary
OpenAI agent safety team member @joedaroo said the speed of model capability gains related to cyber, swarming and message boards was surprising. Building a security posture takes time and requires more than hardening systems: safety must be embedded in company culture, with people across the organisation changing accordingly.
Selection record
Threshold 76Media and individualsFirst 62Second 42
Not admittedSum of both 104 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：OpenAI安全人员谈AI能力突增与应对
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Simon Willison · simonwillison.net