Skip to content
Simon Willison·· 2026-09-29

Quoting @joedaroo

Quoting @joedaroo

AI summary

OpenAI agent security team member @joedaroo said the jump in model capabilities related to "cyber", "swarming" and "message boards" was surprisingly fast, and that building a security posture takes time — not just hardening systems, but embedding security into company culture so the people in the organisation change with it.

Selection record

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