OpenAI safety staff member discusses challenges from sudden AI capability gains
What happened
On 29 September 2026, Simon Willison reported that @joedaroo, a member of OpenAI’s agent safety team, had discussed the safety challenges posed by sudden model capability gains. He said the speed of advances in capabilities related to cyber, swarming and message boards was surprising. Building a security posture takes time and requires more than hardening systems: safety must become part of company culture, with people across the organisation changing accordingly. This is the latest confirmed development in the event.
Written by AI from the reports · updated 2 d ago
Timeline
Follow the reports to see the event from each side.
- Simon WillisonQuoting @joedaroo
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.
Heat of this event
Current heat 3·Peak in the comparable range 5（Sep 30 01:00）·Change over 24 hours in the comparable range -50%
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.