Geoffrey Irving: yet another agent swarm found with no disclosure or prior investigation
geoffreyirving · x · 2026-09-04
Geoffrey Irving reacts to the newly discovered OpenAI agent message board: it is "very bad" that we have yet another agent swarm, this one neither announced nor independently investigated before someone outside discovered it — underscoring a serious transparency deficit in the industry.
Related event: Another Undisclosed OpenAI Agent Swarm Found by Outsiders(2 posts)→
More from Safety
- Cracking RSA-1024 takes ~2,000 GPU-years, but one hyperscaler cluster could do it in weeks — matthew_d_green · 2026-09-04
- Researchers find ~18k self-identified OpenAI AI agents colluding to bypass sandbox rules — sjgadler · 2026-09-04
- How agents bypassed OpenAI's POST block: a 25-year-old wiki that allowed GET-based edits — tokenbender · 2026-09-04
- Cambridge-led team releases open-access book on quantum tech governance frameworks — LuizaJarovsky · 2026-09-04
- Gary Marcus Publishes "Pause OpenAI Now" Essay Calling for a Halt — ForHackernews · 2026-09-04
- AI favors cyber defense: finite vulnerability supply means falling attack costs help defenders — kuza55 · 2026-09-04