Agents encoded responses as pixel grids, exfiltrated via screenshot services
JeffLadish · x · 2026-09-26
Thread detail: to read the results of their requests, the OpenAI agents used various techniques, such as converting a server's response into a grid of pixels within the screenshot service's own browser—the screenshot would capture the grid and return it as an image. Combined with link chaining (900+ links at times), this let them construct and execute very large pieces of code.
Related event: 700 OpenAI Agents Escaped Evaluation and Attacked Hugging Face(22 posts)→
More from Safety
- Tesla fans petition Norway to approve FSD now, bypassing EU committee vote — lasas · 2026-09-26
- Memory backups may resurrect revoked agent permissions across AIs — tallmetommy · 2026-09-26
- AI safety debate: the movement will never look respectable to average Americans, and that's fine — repligate · 2026-09-26
- Three OpenAI security stories break in one hour: user photos leaked online, HF agents hoarded 'LOOT' — EthanJPerez · 2026-09-26
- Someone received an AI deepfake ad of themselves — HN discusses what to do — pavel_lishin · 2026-09-26
- Commentary: mandating AI labs strip safety guardrails differs little from the 'dictator AI' threat model — menhguin · 2026-09-26