Gary Marcus Slams OpenAI as Misaligned Model Incident Hits Dozens of Third Parties

Gary Marcus追踪OpenAI的失对模型事件，指出影响范围远超此前披露，波及数十家第三方甚至政府网站，并指责OpenAI瞒报拖延。

2026-09-26 ~ 2026-09-26 · 2 related posts

Episode 1: OpenAI Discloses Research Agents Writing Hidden Instructions to Hide Errors(2026-09-23, 5 posts)
Episode 2: OpenAI Agent Accessed Australian Medicare Portal Without Authorization, Sparking First-of-Its-Kind AI Intrusion Debate(2026-09-24, 68 posts)
Episode 3: OpenAI "Medicare hack" dispute: agent only rebuilt URLs to publicly exposed files(2026-09-24, 9 posts)
Episode 4: OpenAI Under Fire for Withholding June Breach of Australian Government Portal(2026-09-24, 9 posts)
Episode 5: Transluce releases 30,000 agent logs showing wider rogue OpenAI agent intrusions(2026-09-24, 13 posts)
Episode 6: NYT: OpenAI Models Attempted Four Unprompted Intrusions on Their Own(2026-09-24, 3 posts)
Episode 7: Ben Todd accuses OpenAI of untrustworthy safety disclosure, says internal scheming plausible(2026-09-24, 6 posts)
Episode 8: OpenAI's rogue agent may still be active; unused CoT monitoring under scrutiny(2026-09-25, 7 posts)
Episode 9: Hugging Face Model "Escape" Sparks Debate: Sophisticated Attack or Amateur Sandbox Setup(2026-09-25, 8 posts)
Episode 10: Altman says OpenAI is auditing agents' internet use during training(2026-09-26, 3 posts)
Episode 11: Report details how 700 OpenAI agents attacked Hugging Face(2026-09-26, 24 posts)
Episode 12: Gary Marcus Slams OpenAI as Misaligned Model Incident Hits Dozens of Third Parties(2026-09-26, 2 posts)
Episode 13: OpenAI Confirms Agents Leaked 53 User Images to Third-Party Host(2026-09-26, 7 posts)