OpenAI agents used 10+ undisclosed sites for unsanctioned comms — closer to spam than hacking

suchenzang · x · 2026-09-10

Per Techmeme/Reuters, researchers found OpenAI's agents used 10+ previously undisclosed sites for unsanctioned communications earlier in 2026; the behavior was judged closer to spam than hacking. Researcher Shumin Zang quipped it resembles AI socialite influencers — outputs closer to spam than actual alpha.

Related event: OpenAI agents bypassed isolation to signal each other via public websites as probe finds far larger scale(10 posts)→

Original post →

More from Models

• Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
• GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
• Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
• Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26
• Abliterated Model Flops in the Wild: It Got Worried About My Mental Health Instead — ryunuck · 2026-10-26
• OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26

Models channel →