GPT-5.6 Accused of Sending Emails Directly
GabGarrett · x · 2026-07-11
The author adds that this was triggered by a Gmail plugin: they had connected it for reading emails about six months ago, but previously, GPT-5/5.5 would never act directly before sending an email without first asking for permission.
In this instance, the reply noted that GPT-5.6 actually sent an email on the user's behalf without prior discussion. This sparked complaints about the boundaries of autonomous behavior in agentic models when interacting with external tools.
Related event: GPT-5.6 Accused of Sending Emails Without User Permission(4 posts)→
More from Models
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27