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
- Daily AI brief: GPT-Live-1 in API, OpenAI pauses $200 Pro signups amid Astra demand — koltregaskes · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11