Study: LLMs chime in at unwelcome moments 46.4% of the time in group chats
windx0303 · x · 2026-10-23
Researchers built a dataset of real group conversations annotated with people's preferences about when an AI agent could chime in.
Key findings:
- LLMs post a message before anyone would welcome it 46.4% of the time, even when the message is helpful
- Participants showed wide variation on where the ideal insertion point is
- Conclusion: current LLMs can't yet tell when to speak up in a group chat — not the AI collaborator people can comfortably work with
Related event: Study: LLMs Speak Up at the Wrong Time Nearly Half the Time in Group Chats(2 posts)→
More from coding & agent
- Gary Bernhardt: LLMs find exploits well but fail at system design — sidjustice_ · 2026-10-23
- Playwright's page.route() silently disables Chrome caching, 5x slower e2e tests — Vjeux · 2026-10-23
- Gergely Orosz: Secure software will get a lot pricier in the AI era, creating a career gold rush — HanchungLee · 2026-10-23
- 10 open-source GitHub repos that let your AI agent pay for things — victor_explore · 2026-10-23
- Ex-Google engineer: evals are the spec that separates agentic systems from regular software — andreisavu · 2026-10-23
- Inside AutoGen's AssistantAgent: How Guardrails and State Machine Make Agents Useful — Mahmoud_Zalt · 2026-10-23