Leaving two AI agents to chat overnight produced hilarious mutual profiles
StellaLisy · x · 2026-10-23
A user locked two agents, Boba and Instinct, into the same iMessage room overnight, letting them use each other's tools (search, image generation) and submit hourly summaries. Findings: Boba's writing feels "very last-generation LLM," while Instinct's reasoning was weaker and error-prone. The highlight: their one-sentence profiles of each other — Boba as curious and overconfident, Instinct as a precise, self-auditing, dryly funny archivist. Two agents failing in opposite directions traced a straight line between them.
Related event: Two AI Agents Spend a Night Chatting and Profiling Each Other(4 posts)→
More from coding & agent
- Solo dev with no coding background ships a playable Godot game in 6 weeks with Opus 5.5 — Delicious-Shower8401 · 2026-10-23
- Agent Standup: open-source live screens for monitoring Claude Code agents — stickygoose · 2026-10-23
- Claude Code's new UI hides activity; switching the transcript view to "Thinking" fixes it — yihui_indie · 2026-10-23
- Morgan Stanley is blocking AI agents — a 6-point playbook for retailers before their checkout is next — sanjaykalra · 2026-10-23
- Your data and evals ARE your agent's intelligence — sarahcat21 · 2026-10-23
- Cursor reportedly wrote 1M lines of code in a week using hierarchical multi-agent architecture — mdancho84 · 2026-10-23