AI

Rational Use of Time for Social Coordination in Humans and AI

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 13/11/2026, 07:48:24 UTC.

Briefings

A study published in November 2026 using the Mind card game evaluated 150 humans and two AI model classes (computer-use agents and LLMs). Humans successfully used implicit temporal cues to coordinate, while AI models failed to adapt their strategies over repeated interactions. The research suggests human probabilistic reasoning emerges without real-time experience, presenting new challenges for AI coordination.

Key points

• Humans use implicit temporal cues to infer partners' beliefs during dynamic social coordination in the Mind card game.
• AI models tested failed to adapt their behaviors to partners' signals over the course of repeated interactions.

Context

This research investigates how humans and AI systems coordinate using only time as a signal, without explicit communication. The study uses a cooperative card game where players must achieve shared goals across repeated interactions, testing whether AI can replicate human implicit probabilistic reasoning about continuous-time signals.

Limitations

The study covers 150 humans and two AI model classes but does not include other model types or human participants. Results are based on a single card game task and may not generalize to all social coordination scenarios. Findings are preliminary and subject to further validation.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 13/11/2026, 07:53:54 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeidtwh6fpbiolinypxpquowl6cftfjrgml26635qtm3ibicdvwyque