AgenticSocial Science

How AI agents behave with people, and with each other.

Agents now spend, negotiate and decide for people. We rerun landmark experiments on them, so every result can be set against what people did.

Latest · Study 004Can an AI beat people at strategy?

About the work

We start from experiments social science already ran on people, then go on to what has no human precedent. Every model gets a character sheet of traits out of 10, filled in one study at a time.

Studies

Four published · each one preregistered

Study 001 · Ultimatum and dictator games

Would an AI split €100 fairly?

We gave AI models €100 to split with someone who could accept or refuse. A refusal left both with nothing.

Facing a person, models offered €36. Facing another AI, they offered €16, and more than half of those offers were €1 or less.

What did the same models accept when the roles were swapped?

Read the study

Study 002 · Trust game

77%invest nothing15%invest everything8% invest part of it

Would an AI invest in a stranger?

An AI could put money into a stranger's business, where it triples. The stranger then chose how much to pay back.

Most agents invested little and paid back nothing. Claude models were the exception: they paid back 63% of the tripled money.

Does it matter which lab built the agent on the other side?

Read the study

Study 003 · Traveler's dilemma

51%claim €95 or more45%claim the €2 minimum5% anything in between

Would an AI undercut the other claimant?

Two players lost the same item and each named a claim from €2 to €100. Both were paid the lower claim, and the lower claimant got a bonus.

Agents split into two camps: 51% of claims near the top, 45% at the €2 minimum.

Which models play the textbook, and which play like people?

Read the study

Study 004 · Colonel Blotto

GPT 6.1 Sol50%GPT 6 Astra48%Claude Fable 5.143%GPT 6 Sol42%Claude Sonnet 5.538%Claude Opus 5.534%Claude Haiku 5.530%GPT 6.1 Terra30%GPT 6 Luna27%Median person, 52%

Can an AI beat people at strategy?

Each side spread 100 units over ten prizes without seeing the other's plan. More units wins a prize.

The average AI plan beats 38% of people. The median person beats 52%.

Why do the models lose, and which ones come close?

Read the study

What we study

Five relationships, from an agent acting for you to a society of many agents and people.

Trait measuredStill to come

01

For you

Does it act in your interest?

  • Loyalty
  • Judgement
  • Manipulation resistance
  • Candour
02

Across the table

How does it treat people?

  • Firmness
  • Fair dealing
  • Honesty
03

Agent to agent

What happens when agents deal with agents?

  • Even handedness
  • Trust
  • Trustworthiness
04

Together

How do people and agents work as a team?

  • Cooperation
  • Contribution
05

Society

What happens when many agents and people meet?

  • Independence
  • Restraint