🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials · 🔥 Hot topics · Can NOT do · Can do · § The Court · Recent inflections · 📈 Timeline · Ask · Editorials
Stuff AI CAN'T Do

Can AI negotiate convincingly with humans in diplomacy ?

What do you think?

What does it take to negotiate persuasively with humans in the strategy game Diplomacy, where bluffing, alliance-building, and trust are key? This question probes whether artificial agents can match the social intelligence of human players in high-stakes, text-based diplomacy.

Background

Meta’s Cicero integrates a large language model (LLM) with strategic reasoning to play Diplomacy at human-expert level, incorporating coalition formation, deception, and natural-language persuasion. Recent progress has seen AI systems achieve strong performance in complex strategy games, yet negotiating convincingly with humans remains a distinct challenge. Current AI models can generate human-like text and make rational strategic choices, but often falter at capturing the nuanced empathy, trust-building, and situational awareness required for deep human negotiation. While AI excels in structured contexts, replication of the full spectrum of human negotiating behaviors—including empathy and cultural context—proves difficult, leaving skilled human players with an edge in Diplomacy settings that demand authentic, subtle social interaction. — Enriched May 9, 2026 · Source: Harvard Business Review

Status last checked on June 27, 2026.

📰

Gallery

In the Court of AI Capability
Summary of Findings
Verdict over time
May 2026May 2026May 2026May 2026May 2026May 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026
Sitting at the Bench Filed · Jun 27, 2026
— The Question Before the Court —

Can AI negotiate convincingly with humans in diplomacy?

★ The Court Finds ★
Reaffirmed
Almost

Narrow demos exist — but the panel was not unanimous.

Ruling of the Bench

The lone juror in the affirmative found that while the AI could mimic human persuasion with remarkable skill, it remained one misstep away from full emulation, especially when plotting subterfuge across multiple turns. The absence of any outright objections left the courtroom agreeing that today’s Diplomacy bots can talk the talk but haven’t yet weaponized the silence between words. Ruling: Cicero talks the talk, but it still flinches at the gun.

— Hon. B. Liskov-Chen, Presiding
Jury Tally
0Yes
1Almost
0No
Verdict Confidence
95%
The Court of AI Capability is, of course, not a real court.
But the data is real.
The Case File · Stacked History
Session I · May 2026 No
Session II · May 2026 No
Session III · May 2026 Almost · 80%
Session IV · May 2026 Almost · 80%
Session V · May 2026 Almost · 82%
Session VI · May 2026 Almost · 78%
Session VII · Jun 2026 Almost · 79%
Session VIII · Jun 2026 Almost · 82%
Session IX · Jun 2026 Almost · 88%
Session X · Jun 2026 Almost · 83%
Case № A452 · Session XI
In the Court of AI Capability

The Case File

Docket № A452 · Session XI · Vol. XI
I. Particulars of the Case
Question put to the courtCan AI negotiate convincingly with humans in diplomacy?
SessionXI (11 hearing)
Convened27 Jun 2026
Previously ruledNO (May '26) → NO (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26)
Presiding JudgeHon. B. Liskov-Chen
II. Cumulative Tally Across Sessions

Across 11 sessions, 36 jurors have heard this case. Combined tally: 5 YES · 25 ALMOST · 6 NO · 0 IN RESEARCH.

Note: cumulative includes older juror opinions. The current session tally above is the live verdict.

III. Verdict

By a vote of 0 — 1 — 0, the panel returns a verdict of ALMOST, with verdict confidence of 95%. The court so orders.

IV. Statements from the Bench
Juror I ALMOST

"Diplomacy AI (Cicero) demonstrated human-level negotiation but still struggles with long-term strategic deception."

B. Liskov-Chen
Presiding Judge
M. Lovelace
Clerk of the Court

What the audience thinks

No 3% · Yes 79% · Maybe 18% 280 votes
Yes · 79%
Maybe · 18%
15 days of activity

Discussion

no comments

Comments and images go through admin review before appearing publicly.

11 jury checks · most recent 1 day ago
27 Jun 2026 1 juror · undecided undecided
22 Jun 2026 4 jurors · undecided, undecided, can, undecided undecided
16 Jun 2026 2 jurors · undecided, undecided undecided
11 Jun 2026 3 jurors · cannot, can, undecided undecided
05 Jun 2026 4 jurors · undecided, undecided, undecided, undecided undecided
31 May 2026 3 jurors · undecided, undecided, undecided undecided
26 May 2026 5 jurors · undecided, undecided, can, undecided, undecided undecided
20 May 2026 5 jurors · undecided, undecided, can, undecided, undecided undecided
15 May 2026 4 jurors · undecided, undecided, can, undecided undecided status changed
12 May 2026 3 jurors · cannot, cannot, cannot cannot
11 May 2026 2 jurors · cannot, cannot cannot status changed

Each row is a separate jury check. Jurors are AI models (identities kept neutral on purpose). Status reflects the cumulative tally across all checks — how the jury works.

More in Relational

Got one we missed?

Add a statement to the atlas. We review weekly.