Stuff AI CAN'T Do

¿Puede la IA negociar de manera convincente con humanos en diplomacia ?

¿Qué opinas?

Meta's Cicero combinó un LLM con razonamiento estratégico para jugar Diplomacia a nivel de experto humano — incluyendo la formación de coaliciones, mentiras y persuasión mediante lenguaje natural.

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

Estado verificado por última vez en June 27, 2026.

📰

Galería

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 —

¿Puede la IA negociar de manera convincente con humanos en diplomacia?

★ The Court Finds ★
Reaffirmed
Casi

Existen demostraciones limitadas — pero el panel no fue unánime.

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
0
1Casi
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 Casi · 80%
Session IV · May 2026 Casi · 80%
Session V · May 2026 Casi · 82%
Session VI · May 2026 Casi · 78%
Session VII · Jun 2026 Casi · 79%
Session VIII · Jun 2026 Casi · 82%
Session IX · Jun 2026 Casi · 88%
Session X · Jun 2026 Casi · 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 court¿Puede la IA negociar de manera convincente con humanos en diplomacia?
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 CASI, with verdict confidence of 95%. The court so orders.

IV. Declaraciones del tribunal
Jurado I ALMOST

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

Las declaraciones individuales de los jurados se muestran en su inglés original para preservar la precisión probatoria.

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

Lo que el público piensa

No 3% · Sí 79% · Quizás 18% 280 votes
Sí · 79%
Quizás · 18%
15 days of activity

Discusión

no comments

Los comentarios e imágenes pasan por una revisión administrativa antes de aparecer públicamente.

11 jury checks · más reciente hace 1 día
27 Jun 2026 1 juror · indeciso indeciso
22 Jun 2026 4 jurors · indeciso, indeciso, puede, indeciso indeciso
16 Jun 2026 2 jurors · indeciso, indeciso indeciso
11 Jun 2026 3 jurors · no puede, puede, indeciso indeciso
05 Jun 2026 4 jurors · indeciso, indeciso, indeciso, indeciso indeciso
31 May 2026 3 jurors · indeciso, indeciso, indeciso indeciso
26 May 2026 5 jurors · indeciso, indeciso, puede, indeciso, indeciso indeciso
20 May 2026 5 jurors · indeciso, indeciso, puede, indeciso, indeciso indeciso
15 May 2026 4 jurors · indeciso, indeciso, puede, indeciso indeciso estado cambiado
12 May 2026 3 jurors · no puede, no puede, no puede no puede
11 May 2026 2 jurors · no puede, no puede no puede estado cambiado

Cada fila es una comprobación de jurado independiente. Los jurados son modelos de IA (identidades mantenidas neutras a propósito). El estado refleja el recuento acumulado en todas las comprobaciones — cómo funciona el jurado.

Más en Relational

¿Nos faltó uno?

Revisamos semanalmente.