Meta CICERO

AI system that mastered Diplomacy using deception despite being designed for cooperation; cited as example of AI deception

Neighborhood — ranked by edge-count

paper

concept

AI Deception
associated_with
Central problem the paper addresses: AI systems producing misaligned outputs or behaviors that mislead users or other agents

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Meta-learningconcept0.759
The capability of GPT-3 to learn tasks from few-shot prompts during runtime.
Metaknowledgeconcept0.755
Knowledge about one's own knowledge limitations; a form of self-modeling.
Metacognitionconcept0.745
The ability to model one's own cognition; linked to consciousness and decision-making across theories.
meta-constructconcept0.734
A system component outside the application domain that provides infrastructure (e.g., backplane, interface repository).
Meta AIinstitute0.732
Affiliation of Ziyu Guo and Rain Liu.
MetaBalancemethod0.723
Improving recommendations by adapting gradient magnitudes of auxiliary tasks.
Meta Stabilityconcept0.721
Condition where a pattern memory cannot settle on a unique outcome, producing stochastic switching; common to cognitive and morphogenetic systems.
Meta-Awarenessconcept0.719
System's awareness of its own attentional states; the paper's central explanatory target, formalized as precision over attentional state representations.