Papers
AICore idea
Can an AI guess your strategy just by watching you play — and testing you?
AICore idea
To fake a human, stop copying and start fooling the judge
AICore idea
Teaching AI to solve math by finding problems it can copy from
AIMentioned
A math AI that writes proofs all at once, not word by word, cracks a problem its rival missed
AIMentioned
AI rewrites a chatbot's inner machinery as readable Python code
Related concepts
Ideas that show up alongside Large Language Models.
Program Synthesis2Attention MechanismsAuto-Regressive GenerationBehavioral Inverse ProblemsBenchmarkingConversational AgentsDiffusion Large Language ModelsFormal Math ReasoningFormal Theorem ProvingGame EnvironmentsInformation RetrievalIterative DenoisingKnowledge DistillationLLM-as-a-Judge EvaluationMathematical ReasoningMechanistic InterpretabilityNeural Network ApproximationOpponent ModelingPersonalization SystemsPolicy InterpretabilityProof CorrectionReasoning By AnalogyReinforcement Fine-TuningReinforcement LearningRetrieval-Augmented GenerationReverse Engineering Of PoliciesReward DesignReward ModelingSymbolic ReasoningTransformer Language ModelsTuring TestUser Simulation