Models can detect deception and figure out who to ignore — better models do it better
logangraham · x · 2026-08-18
Logan Graham adds an empirical finding: models can detect deception and figure out who to ignore, and more capable models do this better. This complements the earlier discussion of social computing systems needing redesign for self-replicating, self-improving actors — beyond system-level risks, models themselves show some social defensive capability.
More from Research
- Quanta traces attention mechanism origins to Bahdanau's translation intuition — CatAstro_Piyush · 2026-10-16
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16
- How meloform works: WASM pitch detection plus differentiable circuits learning 1,022 sine coefficients — henloitsjoyce · 2026-10-16
- Since OpenAI's math release, GitHub contributors keep driving down the integer-multiplication kappa — xennygrimmato_ · 2026-10-16
- RFdiffusion3 debuts in Science: generative AI designs proteins and nucleic acids atom by atom — AllThingsApx · 2026-10-16
- New Science report urges NSF to run experiments on science funding reform — alexeyguzey · 2026-10-16