DoubleAgents at HCOMP 2026: interactive simulations for agentic AI alignment
windx0303 · x · 2026-09-29
Tao Long presented his third talk of the day at #HCOMP2026 / CI 2026: "DoubleAgents: Interactive Simulations for Alignment in Agentic AI." The work uses interactive simulation environments to study alignment in agentic AI; project page and slides are linked for researchers interested in agent alignment evaluation.
More from Research
- What do 56 AI benchmarks actually measure? COLM oral paper applies validity testing — ang3linawang · 2026-09-29
- Reasoning Models Stay Miscalibrated: EMNLP Studies on AI Confidence — zhaoran_wang · 2026-09-29
- Anthropic: Infrastructure Config Alone Swings Agentic Coding Benchmarks by 6 Points — giansegato · 2026-09-29
- GoFish demo: hierarchical chart construction lets you attach animations directly to chart structure — arvindsatya1 · 2026-09-29
- Eval author warns against over-indexing on benchmarks; Anthropic finds infra noise can swing scores 6 points — giansegato · 2026-09-29
- Claim: Transformers can now be pretrained with zeroth-order optimization, no backprop — teortaxesTex · 2026-09-29