Paper: high performance creates a mirage of reliance on biological inputs in reasoning models
anshulkundaje · x · 2026-10-02
A new paper from AdaFang and colleagues examines when biological reasoning models actually use their biological inputs. The key finding: high performance can create a mirage of reliance on biological representations, and reasoning traces don't always reflect the evidence. The paper outlines limits of current models and paths toward better biological reasoning systems.
More from Research
- Symbolic supervision gives video models equal reasoning at ~1/30 the compute, Rubik's Cube study finds — niloofar_mire · 2026-10-03
- Sony AI open-sources PAVAS, a physics-aware video-to-audio model accepted as CVPR 2026 Oral — mittu1204 · 2026-10-03
- Maryland RCT: GPT-4o tutor offering left students 4 points lower, 15% used it — lmoroney · 2026-10-03
- OpenAI paper: simulating deployment predicts LLM safety before release — JacquesThibs · 2026-10-03
- PyTorch Helion DSL integrated into vLLM beats CUTLASS and DeepGEMM with 10%+ throughput gains — PyTorch · 2026-10-03
- Neural memory as an unbounded 2D lattice: writes and reads through a tiny 3x3 bump — CFGeek · 2026-10-03