AI + formal verification: a researcher asks what happens when formalization becomes cheap
IanArawjo · x · 2026-09-25
Kaiyu Yang, working on AI + formal verification since 2018, reflects in a long-form post on the current excitement and a deeper question: what happens when formalization becomes cheap—what can it actually solve, and what changes? HCI researcher shreya adds that using AI to help humans author more specifications is an interesting open direction, and Ian Arawjo agrees the HCI angle deserves exploration.
Related event: Researcher reflects on what cheap formalization will unlock(2 posts)→
More from Research
- Sakana AI × Pathway Post-Transformers lecture on AI and the brain now online — kaixhin · 2026-11-11
- Defending METR: public data can't second-guess its AI speedup findings — peterwildeford · 2026-11-11
- Adversarial RL envs for backdoor insertion vs. detection: where does it converge? — DimitrisPapail · 2026-11-11
- DiffusionEngine: an open-source modular PyTorch DDPM framework seeking contributors — Euphoric-Incident-93 · 2026-11-11
- UniPath (NeurIPS 2026): adaptively coordinating understanding and generation in one model — jindong_wang92 · 2026-11-11
- Versor pitches real2sim2real: robotics sim needs physical dynamics, not just visuals — abhishekunique7 · 2026-11-11