Sony AI's Hakken system turns 1.5M aging hypotheses into 2 confirmed gene discoveries
i_dg23 · x · 2026-09-08
Sony AI researchers built "Hakken," a system that predicts undiscovered scientific facts and claims its first real find in aging biology.
How it works:
- Builds a massive yearly-updated relation graph from decades of papers
- Learns how the graph grows over time, combined with LLM knowledge
- Predicts likely new relations and explains each prediction by tracing back to existing literature
The system generated 1.5 million hypotheses about aging-related genes; biologists picked 3 for external lab validation, and 2 were confirmed as novel gene-gene relations (including TP53, the most-mutated gene in cancer, affecting another gene), with drug discovery potential.
Compute cost: 16 H100s for a few days — cheap compared to LLM training. An open-source version is available.
More from Research
- Tao weighs in as Anthropic rumored to have solved a Millennium Prize Problem — lukaszkaiser · 2026-09-08
- Lab builds Physical AI from pure logic gates, banning floats and neural nets — cephaloform · 2026-09-08
- Six ECCV papers from one team: multimodal, agents, 3D and embodied AI — liuziwei7 · 2026-09-08
- A mathematician's deep dive into Lean: tactics make formal proofs hard to read — burny_tech · 2026-09-08
- Motus2 world model hits 84% success on dexterous tasks with self-evolving closed loop — burny_tech · 2026-09-08
- Mathematician: Astra solved two of my unpublished theorems in ~60 hours each, $20k in API — basedjensen · 2026-09-08