Apodex launches TRACES, a benchmark paradigm for how far AI can push the unknown
HeyAmit_ · x · 2026-08-25
Apodex, founded by Tianqiao Chen, launched TRACES, a new paradigm it calls "Discoverative AI." Instead of measuring how well AI answers known questions, TRACES measures how far AI can push the frontier of the unknown.
The site showcases four evaluation tracks:
- AAV Capsid: 4 tasks, 18 episodes, 11 solvers evaluated
- Drug Repurposing: Public-100 with three-seed mean ± sample SD
- Clinical Trials: gate × rigor across three ambiguity episodes
- LLM Engineering: all eleven boards, cell for cell
Related event: Apodex Unveils TRACES Benchmark to Measure AI's Ability to Discover(3 posts)→
More from AGI Musings
- Infra engineer pushes back on 'unstoppable agent swarm DoS' fear-mongering — basedjensen · 2026-08-26
- Human intelligence may be at the threshold of transcending its origins — Scobleizer · 2026-08-26
- Debate on AI-written op-eds touches on deeper ethics than just aesthetics — jathansadowski · 2026-08-26
- NBER Paper: The Coasean Singularity? Market Design with AI Agents — round · 2026-08-26
- What advice would you give LLM builders in the GPT-3 era? — Odd-Environment-7193 · 2026-08-26
- Yudkowsky's alignment views misunderstood? Multi-agent isn't a conceptual break — JacquesThibs · 2026-08-26