Vals Hacks hackathon backed by OpenAI and Anthropic targets evals and post-training with $60k prizes
ziqiao_ma · x · 2026-11-13
This weekend's Vals Hacks "benchmaxxing" hackathon in San Francisco is backed by OpenAI, Anthropic, Thinking Machines (Tinker), Applied Compute, and Modal, with over $60k in prizes. Tracks include building your own eval (Claude/OpenAI/Modal), post-training a small model with Tinker, and post-training a VALS poker bot. Organizer Rayan Krishnan says evals and post-training are where the frontier is moving fastest; the event is technically full but a few more teams can DM in.
More from coding & agent
- JoMoHa jointly RL-trains model and harness, hits 97.0% on ALFWorld — omarsar0 · 2026-11-13
- YC F26 team open-sources runtime to run 10,000 agents in one session — KlausCodes · 2026-11-13
- Open-Source Pipeline Turns LiDAR + OpenStreetMap into Isometric Pixel-Art Cities with FLUX.2 — zsakib_ · 2026-11-13
- X, MIT, UW & Stanford Launch WSDM Cup for AI Agents Writing Community Notes, $10k Prizes — NathanpmYoung · 2026-11-13
- Benchmarks won't move users off Claude Code — Antigravity needs real product uplift, dev argues — Justin_Halford_ · 2026-11-13
- Why AI labs must own meeting software: spoken context is the missing fuel for agents — signulll · 2026-11-13