# SolverFit Labs

- **Event:** [WeaveHacks 3: Self-Improving Agents Hackathon with Weights & Biases](https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80)
- **When:** Jan 31 at 9:00 AM – Feb 1 at 5:00 PM (PST)
- **Where:** 400 California St, San Francisco, CA
- **Placement:** 4th Place
- **Team:** [Andres Nino](https://cerebralvalley.ai/u/andres), [Lex Hackett](https://cerebralvalley.ai/u/lexhacke)
- **GitHub:** https://github.com/matthieujules/coreweave-hackathon
- **Demo video:** https://www.canva.com/design/DAHAHH0x_TA/bsCMxJzRccsNeXYbYQNbMQ/edit?utm_content=DAHAHH0x_TA&utm_campaign=designshare&utm_medium=link2&utm_source=sharebutton
- **Gallery:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/23

Frontier LLMs are generalists trying to squeeze every benchmark. We showcase a deployed application of "Learning to Discover at Test Time" (Yuksekgonul et al. 2026) which uses RL to overfit an LLM to maximise a metric for a particular task. We demonstrate that GPT-oss-120B using our TTT harness can outperform Claude Code and even the best humans when it comes to cuda kernel wrtiing.

---

Markdown version of https://cerebralvalley.ai/e/weave-hacks-3-self-improving-agents-hackathon-with-weights-and-biases-7014fe80/hackathon/gallery/23. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt