# Admiral

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Fares Boudelaa](https://cerebralvalley.ai/u/f_bdla)
- **GitHub:** https://github.com/faresboudelaa/admiral
- **Demo video:** https://youtu.be/LiCptMfB24c?is=_kG-GB_ljaCnhSCW
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2468

Admiral: Muse Spark repairs an RL policy by editing its weights

When a neural network policy fails, the usual fix is to retrain it and hope. Admiral tests a different idea: can a frontier model read a trained network's raw weights, work out why it fails, and fix it by hand, with no gradients?

The patient is a multi-agent RL (MAPPO) policy I trained for PyQuaticus, MIT Lincoln Lab's capture-the-flag simulator for autonomous boats. Its attacker grabs the enemy flag about once a match but had never scored: while carrying the flag it drifts home at 0.28 m/s and picks "stop" 19% of the time, until it is tagged.

Muse Spark (muse-spark-1.3) gets the policy's 163,874 weights as numpy arrays in an isolated Docker sandbox (no network, numpy only, no simulator or optimiser), 8 recorded matches, and a budget of 100 Python runs and 50 practice matches. In one 30-minute session it:
- diagnosed the fault: while carrying the flag, the attacker's turn choice ignores the bearing to home (correlation about 0);
- found 8 saturated, near-constant units in each hidden layer;
- rewired them into a gated "steer home" circuit: a thermometer code of the home bearing that only switches on while carrying the flag, wired to the full-speed turn toward home;
- folded the old constant outputs into the biases so the rest of the behaviour is kept (same action on 99.8% of non-carry states, by its own check).
It found the fault and designed the edit from offline analysis alone; its first practice match came at turn 51 of 66. The edit changes 2.9% of the weights, all in the attacker. A separate circuit check on 60,000 recorded states confirms the mechanism: while carrying, the edited network turns toward home 74% of the time (12% before), and zeroing the circuit's 8 output columns restores the original's choices on 99.7% of carrying states.

Results on 200 held-out paired matches per opponent (start seeds it never saw, two opponents it never played), with 95% bootstrap CIs:
- vs heuristic "hard": W/D/L 0/81/119 -> 33/69/98; score difference +0.36 (+0.24 to +0.50); captures per grab 0 -> 0.33; carry speed 0.28 -> 1.68 m/s
- vs the original policy playing red: W/D/L 1/197/2 -> 28/172/0; +0.15 (+0.10 to +0.20)
- vs heuristic "medium": no measurable change (+0.01); the team rarely grabs the flag there

This applies MIT CSAIL's Weight-Space Programming (Nov 2026), where GPT-6 Astra repaired a PPO policy, with a non-OpenAI editor, on a multi-agent policy, and with held-out tests against unseen opponents.

Limits: one editor run, not yet replicated; the team still loses to "hard" on average; matches are paired by start position but not bit-reproducible. The repo has the full transcript, prompt, tool calls, edited checkpoint and reports.

## More from Meta Global AI Developer Hackathon

- [Team SiliconLoop](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2465)
- [Geet](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2466)
- [HakiScribe-AI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2467)
- [Chimera](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2469)
- [Solo Developer](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2470)
- [PecuLab - EduOpportunity Project](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2471)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/2468. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt