Ahmedn1/wsplab-patch-minatar-seaquest

reinforcement-learning model by Ahmedn1

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

A wsplab patch. An LLM (Claude Opus 5.5) read this small game policy's weights and changed 32 of them directly: no training, no gradients, and no running the network in its own code. Mean return rose from 52.1 to 75.7 over 2,000 held-out episodes. Verdict: confirmed. The edit beats the original on held-out episodes, and beats a random edit of the same size by +74.8 ± 0.9. GPT-6 Astra wrote this policy from scratch in Experiment 5 of Sparks of Weight-Space Programming (Takehi, Teoh, Zhang and Khattab), and it scored 53.1 there. It is networks/seaquest/hand.npz in the authors' release, converted to safetensors here (base/model.safetensors) without any change. W2 32×32, W3 32×6. 32 entries changed: 16 in W2, 14 in b2, 1 in W3 and 1 in b3. W1 is untouched. The full session is in evidence/session/. In the editor's own account (evidence/session/finalanswer.md), it read the network as a hand-built rule…

Ahmedn1/wsplab-patch-minatar-seaquest on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-09T07:06:50.592Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

Ahmedn1/wsplab-patch-minatar-seaquest is a reinforcement-learning model repository published by Ahmedn1 on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: reinforcement-learning
Library: Not reported
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: Not reported
Architecture: Not reported
License: cc-by-4.0
Access: Not gated by Hugging Face
Created: 2026-11-09T06:49:22.000Z
Last modified: 2026-11-09T06:49:24.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion