开源项目Model-Booster支持LLM直接编写网络权重
Start here
2026年11月4日，开源项目 Model-Booster 发布可视化实验环境，探索利用大语言模型 Claude Opus 直接编写小型神经网络的权重代码，无需依赖传统梯度下降进行训练。在该环境中，用户可在浏览器内通过调整滑块来混合权重，实时观察包含约 170k 权重的未训练多层感知机（MLP）在接球、躲避及走迷宫等小游戏中的行为变化。此外，该项目支持本地部署，能够驱动 Claude Code CLI 编写权重并运行测试评估，单次生成通常耗时数分钟。
AI-generated from reports · Updated 11 hours ago
Report timeline
Follow the reports to see different sides of the story.
- Hacker News · AISelectedOpen-source visual lab Model-Booster enables LLMs to directly code neural network weights
Open-source project Model-Booster has released a visual experimental environment that uses Claude Opus to directly code weights for small neural networks without gradient descent training. Users can adjust sliders in the browser to blend weights and observe real-time behavioral changes in an untrained multilayer perceptron (MLP) with roughly 170k weights across mini-games like catching, dodging, and maze navigation. Local deployment drives the Claude Code CLI to write weights and execute test evaluations, with each generation typically taking several minutes.
Story heat trend
Current heat 7·Comparable peak 10（Nov 4 03:00）·Comparable change, last 24 hours–
Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.