lm_understand-logs
lm_understand-logs is Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - RikiyaT/lm_understand-logs. It is ranked #142 on the Dev Radar, in Other, first seen 52 min ago and shared in 2 posts (1.8k views).
GitHub - RikiyaT/lm_understand-logs: Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' · GitHub Skip to content Navigation Menu Sign in Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation lm_understand-logs Public Notifications You must be signed in to change notification settings Fork 0 ( 0 ) Star 11 ( 11 ) You must be…
What people said about lm_understand-logs on X
🤯天呐！GPT-6 Astra 居然直接“手改” 开源权重，Qwen3.5-0.8B小模型数学能力提升近6倍！无训练、无梯度！ MIT CSAIL 团队让 GPT-6 Astra 直接读取并编辑 Qwen3.5-0.8B 的权重（不是微调！），仅改动 0.016% 的参数，就解决了官方模型卡都警告的推理死循环问题，数学能力最高提升约 6倍，指令跟随也涨了约 3倍！ 这就是他们提出的 Weight-Space Programming（权重空间编程）：前沿大模型已经能原生读写神经网络权重了！ 核心亮点 🔹只改了 0.016% 权重（约13万个参数），无梯度、无训练 🔹修复 Qwen 官方已知的推理循环问题…
— @NFT_Chen, 52 min ago · 20 likes · see the post
😲不可思议！向GPT-6 Astra喂了4个开源小游戏的神经网络权重。 这4个网络长得一模一样（同样结构、同样输入输出），只给它一堆纯数字权重，不告诉它是什么游戏，也不给任何提示。 结果它直接全部认出来了：Breakout、Pong、Pac-Man、Freeway，准确率极高。 AI现在不仅能玩游戏，还能直接“读懂”游戏AI的脑子长什么样。 #GPT6Astra #AI #神经网络 #WeightSpaceProgramming #开源游戏 #LLM https://x.com/nft_chen/status/2117335503955800533?a=AtqDzRLcSmNpJKaSTXk&s=46…
— @NFT_Chen, 14 min ago · 12 likes · see the post
Alternatives to lm_understand-logs
- deepseek-v4.1-flash-1017-gguf — Image-Text-to-Text model with 748B parameters. Download, explore files and run it on Hugging Face.
- modelscope.ai — 📄 Technical report
- numbat — Machine learning model with 6.8T parameters. Download, explore files and run it on Hugging Face.
- deepseek-v4.1-flash-1017-uncensored-gsq-rco-gguf — Text Generation model with 552B parameters. Download, explore files and run it on Hugging Face.
- nanbeige4.3-33b — We’re on a journey to advance and democratize artificial intelligence through open source and open science.
- hairdeck — HairDeck: Animation-Ready Stylized Hair Cards from a Single Image - hyz317/HairDeck
lm_understand-logs in numbers
- Rank on the Dev Radar: #142 of 9055
- Shared in 2 posts by 1 account: @NFT_Chen
- 1.8k views on those posts
- First seen 52 min ago, last shared 14 min ago
- Pricing seen by AGK Intelligence: open source
- Market: Other
FAQ
What is lm_understand-logs?
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - RikiyaT/lm_understand-logs It was first shared on X 52 min ago and is ranked #142 on the Dev Radar.
Is lm_understand-logs free?
It is open source.
Who shared lm_understand-logs?
1 account on X, including @NFT_Chen, in 2 posts totalling 1.8k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9.1k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-02 20:07 UTC. Full method.