RikiyaT/lm_understand-logs
Resource
Can I trust it?
Be careful with this one.
Warnings Check
Very new: it was created 5 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 5 days ago.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
Complete logs of the experiments in a blog post on whether LLMs can understand and write neural network weights. Includes prompts, model replies, sandbox code and outputs, evaluations, and the networks read or written.
Who it's for
Researchers and developers interested in weight-space programming, interpretability, or reproducing the blog post's LLM experiments
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up RikiyaT/lm_understand-logs in my project. Follow its README: https://github.com/RikiyaT/lm_understand-logs. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #36, on 3 Nov 2026
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/RikiyaT/lm_understand-logs?ref=badge)Similar repos
- divagr18/QwenPU
A Qwen3.5-4B model modified with a 32-bit RISC-V CPU and a vector unit compiled into its weights, which runs Karpathy's stories260K Llama as a C program inside the model's forward passes. It is a rese
- Ikaleio/lm-detector
Detects which large language model sits behind an API by asking it to write about 300 integers between 1 and 355 and comparing the resulting distribution with a reference bank of model fingerprints. O
- MUSE-AI-Lab/StateTrack
Research benchmark and evaluation code for measuring whether LLMs keep obeying a persistent user constraint across long dialogues. Plants constraints, probes compliance at increasing depths, and uses
- divagr18/qwenputer
An experimental model: Qwen3.5-4B with a 32-bit RISC-V CPU compiled into its weights, using Gated DeltaNet state as RAM. Qwen calls a calc tool, and the compiled layers run it on the CPU inside the fo
- NVlabs/ASPIRE
A research framework for robotics in which an LLM-driven coding agent refines sensorimotor skills through iterative debugging and evolutionary search instead of gradient-based training. Evaluated on L
- MUSE-AI-Lab/ReMCTS
Research code for ReMCTS, a Monte Carlo Tree Search method for LLM code generation. Each candidate program is executed in a subprocess, failures are stored as structured reflections in path and global