MIDREAL
Menu

Home / lm_understand-logs

RikiyaT

lm_understand-logs

WatchingWatchingNone of the above. Nothing stands out yet. More on the methodology page

RikiyaT/lm_understand-logs

Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'

PythonCategories: Local AI

Our summary

This repository contains the complete logs of the experiments described in the blog post 'LLMs can understand and write neural network weights'. It includes prompts sent to the model, responses and reasoning summaries, code run in a sandbox with its output, evaluation scoring, and the networks read or written.

Who it is for: Readers of the blog post who want to check or rebuild its experiments

What the README claims

  • Logs of every experiment in the blog post are included The complete logs of every experiment in the blog post Too broad to verify
  • All 1,125 turns in this release are tool-free All 1,125 turns in this release are tool-free. Not checked
  • Code runs in a sandbox using bubblewrap with no network access bubblewrap, no network, a working folder kept between runs, and a time limit per run. Not checked
  • The repository covers eight experiments, listed in a table | [`exp1_which_game/`](exp1_which_game) | Experiment 1: which game was this network trained on? | Not checked
  • Logs, data and networks are licensed under CC BY 4.0 | Logs, data and networks | CC BY 4.0 | Not checked

Written by AI from the project's README on 2026-11-04. It does not affect the verdict.

Watching: no other rule matched yet.

7-day star gain 40, down from 127 the week before.

Gaining 40 stars this week. Last push 23 days ago.

Verdict

TOO EARLY scored 1h ago

There is not enough data on this project yet to call it. The numbers below are shown anyway.

Too close to call

Early read: we are missing data on the size of the team behind it and how widely it is used. This is an estimate and will be replaced by a verdict once we have the data. How early reads work.

Hype
92
Reality
7
Hype Gap
+84
Momentum
-
Confidence
60%
  • Maintained moves Reality -21 points.
  • Responsive moves Reality -13 points.

Rule verdict-2.0, scoring score-2.0. How we score. Backtest.

Repository on GitHub

Find them on

Maintained by

Maintained by 1 primary developer, 0 external contributors in the last 90 days.

  • RikiyaT is a GitHub individual account.
  • GitHub account created January 2023.
  • Top contributors by commits: RikiyaT 100%.

Why now 3% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

Stars StarsThe number of GitHub stars on the repository at our latest reading.
1,284
Gain 7d Gain 7dStars gained since our latest reading from at least 7 days ago.
+40
Pace Velocity (Nx usual pace)This week's star gain divided by the project's usual weekly gain. The usual gain is the average weekly gain over the 4 weeks before (days 8 to 35 ago), counted as at least 10 stars. 2.0x means twice the usual pace. Without a reading from 35 days ago, the ranking assumes 2% of the stars the project had 7 days ago as its usual weekly gain. More on the methodology page
1.6x
HN points HN pointsHacker News points added up across posts that mention the project, published in the last 7 days.
0 7 days
Downloads DownloadsDownloads per day of the project's package, as the registry (npm or PyPI) reports them.
n/a
Contributors Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.
1
Last release Latest releaseDays since the latest GitHub release was published.
n/a

Gain 24h Gain 24hStars gained since our latest reading from at least 24 hours ago. +1. Forks ForksThe number of GitHub forks of the repository at our latest reading. 167. Open issues Open issuesThe number of open issues on the repository at our latest reading, as GitHub counts them. 11. Days since push Days since pushDays since the last push to the repository. 23 days. Archived ArchivedWhether the owner has archived the repository on GitHub. An archived repository is read-only. no. Hacker News posts in 7 days Hacker News postsThe number of Hacker News posts that mention the project, published in the last 7 days.: 0. Watchers WatchersThe number of GitHub users watching the repository for notifications, at our latest reading. 10.

Facts

Language
Python source, checked 21 Nov 2026
Releases
0 source, checked 19 Nov 2026
Contributors
1 source, checked 19 Nov 2026
Archived
no source, checked 21 Nov 2026

Nerd stuff

Languages
Python (detected), Jinja (detected), Shell (detected)

The Receipts

SourceEvidenceDate
Hacker NewsThread, 3 points, 0 comments8 Nov 2026
Newsletter or feedServing Qwen3.5-0.8B with a 0.016% weight edit: measure the loops, pin the sampling on the server20 Nov 2026
Newsletter or feedAI Models Are Starting to Engineer Other AI Models17 Nov 2026
Newsletter or feedGPT-6 Astra edits a small model’s weights, pointing to AI debugging12 Nov 2026
Newsletter or feedBefore trusting a weight edit, I measured the bug it fixes7 Nov 2026
Newsletter or feedWeight-Space Programming: When LLMs Learn to Read and Rewrite Neural Network Weights6 Nov 2026
Newsletter or feedAn LLM edited a small model's weights directly and its math score rose 6x5 Nov 2026
Newsletter or feed3 of 4 weight games guessed from raw numbers4 Nov 2026
Newsletter or feedA Small Weight Edit Helped Qwen Finish Its Reasoning. That Defines the Result.4 Nov 2026
Newsletter or feedComment GPT-6 Astra a corrigé Qwen3.5-0.8B en modifiant 0,016 % de ses poids4 Nov 2026
Newsletter or feedGPT-6 Astra แก้ไข Qwen3.5-0.8B ได้อย่างไร ด้วยการแก้ไขน้ำหนักโมเดลเพียง 0.016%4 Nov 2026
Newsletter or feedGPT-6 AstraがQwen3.5-0.8Bを重みの0.016%編集で修正した方法4 Nov 2026
Newsletter or feedQwen weight editing: how Astra reduced thinking loops3 Nov 2026
Newsletter or feedQwen 3.8 27B on my laptop can interpret model weights, too3 Nov 2026
Newsletter or feedGPT-6 Astra Edited Qwen3.5-0.8B's Weights. The MATH-500 Jump Was a Loop Fix3 Nov 2026

What changed recently

GitHub release dates we stored. We do not track license changes yet.

Cite this

lm_understand-logs is a GitHub project at https://github.com/RikiyaT/lm_understand-logs written mainly in Python, described there as "Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'".

Source: https://midorreal.com/project/rikiyat-lm-understand-logs, checked 22 November 2026. The same facts as JSON: /project/rikiyat-lm-understand-logs.json.

Rank history

Peak day: +202 stars on 4 Nov 2026, 18 days ago.

Best rank on Blowing up: #8 on 10 Nov 2026.

Label timeline

  • 3 Nov 2026: Watching
  • 4 Nov 2026: Surging
  • 5 Nov 2026: Watching

Stars

Stars each day Stars each dayThe highest star count we recorded on each day., last 19 days. Without JavaScript this shows the last 30 days.

Events in this window

Dated items we stored, last 30 days. They sit near the chart, they do not explain it.

Stars gained each day Stars gained each dayThe difference in the daily peak star count between consecutive days that both have a reading., between readings on consecutive days. Last 30 days in the fallback.

Packages

- We checked npm, PyPI, Docker Hub, crates.io and Homebrew and found no package that links to this repository.

Signals

SourceWhat we measuredChecked
GitHub1,284 stars, 40 gained in 7 days21 Nov 2026
Hacker News1 post stored, 0 points in the last 7 days15 Nov 2026
Feed mentions14 mentions in tracked newsletters and blogs20 Nov 2026
npmNo linked package found-
PyPINo linked package found-
Docker HubNo linked package found-
crates.ioNo linked package found-
HomebrewNo linked package found-
deps.devNot tracked yet-
Hugging FaceNot tracked yet-
BlueskyNot tracked yet-
Stack ExchangeNot tracked yet-
YouTubeNot tracked yet-

Attention vs adoption

Attention: above 76% of tracked projects 76%
Star velocity against all tracked projects

Adoption: not enough data to rank
Downloads, dependents and pulls

Not enough comparable data yet to set attention against adoption. This describes the numbers; it is not a verdict.

Compared with Local AI

MeasureThis projectCategory median
Star velocity1.60.7
Days since releaseno data8.0
Contributors, all time13
Median time to first reply on issuesno data20 hours
Commits in the last 30 days131

Star velocity: above 78% of Local AI projects

Contributors, all time: above 0% of Local AI projects

Commits in the last 30 days: above 8% of Local AI projects

Compared with the project's first category only. A percentile line appears only where at least 30 projects in the category have the measure. This describes the numbers; it is not a verdict.

Compare with

Hacker News

Points by day Hacker News points by dayPoints on Hacker News posts that mention the project, grouped by the day each post was published. across 1 post and 1 day, 3 points in total.
PostPoints PointsThe points the post has on Hacker News.Comments CommentsThe number of comments on the post on Hacker News.Date
Hacker News post 3 0 8 Nov 2026

Caveats

  • GitHub lists 1 contributor to this repository. Source
  • The repository has no security policy on GitHub. Source
  • The repository has 0 releases on GitHub. Source

Repo health

  • Languages LanguagesShare of the repository's code by bytes, as GitHub's language detection reports it. The five biggest languages are named and the rest are grouped as Other.Python 99%, Jinja 1%
  • License LicenseThe SPDX license id GitHub detects, and a class: Open source (OSI) if the license is on the Open Source Initiative approved list, Source-available if the code is readable but the license limits use, Unclear if GitHub cannot match a known license, No license detected if it finds none. A public repository without a license is not open source.Unclear
  • Repository age Repository ageTime since the repository was created on GitHub. This is the repository, not necessarily the project, which may have existed elsewhere before.24 days, created 29 Oct 2026

Development

  • Commits in the last 7 days Commits in the last 7 daysCommits to the repository in the last 7 days, as GitHub counts them.0
  • Commits in the last 30 days Commits in the last 30 daysCommits to the repository in the last 30 days, as GitHub counts them.1
  • Commits in the last 90 days Commits in the last 90 daysCommits to the repository in the last 90 days, as GitHub counts them.1
  • Contributors, all time Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.1, a small team
  • Releases ReleasesThe number of GitHub releases, and how many days ago the latest one was published.0
  • Issues in the last 30 days Issues in the last 30 daysIssues opened and issues closed in the last 30 days, as GitHub search counts them.8 opened, 0 closed
  • Pull requests merged in the last 30 days Pull requests merged in the last 30 daysPull requests merged in the last 30 days, as GitHub search counts them.0

Maintenance

  • Stale open issues Stale open issuesOpen issues with no update in the last 90 days, as GitHub search counts them.0
  • Open pull requests Open pull requestsPull requests open now, as GitHub search counts them.3

Hygiene

  • Automated tests or builds (CI) Automated tests or builds (CI)Whether the repository has at least one GitHub Actions workflow file in .github/workflows.No
  • A tests folder A tests folderWhether the repository has a top-level folder named tests, test, __tests__ or spec.No
  • A license A licenseWhether GitHub detects a license file in the repository.Yes
  • Contributing guide Contributing guideWhether the repository has a contributing guide.No
  • Code of conduct Code of conductWhether GitHub finds a code of conduct in the repository.No
  • CODEOWNERS file CODEOWNERS fileWhether the repository has a CODEOWNERS file, which names who reviews changes to which files.No
  • A Dockerfile A DockerfileWhether the repository has a Dockerfile at its top level.No

Security

  • Security policy Security policyWhether the repository has a SECURITY.md or SECURITY.rst file.No
  • Unpatched high or critical advisories Unpatched high or critical advisoriesPublished GitHub security advisories rated high or critical on this repository that list a vulnerable version with no patched version.0

Badge

For maintainers: one measured fact, no verdict. First spotted by Mid or Real at 302 stars on 3 Nov 2026

Markdown

[![Mid or Real](https://midorreal.com/badge/rikiyat-lm-understand-logs.svg)](https://midorreal.com/project/rikiyat-lm-understand-logs)

HTML

<a href="https://midorreal.com/project/rikiyat-lm-understand-logs"><img src="https://midorreal.com/badge/rikiyat-lm-understand-logs.svg" alt="Mid or Real"></a>

Verdict badge: Mid or Real: too early It shows the verdict as this page shows it today.

Markdown

[![Mid or Real: too early](https://midorreal.com/badge/rikiyat-lm-understand-logs.svg?style=verdict)](https://midorreal.com/project/rikiyat-lm-understand-logs)

HTML

<a href="https://midorreal.com/project/rikiyat-lm-understand-logs"><img src="https://midorreal.com/badge/rikiyat-lm-understand-logs.svg?style=verdict" alt="Mid or Real: too early"></a>

Passport

Copy these facts into a post, a README or a page. Cite as "Source: Mid or Real". Full record: JSON.




First tracked 3 Nov 2026 at 302 stars.

Projects blowing up

How we call a verdict

Is this your project? Claim it

Figures by method 1.0