{"name":"lm_understand-logs","repo":"RikiyaT/lm_understand-logs","url":"https://midorreal.com/project/rikiyat-lm-understand-logs","repository":"https://github.com/RikiyaT/lm_understand-logs","description":"Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'","facts":{"language":{"value":"Python","source":"https://github.com/RikiyaT/lm_understand-logs","checked":"21 Nov 2026"},"releases":{"value":"0","source":"https://github.com/RikiyaT/lm_understand-logs/releases","checked":"19 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/RikiyaT/lm_understand-logs/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/RikiyaT/lm_understand-logs","checked":"21 Nov 2026"}},"stars":1284.0,"writeup":{"what_it_is":"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.","audience":"Readers of the blog post who want to check or rebuild its experiments","claims":[{"kind":"broad","claim":"Logs of every experiment in the blog post are included","excerpt":"The complete logs of every experiment in the blog post","status":"too_broad"},{"kind":"specific","claim":"All 1,125 turns in this release are tool-free","excerpt":"All 1,125 turns in this release are tool-free.","status":"not_checked"},{"kind":"specific","claim":"Code runs in a sandbox using bubblewrap with no network access","excerpt":"bubblewrap, no network, a working folder kept between runs, and a time limit per run.","status":"not_checked"},{"kind":"specific","claim":"The repository covers eight experiments, listed in a table","excerpt":"| [`exp1_which_game/`](exp1_which_game) | Experiment 1: which game was this network trained on? |","status":"not_checked"},{"kind":"specific","claim":"Logs, data and networks are licensed under CC BY 4.0","excerpt":"| Logs, data and networks | CC BY 4.0 |","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-04"},"why_now":null,"owner_supplied":null,"score":{"verdict":"too_early","hype":92,"reality":7,"gap":84,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":{"estimate":true,"lean":"too_close","gap_low":null,"gap_high":null,"rule":"early-2.0"},"changes":[{"date":"2026-10-29T04:17:30+00:00","text":"Repository created","source":"https://github.com/RikiyaT/lm_understand-logs"}],"cite":"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'\".","attribution":"Data from Mid or Real, https://midorreal.com/project/rikiyat-lm-understand-logs, checked 22 November 2026. Attribution with a link is required.","still_real":null}