 |
| LLMs are not superhuman at reading and writing neural network weights (seangoedecke.com) | ||
| recommended by 2 users | 2026 | 117 points by agrm | llm internals | original thread | | ||
| 2 users recommended this thread. What they said: |
| pera Nov 3, 2026 | on: Astra can read and write weights to improve Qwen | context |
|
phoghed Nov 3, 2026 | on: The 'Astra can read and write weights to improve Qwen' post… | context
Wasn’t all that obvious to anyone who read the original post when they got to the section that explicitly explained what the author of this post is now summarizing? Sure if you only read the title and brief at the top you’d walk away without the full picture though. This is a better response imo: https://news.ycombinator.com/item?id=50344861 |
| Also recommended by people who recommended this: | ||
| 1. | My YC app: Dropbox - Throw away your USB drive (getdropbox.com) | |
| recommended by 162 users | 2007 | 104 points by dhouston | original thread | | ||
I think this other submission from yesterday that visualised the examples was quite helpful:
https://news.ycombinator.com/item?id=50344861