Re:Astra can read and write weights to improve Qwen
by user43928 on Monday November 02, 2026 @03:12PM
(#50343000)
Opus 5.5 also identified Breakout for me when I tested it in the Chat on the website.
Re:Astra can read and write weights to improve Qwen
by mlmonkey on Monday November 02, 2026 @04:12PM
(#50343830)
Can you give some details on what you did?
Re:Astra can read and write weights to improve Qwen
by user43928 on Monday November 02, 2026 @04:27PM
(#50344023)
I asked Opus 5.5 in Claude Code to prepare a reproduction of one of the things in the article.
It created a 130 KB file with the prompt for the task of identifying the game + the weights.
I pasted that into Claude on the web and asked it to perform the task without using tools.
Re:Astra can read and write weights to improve Qwen
by ConteMascetti71 on Monday November 02, 2026 @06:36PM
(#50345778)
i tested with deep seek and generated (you can read all reasoning pattern) the whole model for the breakout game
https://chat.deepseek.com/a/chat/s/9e864beb-698b-4079-94c4-e...
Unless Astra was trained on other networks, how is it able to reason about the weights?
Does this mean that OpenAI has been including networks in its training sets, maybe in an attempt to RSI? I wonder which other networks are able to ingest other networks and reason about their weights?