唐突魚酥 retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
這陣子大量嘗試用 Local LLM 及 Pi 來投入開發,染上看 thinking 內容的習慣,有一次看到他過度思考及跳針道歉正覺得怪怪又忽然看到 to die,嚇到馬上中止。
詳細的 session 內容及為什麼會發生這種事的調查: tech.imnotyourson.com/llm-gl…
這陣子整合 Local LLM 過程的淺見:tech.imnotyourson.com/local-…
4
304
kukuroo.cc
條件:
1. iOS 跟 macOS 的 Safari 限定(但,到底誰會用 macOS 來收推播?)
2. 要收推播的網頁得加到桌面
3. 有 Cloudflare 帳號,推播跟輕量 serverless function 簡直絕配
4
223





