this might be possible without T3 code and @jullerino @theo and @maria_rcks's work however.. building Rook which has one job to delegate and control both of my machines has been an absolute pleasure and I'm doing a lot more a lot faster
193
look how weird these comments are.. do people really think I genuinely need to ask the AI whether to kill a mob or not ? it's just a demo of it responding. The addon helper can read tons of data. People are telling me to kill myself in the comments ?
Pushed an update to Airtype for Omarchy - Speech to text pasting works properly inside of WoW forever now automatically just works when the client is active and also works to easily paste into the T3 Code Wow addon made by @ryanrhughes
topmass retweeted
We're giving away a Hogwarts Legacy custom wrapped NVIDIA GeForce RTX 5090 to celebrate its official release with DLSS 5 🪄
To enter:
🟢 Share this post
🟢 Comment #RTXON
Terms and Conditions: nvidia.com/en-us/geforce/con…
Both used Pi, medium reasoning and ~200k context, with compaction and no overall task budget. Qwopus ran Q4_K_M on llama.cpp; Flash-Next ran IQ2_XS on Strata. This model is really nice to use huggingface.co/Jackrong/Qwop…
124
probably fine.
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.…
180








