Byte 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.…
Byte retweeted
Discord now supports full ANSI colors!
I updated my colored text website to let you use them, as well as create rainbows and gradients and stuff.
Byte retweeted
We’re rolling out monthly Claude Platform API credits for Max and Team plans:
Max 5x: $100
Max 20x: $200
Team: up to $500, pooled
Works on any model, including Haiku 5.5, in your code or third-party harnesses.
How it works and full terms: support.claude.com/en/articl…
Byte retweeted
You can now mod Claude Code:
- Change how it behaves
- Customize the UI
- Swap in your own features
Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app.
A few examples:
Byte retweeted
Someone 'accused' me of vibe coding the LFRR simulator.
I've been coding since 1982, I've hand assembled machine code, injected fixes into running processes, worked on software that's made it to Mars and worked as a software developer for decades.
OF COURSE I USED AI CODE TOOLS
Byte retweeted
Skate 3 has been 100% recompiled for PC.
It's reached it's 2.0 update which introduces a fully native renderer enabling 2x+ the FPS at 1/4 the GPU power, and Apple Silicon went from 25 to 250 FPS at 4K.
Originally starting with rexglue, progression has advanced far enough to fully abandon its reliance on emulation via xenia for GPU rendering.
This is proof of what's possible, there is plenty to be excited for! Go try it out!!
Byte retweeted
Unmodified macOS 13 at 60+ fps, metal2vulkan translated (world's first! byte-exact Metal 4-capable Vulkan Translator), running on a standard linux/vulkan host. No GPU passthrough.
I wrote zero lines of code. Only directed/orchestrated.
We heard you. And we agree.
In light of recent developments in physical media, GitHub is proud to announce that you can now obtain your public repo on CD-ROM.
Keep it. Lend it to friends. Pass it on to your children.
Your code is physically yours, forever. Until you lose it, let's be real.
Order yours today.
gh.io/cd












