Good deorbit burn.
Landing burn in 53 minutes. nitter.gq/i/broadcasts/2brajgZlO…
😍
Probably the most asked for feature ever, spend limits for Workers and Durable Objects are now generally available on @Cloudflare
No more billing surprises! Super proud of this and how well it works.
Support for the rest of our products on Cloudflare is coming next.
blog.cloudflare.com/spend-ma…
8
Replying to @FinansowyUmysl
pfff to ty nie wiedziałeś że helikopterem sie lata nad biedotą, kolegów zabrałeś? bo nie wiemy co oni na to
80
Dominik Kowalski retweeted
Helping scale @AmpCode on @rivet_dev has been such a pleasure this year!
Getting to see how their team works on Amp and how they use Rivet Actors to build the future of coding is a glimpse at the next decade of engineering will look like
😲
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.…
10
Replying to @PatrykLDev
can't wait! are there any plans for TUI so we can use it with herdr/moshi?
21










