Building things / previously eng @malbeclabs_xyz @DigitalOcean @Shopify
Joined April 2009
- Tweets2.2K
- Following1.3K
- Followers1.1K
- Likes2.7K
Steven Normore 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.…
I love the “Joys of the Craft” passage from The Mythical Man-Month.
The joy of making things. Making things people use. Building complex systems and watching them work. Always learning. Turning something in your head into something real.
Almost none of it is about writing code.
Steven Normore retweeted
It's pencils down, people. Writing code by hand is no longer an economically viable skill for most programmers at most companies. But the future of making software has never been brighter. Don't you dare black pill this beautiful moment! youtu.be/vDjW_dRyKXY?si=6Fsf…
Steven Normore retweeted
Be like water
DoubleZero Edge now carries data from @HyperliquidX.
Streams are entirely uncapped, every market, every order, the full L4 book including HIP-3.
Introducing the first-class path to Hyperliquid’s order book, and the fastest commercially available feed on the market.
Cloudflare is really good these days.
wow it's been a good run but I'm finally a *paying* @Cloudflare customer
touché, @eastdakota, you built the best free tier of any technology company in history 🙇🏻♂️
1
255
Low-risk way to try Muse if you’re not ready to give it access to your email: give it your Netflix account.
4
183
Still the same game, but with more leverage and bigger ambitions.
before ai you would
- write some code
- it works, ship it
- few months later you'd realize it was bad
- you'd refactor it
- repeat
not sure much has changed. you can produce a lot of code now but you can also refactor a lot of code
1
177
Understanding a system by reading every line of code isn’t scalable, and never was.
It might feel chaotic or untethered, but getting comfortable with that was always part of the job.
Delegate coding. Never delegate understanding.
If code was previously your source of truth for managing understanding, then you need a new source of truth artifact. If code-centric workflows were how you developed that understanding, then you need new workflows.
1
179
Steven Normore retweeted
yet another fun jev experiment... i took a particle fluid simulation, pulled out the part that does the physics (what happens when two particles collide) and let jev handle it at the micro scale. 6.3 million decisions for this one, and the only laws it's told to follow are conservation of momentum and energy, and it never once broke them.
