@bit_wreck
Account based inCanada
About this account
- Account based in
- Canada
- Connected via
- Canada App Store
Account-level information from X, not a live location or the device used for a specific post.
Yeet.
Joined August 2014
- Tweets13K
- Following5.8K
- Followers386
- Likes37.1K
Fânaț retweeted
Software should be fun. It should make you feel something, positive hopefully. Utilitarian software is the worst. The human experience is why life is worth living (even for something as teeny tiny as a terminal).
Fânaț retweeted
> wakes up
> there are 5 open issues
"wow someone is actually using Bend 🥳"
> spends the Saturday fixing them
> done! now I can play some League
> there are 20 open issues
😐
Fânaț retweeted
Bend 2 is here!
It is a new programming language that blocks AI mistakes via *proof checking* - the same technique big AI labs used to solve open math problems, like Navier-Stokes.
It is also very fast, and runs on GPUs.
Watch the video. Link in the comments.
RELEASE DAY
After almost 10 years of hard work, tireless research, and a dive deep into the kernels of computer science, I finally realized a dream: running a high-level language on GPUs. And I'm giving it to the world!
Bend compiles modern programming features, including:
- Lambdas with full closure support
- Unrestricted recursion and loops
- Fast object allocations of all kinds
- Folds, ADTs, continuations and much more
To HVM2, a new runtime capable of spreading that workload across 1000's of cores, in a thread-safe, low-overhead fashion. As a result, we finally have a true high-level language that runs natively on GPUs!
Here's a quick demo:
Fânaț retweeted
love jev, but upset it
- isn't open source?
- it lack vision capability?
We fixed all of that, introducing SimpleJev.ai
A fully open source library which takes any HF model and Jev-ify it, with an API endpoint
Now on github, and live in production at @FeatherlessAI
Fânaț retweeted
Kev-0.5B: A tiny open source Jev-like decision model with a TypeSafe-compatible API based on Qwen2.5-0.5B that you can train and run on a MacBook Pro.
Model card and weights are available on GitHub
github.com/jaredpalmer/kev
Fânaț retweeted
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run!
Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮
Ask your claude to install it and be amazed
Use this prompt
```
Install, and configure :
github.com/tamaratran/fast-j…
```
found the perfect use case for @typesafeai Jev:
instant compaction
in 2026, why is compaction still a summarization prompt?
Jev can make it instant by scoring every tool call and dropping what’s irrelevant
Fânaț retweeted
All the grifters are completely wrong about Jev’s architecture so I decided I’d release an open-weight version. BUT training takes time, so while we all wait I decided I’d drop the sauce.
archerhume.com/posts/jevs-ar…
Fânaț retweeted
Astra built this from scratch on Bend2 and tbh I'm kinda speechless?
for a context, Bend2 has no game engine, no 2d graphics, let alone 3d, not even FONTS. it is basically just a fast Python
it wrote the ENTIRE ENGINE overnight and somehow it kicks ass at 120 FPS
I trained a small model to do syntax highlighting in the browser with GPU.
Meet gpu-lexer from Vercel Labs: Small (27.5KB), fast (runs on WebGPU), and language-agnostic (model guesses the syntax).
gpu-lexer.vercel.app
It is experimental and built for learning!
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
Fânaț retweeted
Announcing a solution to the Navier-Stokes problem, one of the seven Millenium Prize problem.
Represents a major milestone for both AI and mathematics, as well as pointing to an upcoming renaissance in scientific discovery.
Hoping that the knowledge created by this model can help the community better understand non-linear PDEs, which are used to model much of the physical world.
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
Fânaț retweeted
hey Astra, how fast are you really at using a computer?
Readers added context they thought people might want to know
The video shows Astra executing a pre-planned batched sequence of mouse clicks, keyboard presses and timed waits, not live real-time high-speed control. The poster clarified hybrid inputs and advance planning in replies.
x.com/victornunez/st…
x.com/victornunez/st…
x.com/victornunez/st…
openai.com/index/gpt-6-as…
openai.com/index/computer…
Fânaț retweeted
first, sorry for the messy rollout.
second, when we screw up, we try to make it right.
third, we should be able to begin broad rollout to API customers and chatgpt subscribers in the near future. as usual we will start with pro subscribers.
Fânaț retweeted
Beware people obsessed with outcomes instead of building outcome machines. Its worse than ever with AI, but these people existed before. Short term results above all else, etc. Don't fall into the trap. Invest in building strong fundamentals, invisible supports, and outcomes flow like water. An outcome machine.
Fânaț retweeted
the language isn't 100% perfect yet. the Lean formalization drifted from the core a bit as I made some changes on how the data-kinded types work, so I'm not 100% (although very close!) confident about the consistency of the core, but that should settle in a month or two. I also removed some overkill features like fibers, GUI apps and compile-time parameters, so these will be for a V2.1. I'm also not 100% happy about the state of the compiler and I predict there will be a few bugs after launch, and that it might be still a little bit overfit on the benches, but these will be patched and generalized quickly after launch - user input will be very helpful. my main concerns are people not understanding what it is for and/or some bug giving them a bad experience. but things are great and if I wait for absolute perfection I'll never launch, so, this is it. Lean has consistency bugs after a decade of development, it won't be the end of the world if we have a few in the very first weeks I guess. bend2 is up to 100x faster than bend1, it is C-class speed on single core, CUDA-class on GPUs, it checks fast, it has proofs. it is a nice project and I hope people like it and find good uses to it