antirez

Credits where credits is due: kudos to @OpenAI in the context of the new scientific releases, for putting the scientists that worked in a given field for a long time at the center of the process of understanding and announcing the new discoveries.

I believe StarTrek Voyager to be a masterpiece and often I think that, to make it happen, an incredible level of trust in a crazy project was needed (for StarTrek in general): people writing scripts and acting like all that crazy stuff mattered (they matter). It's not obvious.

Work in progress, Iris.c in a DGX Spark running Flux 3 Klein. I know prompts for Flux 3 should be post-processed for better results, but it kind works even with humans written descriptions, more or less. New Iris release in the next days.

Even if the DGX Spark is SM121 and not SM100, yet maybe we can get something good for DwarfStar kernels from DeepSeek Infer. Let's try.

AI: there is great chaos under heaven; the situation is excellent.

DeepSeek infer is the cloud version of DwarfStar, conceptually. Vertical inference engine for one model and specific hardware. Good move. And well, a lesson to the ones that criticized this approach as well.

For the ZX Spectrum lovers, there was enough documentation around to also simulate the whole Spectrum PCB with very precise ULA emulation (cross checked with the actual gates implementing it). On my GitHub as usually.

DwarfStar GGUF for DeepSeek v4.1 Flash new checkpoint is now available. It is an improvement even only for the better token efficiency. Upgrading is a must.

The Commodore 64 hardware simulator is now online: github.com/antirez/c64-...

Soon on GitHub #c64 #retrocomputing

What Tao should do right now instead of slide decks? Use AI and his skills to make the AI results understandable. Never bet against technology.

DeepSeek v4 .1 score in DeepSWE 1.1 is higher than Mistral Large 4. The same for other benchmarks as well. Happy to see more europeans LLMs but unhappy when the comparisons are not the ones obvious.

*** STOP DEATH PENALTY IN THE USA ***

Wrong advice for junior developer: look at the AI generated code, since you need to mature as a programmer. Right advice: save time with AI coding and write by hand "get-better" programs: interpreters, games, ray tracers, ...

I claim that if you are a normal person that like me don't have "fuck you money", so unable to spend large sums of money randomly, you should do all your programming work with two max accounts (OpenAI / Anthropic for instance) in the worst case, and never buy tokens via API.

ZX Spectrum 48k Another World demo released: github.com/antirez/anot...

Good programmers state they use models like GPT 6 Astra without obtaining good results: it makes me feel I live in a parallel universe. But the explanation is not that hard: good programming in the past and now requires a different skill set, even if there is some overlap.

I'm worried to see people that think the right move is to question AI companies and narratives around AI regardless of logic and the actual significance of events we are living. They act just as an inverted flock, but still a flock. Sometimes it's fear of friends judgement.

Trivially known for years but since apparently every year everything about machine learning is new to newcomers...

Jev may have its (narrow) use cases but the hype you see around is the perfect representation of the fact the greatest part of the AI bubble don't know what is important and what is not. Jev is a minor thing happening on AI compared to all the rest, yet the hype exploded.

It looks simple to use

Started yesterday as a joke without any code reference if not papers. Because of fillets already better than TinkerCAD for certain stuff. There is something odd, here: in theory open source should explode right now, but we don't have, apparently, folks motivated to do wonders.

At this point DwarfStar contains many fast fused kernels for important model families: feel free to steal everything you want from there according to the MIT license, in order to improve your own implementation.

Witch hunting level: some guy uses AI to reverse engineer an M4 GPU driver for Linux and part of the community that should be for the open source, for the hacking, for the liberation and freedom is against him.

The irreconcilable misunderstanding about AI is that for some of us is the way to remove suffering, inequality, limits from the human race. For others, a tool: and, right now, the capabilities are at tool level, giving the illusion that the tool is the point.

It drive me nuts that now people use AI to write tweets. If you think that this way you will get more popular and so forth, think twice. Write something authentic. AI is great but it is easy to misuse. Your tweets must be your more cared thoughts.

With the last commit into DwarfStar now you can use DeepSeek v4.1 Flash in a single DGX Spark as well, with SSD streaming. Around 9 t/s generation. It works also dual-spark RDMA at ~22 t/s.

Conspiracy theories are, very often, illogical. If AI companies were worried by open weight models (they probably are btw) the logical response would be to *not* slow down the development of frontier AI, to try locking the advantage. Stop with nonsense.

DeepSeek v4.1 Flash support is now pushed on DwarfStar "main" branch on GitHub, and this is a YouTube video (in English language) where I test both the SSD streamed and the dual MacBook m5 max 128GB setup during a coding session: www.youtube.com/watch?v=ogs8...

About Anthropic banning minors from Claude.

DwarfStar running DeepSeek v4.1 Flash on a 128GB M5 Max at steady 15 t/s. I didn't expect with SSD streaming it could be so fast. Recent SSD streaming changes to retain the right experts surely helped, but also maybe DS4.1 uses the same experts more. Will push online when ready QA > ASAP.