Reproducible bugs are candies. I like programming too much for not liking automatic programming.

Sicily, Italy
My second short story release in English is ready: Tales of Illustrious Computer Scientists: Iola Varga, nun and computer scientist. invece.org/iola.html
19
13
242
342,901
So it was not impossible... just super hard. This is the 48k Spectrum...
19
10
195
12,768
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.
11
3
123
12,121
Advices for young programmers.
Replying to @GergelyOrosz
Accept the present and the future. Embrace it. Have an evidence based career where you try doing meaningful things. Create open source software that does not exist currently since in the past it required teams of people and there were not the economic incentives but now with AI it is possible for individuals to do it.
25
45
559
52,697
Trivially known for years but since apparently every year everything about machine learning is new to newcomers...
34
33
1,242
105,383
I understand it was not clear to everybody I'm talking about zero shot classifiers created out of LLMs with a single (or few) token emitted. Not of general LLMs usage.
1
1
26
5,561
When people talk about AI companies money flow they miss two fundamental things: 1. It is a winner takes all business. With ASI you take pharma, chips, ... 2. In the long term the idea we have of money will disappear.
48
16
352
27,734
Great new stuff from @redis is here: Redis Radar - understand and manage deployments across OSS and all Redis flavors Search on Flex - extends search to large-scale workloads with indexes stored on SSD And much more! redis.io/blog/redis-introduc…
2
1
10
3,368
DeepSeek V4.1 Flash on Strix Halo. I spent the last week adding support to DwarfStar (@antirez ) and testing two ways to run it: SSD streaming on one 128 GB machine, or distributing the model across two nodes over TCP or RoCE. piped.video/1DaMkTuiCEQ
5
14
104
38,596
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.
155
76
1,346
141,466
antirez retweeted
Earlier this summer, I bought a 128 GB Framework Desktop just so I would have access to a large continuous block of unified memory to run frontier-adjacent models at home. I've been really inspired by @antirez's DS4 project which aggressively targets specific model+hardware combos. I recently became aware of @ilintar's project doing this specifically for Strix Halo and I'm really excited about it.
3
3
27
4,403
Please folks stop. AI is great if you use it for the right stuff. But each time you use it to interact with other people, there is a problem. Write less, even just a few words. But your words.
I'm so suck of LLM generated replies on Twitter. I stopped replying almost entirely to my replies on my own Tweets because I expect all of them to just be LLM slop. Why are y'all doing this?
48
49
536
31,418
It looks simple to use
11
135
19,429
Current status (happening often for two days, with Astra)
8
93
14,075
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.
34
8
263
22,427
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.
17
21
406
18,585
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.
53
58
1,838
83,646
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.
17
23
244
17,294
Qwen3.8 Flash Next is now supported in DwarfStar, covering 64GB Mac systems very well and with very fast inference of 50~70 t/s and > 1400 t/s prefill. For now this is Metal only. Thanks to @ivanfioravanti for all the cool work in the PR. N-grams on SSD like for DS4.1F.
59
49
861
59,652
Not sure if this makes sense on the DGX Spark. You have 128GB there, however the extra speed could be very tempting for the Spark users, as well as having a lot of RAM free for other stuff. For ROCm it makes sense as many folks have a Framework Desktop with 64GB.
6
1
41
8,336
Please when listening to people that have the absolute truth at disposal, make sure to check the track record in the latest few years.
Replying to @PessimistsArc
Right. Dario was already claiming that GPT2 was too dangerous to open source back in 2019. I made fun of them then. Everyone should make fun of them now.
18
13
432
54,963