antirez

43K posts

antirez banner
antirez

antirez

@antirez

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

Sicily, Italy Katılım Mayıs 2007
790 Takip Edilen68.3K Takipçiler
Sabitlenmiş Tweet
antirez
antirez@antirez·
My second short story release in English is ready: Tales of Illustrious Computer Scientists: Iola Varga, nun and computer scientist. invece.org/iola.html
English
14
11
187
225.5K
antirez
antirez@antirez·
@lastknight I wish it was that. Apparently people in order to have more popular X accounts, paste conversations to LLMs saying: "tell me something insightful I could say here". And when they interact a lot like that, X algorithms give them some boost. It's nuts.
English
1
0
7
692
antirez
antirez@antirez·
Recently here on X there is this thing of replying to tweets with a vague remark of what the tweet expressed. I see this for months now. I thought most were bots, but as I investigate, I see that many are legitimate humans that are starting acting as bots. Worrying.
English
81
4
338
30.4K
antirez
antirez@antirez·
@chrisvbuskirk We invented Trumpismp with Berlusconi before there was ever Internet. The idea that Trump is elected because of social network manipulation is something I don't believe even for a second for this reason other than many others.
English
0
0
11
755
Chris Van Buskirk
Chris Van Buskirk@chrisvbuskirk·
@antirez Boy this is embarrassing, but its daily for us now....but hey, Italy done some characters is past as well. 😉
English
1
0
0
750
antirez
antirez@antirez·
AI translated Italy president reply to Trump. Thanks Matteo.
English
16
15
293
41.1K
antirez
antirez@antirez·
@VerrielloMic It is a family of optimizations applied for many years, nothing new.
English
1
0
3
857
antirez
antirez@antirez·
I opened an issue in the Redis repository about the 50% memory savings for sorted sets I talked about a few days ago: github.com/redis/redis/is…
English
6
5
222
18.6K
antirez
antirez@antirez·
@sergey11g Check the DwarfStar documentation about distributed inference please. Two 64GB in a fast thunderbolt link can be fine.
English
0
0
1
127
Sergius Cogitans
Sergius Cogitans@sergey11g·
@antirez If this is fundmentally possible with the existing models that don't fit one machine, the scheduling and coordination is doable. Wdyt? Is this the future of local inference?
English
1
0
0
128
antirez
antirez@antirez·
I'm using the Unsloth 4-bit weights to integrate interence into DwarfStar. If the experiment works well I'll specialize the quants with an optimizer for the best setup. My target is however the 512GB M3 ultra and in distributed inference 4 128GB machines with 3-bit variants if quality holds. Inference quality must be the local inference mantra.
Unsloth AI@UnslothAI

GLM-5.2 can now be run locally!🔥 The 2-bit model retains ~82% accuracy after we shrunk it from 1.51TB to 238GB (-84% size). Run on a 256GB Mac or RAM/VRAM setups. GLM-5.2 is the strongest open model to date. Guide: unsloth.ai/docs/models/gl… GGUF: huggingface.co/unsloth/GLM-5.…

English
24
20
416
39K
antirez
antirez@antirez·
@eddy_mane Those are basically bots on my account, they are just acting as a proxy, an adapter, to let AI write on a humans web site.
English
1
0
21
1.8K
.mane🏴‍☠️
.mane🏴‍☠️@eddy_mane·
@antirez Many of them are just humans who use AI to generate replies to copy and paste here, like they are brainless so they delegate everything to AI.
English
3
0
13
1.9K
antirez
antirez@antirez·
@twid I perfectly know but they have surely many for these kind of stuff and more.
English
2
0
13
3K
Todd Dailey
Todd Dailey@twid·
@antirez The M3 Ultra 512GB is out-of-stock, and doesn't even exist as an orderable SKU now, so really no units to send you.
English
1
0
11
3.2K
antirez
antirez@antirez·
The feeling that Apple is selling 92304294024 m5 max 128GB macbooks thanks to DwarfStar but doesn't give a fuck about sending me an M3 Max with 512GB (that I would buy if possible but it is borderline note possible) is growing on me :D
English
25
17
489
40.6K
antirez
antirez@antirez·
@ivanfioravanti @Apple I know. Btw, would happily buy one myself at the normal price, but not on the corners of eBay at 30k...
English
1
0
6
964
Ivan Fioravanti ᯅ
Ivan Fioravanti ᯅ@ivanfioravanti·
@antirez Don't tell me... I spent a fortune on these two beasts. I bet Apple will help us with M5 Ultra (🙏 @Apple )
English
1
0
3
918
antirez
antirez@antirez·
Appreciate, already have access to two (of friends) but would simplify developments if Apple could ship one and I could have it on my desk. So this needed to be told ;D In AI there are money everywhere but the local AI scene is left alone (of course... it's the contrary of making money).
English
3
0
38
3.9K
antirez
antirez@antirez·
@sergey11g Among two, latency is not terrible. Among four, it starts to be an issue, but it's worse than that: 4 128GB machines, you may 4 times the operating system memory tax, so you have actually ~95GB each machine to stay safe. It's not ideal... and a huge waste.
English
1
0
3
512
Sergius Cogitans
Sergius Cogitans@sergey11g·
@antirez Noob question: is inter-machine latency and throughput a huge speed factor?
English
1
0
0
508
antirez
antirez@antirez·
@Wauplin That's a very good news. Thanks.
English
0
0
8
2.3K
Wauplin
Wauplin@Wauplin·
`hf upload` got a full rewrite! Single-pass hashing, multi commits, resumable uploads. Same CLI, way faster, way cleaner. Available in hf latest release (1.20.0).
Wauplin tweet media
English
4
9
58
16.8K
antirez
antirez@antirez·
@__anshukla__ Appreciate the help about remote access but I already got two machines online thanks to friends. But for the CI testing I need a dedicated locale one and for them it's I guess not hard.
English
1
0
2
2.1K
antirez
antirez@antirez·
@Youssofal_ Typo but impossibile to edit courtesy of X but anyway...
English
1
0
9
2.3K
antirez
antirez@antirez·
Jesus X has the most ridiculous ever "edit" implementation.
English
3
0
49
7.2K
antirez
antirez@antirez·
@experquisite @NVIDIAAIDev The DGX Station would be useless for me since I want to support hardware people can actually buy. At 90k this is an elite thing, the Mac Studios are a much better target.
English
0
0
2
102
experquisite
experquisite@experquisite·
@antirez Yeah there’s a big gap in the market for 512GB+ unified memory machines, between the now-cancelled studios and the $90k DGX Stations. You could probably get @NVIDIAAIDev to give you a DGX Station though?
English
1
0
0
110
antirez
antirez@antirez·
@Vamzzz93 Appreciate but it is even hard to find one, and I believe that Apple could benefit a ton from local inference scene, so would be a good idea for them, that have the ability and spending power, to sustain a bit the devs.
English
0
0
3
145
Vamz
Vamz@Vamzzz93·
@antirez Just out up a crowdfund and we will buy you one
English
1
0
1
126