Viewing profile — antirez

Price is not a good meter. Active parameters per token are. Joule would be even better.

Chinese labs are the proof that there is no need of big names, but of the right mindset and agility. It's those last things that Google truly misses, but now they are missing for a…

This is not at the top as it is actively flagged by people that can't psychologically cope with the advances of AI. Hacker News is no longer a web site of an elite.

SSD streaming on an M5 Max 128GB: https://x.com/antirez/status/2082136334160818528 Soon decent speed across two Mac Studios with 512GB of RAM.

So many mathematicians over the years tried hard and failed, but now Anthropic just for some PR magically did it? And this after LLMs obtaining different math wins? What is your lo…

Execution is not the code, but how do you decide to do every part. "Idea does not matter, execution does" always meant: "big generic ideas don't matter, it is how you organize it i…

Because Redis is not "my project", it is a piece of software many relies upon, so I use, for that software, what the community at large agrees to be ok: AI-assisted coding with hum…

Never comment till you read the whole post, since your question is exactly addressed at the end.

I'm against using AI to write text targeting other humans.

Thanks! And sorry for not yet merging many of those. The problem is, I'm dealing with tensor parallelism for the CUDA and Metal-RDMA fork right now, so was not albe to care about P…

Thanks, I believe that as a whole choosing the BSD created a more positive effect, so I'm happy with that. It is just that it is really unfair to read a comment where people use Va…

Sure, it costs less, and AWS is in a dominant position. Users here are playing the side of the bully since they don't care about what is right and wrong with the hyperscalers. "BSD…

Do you understand Redis and ValKey have mostly overlapping code bases? And of that intersection, a big part of the code was written by myself by hand. So no, that's not the case. A…

The flaw is here: > 1. Compute costs collapsed since the advent of Cloud and yet hyperscalers still have fat margins. Cloud opposes switch inertia. To setup a complex system in a d…

In Catania 10 gbit Internet costs 35 euros/month and is available everywhere in the city and even in a big slice of the small towns around Catania. And indeed public incentives pla…

Europeans do a lot of stupid things, but I believe in light of all the scandals we saw in recent times, you can't explain EU behavior and choices without accounting for corruption.…

I love coffee, I take 2 to 3 every day (Italian espresso, so very short, little total caffeine), however for some reason taking the decaffeinated one in the evening interferes with…

DwarfStar work in progress numbers: I see 14 tokens/sec generation, that slopes to 10 t/s with longer 10k or more context size. Consider that the indexed attention requires evaluat…

So to avoid those energy-hungry LLM companies from scraping your website, you force each browser to compute a lot of hashes in a necessarily energy-hungry loop, creating, at the sa…

Why Anthropic can't ask users for passports and provide Fable only to the ones that certify?

They didn't freaked since the order was to still allow 350 million people using it: there is, in such large population, everything, including single persons very against the countr…

Interestingly if we assume 16 concurrent users, prefill drops to 600 t/s and generation to 61 t/s, and this starts to be dangerously near to M5 Max 35 t/s generation and 400 t/s pr…

They try so hard to do a polished presentation that everything is kinda fake and unauthentic. I don't understand how this attitude survived so many years.

Not a single word of this post was written by AI. You are hallucinating.

There is a different way to look at this: that is, actually the Transformer is a minimal complication of what the based model is: in theory the neural network could be just a huge …