antirez

@[email protected]
4 Followers
0 Following
381 Posts
I'm a computer programmer based in Sicily (Italy).

Website: http://invece.org

Blog: http://antirez.com

My sci-fi book (English translation): https://www.ibs.it/wohpe-ebook-inglese-salvatore-sanfilippo/e/9791280845337 or Amazon Kindle

Twitter / X: @antirez

Bluesky: https://bsky.app/profile/antirez.bsky.social
This account is a replica from Hacker News. Its author can't see your replies. If you find this service useful, please consider supporting us via our Patreon.

Officialhttps://
Support this servicehttps://www.patreon.com/birddotmakeup
Instagram@[email protected]
Twitter@[email protected]
Show threadantirezMar 21
Exactly. I was reading all the other comments and wondering why many looked like they were talking of something else.
Show threadantirezMar 20
Basically this is true for most startups in the world BUT Cursor, so here you are kinda inverting the logic of the matter. Cursor is at a size that, if they wanted to use K2.5, they could clearly state that it was K2.5 or get a license to avoid saying it.
Show threadantirezMar 18
In programming, the only rule to follow is that there are no rules: only taste and design efforts. There are too many different conditions and tradeoffs: sometimes what is going to be the bottleneck is actually very clear and one could decide to design with that already in mind, for instance.
Show threadantirezMar 14

So you love interacting with web sites sending requests with curl?
And if you need the price of an AWS service, you love to guess the service name (querying some other endpoint), then ask some tool the price for it, get JSON back, and so forth? Or you are better served by a small .md file you pre-compiled with the services you use the most, and read from it a couple of lines?

> I'd recommend that you take a peek at MCP prompts and resources spec

Don't assume that if somebody does not like something they don't know what it is. MCP makes happy developers that need the illusion of "hooking" things into the agent, but it does not make LLMs happy.

Show threadantirezMar 14
As yourself: what kind of tool I would love to have, to accomplish the work I'm asking the LLM agent to do? Often times, what is practical for humans to use, it is for LLMs. And the reply is almost never the kind of things MCP exports.
Show threadantirezMar 12

Of what is happening with AI the most bizarre thing, for me, is how these tools are 20$ away from being tested. Yet, to form an idea about actual real world usefulness many folks seek some kind of indirect proxy.

This is combined with the incredible general feeling that automatic programming can be evaluated as producing the same results regardless of the user using it. Something true only with benchmarks, basically. Benchmarks are useful metrics because even if weak we need some guidance, but the current real world dynamic is that AI will completely change what it is capable of doing based on the programmer using it.

Maybe never in the history of programming there was a time where diverse programming skills were as important as today (but this may change as AI evolves).

antirezMar 9

GNU, and the AI Reimplementations

https://antirez.com/news/162

GNU and the AI reimplementations - <antirez>

Show threadantirezMar 9

> They completely miss the fact that a lot of his blog post is not actually just about legal but also about ethical matters.

Honestly I was confused about the summarization of my blog post into just a legal matter as well. I hope my blog post will be able to flash at least a short time in the HN front page so that the actual arguments it contain will get a bit more exposure.

Show threadantirezMar 8
There was a recent fix by ollama and I used it.
Show threadantirezMar 8
I inspected manually and indeed the 27B is doing worse, but I believe it could be due to the exact GGUF in the ollama repository and/or with the need of adjusting the parameters. I'll try more stuff.