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]

GNU, and the AI Reimplementations

https://antirez.com/news/162

GNU and the AI reimplementations - <antirez>

Writing a "clear room" Z80 and Spectrum emulator with Claude Code

https://antirez.com/news/160

Implementing a clear room Z80 / ZX Spectrum emulator with Claude Code - <antirez>

Voxtral.c Voxtral Realtime 4B model inference as a C library

https://github.com/antirez/voxtral.c

GitHub - antirez/voxtral.c: Pure C inference of Mistral Voxtral Realtime 4B speech to text model

Pure C inference of Mistral Voxtral Realtime 4B speech to text model - antirez/voxtral.c

GitHub

Tgterm – Control Claude Code from Telegram on macOS (< 1000 lines of C code)

https://github.com/antirez/tgterm

GitHub - antirez/tgterm: Control your MacOS terminals via Telegram, for fun coding agents interaction and profit

Control your MacOS terminals via Telegram, for fun coding agents interaction and profit - antirez/tgterm

GitHub

Updates:

1. Now it is much faster, and the Python benchmarks were re-done correctly (the benchmark didn't account for model loading, and did warm-up before starting the actual inference, while the C code was tested exactly in the reverse way).

2. Now there is --mmap support to run on Linux with blas target with 16GB of RAM. Inference is viable on my old-ish Dell Latitude i5.

3. Seed now part of the PNG metadata.

4. Many other improvements, check the README.

Something that may be interesting for the reader of this thread: this project was possible only once I started to tell Opus that it needed to take a file with all the implementation notes, and also accumulating all the things we discovered during the development process. And also, the file had clear instructions to be taken updated, and to be processed ASAP after context compaction. This kinda enabled Opus to do such a big coding task in a reasonable amount of time without loosing track. Check the file IMPLEMENTATION_NOTES.md in the GitHub repo for more info.

Flux 2 Klein pure C inference

https://github.com/antirez/flux2.c

GitHub - antirez/flux2.c: Flux 2 image generation model pure C inference

Flux 2 image generation model pure C inference. Contribute to antirez/flux2.c development by creating an account on GitHub.

GitHub
Dev Reveals Secrets Behind Stunning New "3D" Platformer For The ZX Spectrum

'Cubix' launched earlier this month as part of YRGB 2025

Time Extension

Coding with LLMs in the summer of 2025 (an update)

https://antirez.com/news/154

Coding with LLMs in the summer of 2025 (an update) - <antirez>

HNSW as abstract data structure: video intro to Redis vector sets

https://www.youtube.com/watch?v=kVApsFUeuEA

Introduction to vector sets: main commands and ideas

YouTube