1. X
  2. antirez
Log inSign up
antirez
43.5K posts
antirez profile banner
user avatar

antirez

@antirez
Reproducible bugs are candies. I like programming too much for not liking automatic programming.
Sicily, Italy
invece.org
Joined May 2007
797
Following
77.5K
Followers
RepliesRepliesMediaMedia
  • Pinned
    user avatar
    antirez
    @antirez
    Nov 22, 2023
    My second short story release in English is ready: Tales of Illustrious Computer Scientists: Iola Varga, nun and computer scientist. invece.org/iola.html
  • user avatar
    antirez
    @antirez
    12h
    Big deal
    user avatar
    DeepSeek
    @deepseek_ai
    14h
    🧩 DeepSeek Harness v0.1 is now available in Developer Preview! 🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license. 🔹 Powered by the Cordis meta-framework, DeepSeek Harness is an agent harness built around one
  • user avatar
    antirez
    @antirez
    15h
    The draft sorted sets PR. 60% less memory in non trivial use cases, and certain operations are even 70% faster (measured via API + networking!).
    Image
    Reduce large sorted set memory with a packed B+ tree by antirez · Pull Request #15635 · redis/redis
    From github.com
  • user avatar
    antirez
    @antirez
    Aug 11
    Less than 100 years ago a group of Italians worked together to make discoveries that enabled nuclear energy:
    en.wikipedia.org
    Via Panisperna boys - Wikipedia
  • user avatar
    antirez
    @antirez
    Aug 10
    Follow my simple reasoning here. Large sparse LLMs are more powerful then dense one *while* being faster and thus more energy efficient. Dense models are a need that is artificially created by VRAM scarcity. Today they are practically useful, but not for long.

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement