Log inSign up
Joseph Suarez ๐Ÿก
9,594 posts
Image
user avatar
Joseph Suarez ๐Ÿก
@jsuarez
I build sane open-source RL tools. MIT PhD, creator of Neural MMO and founder of PufferAI. DM for business: non-LLM sim engineering, RL R&D, infra & support.
puffer.ai
Joined March 2019
123
Following
30.4K
Followers
  • Pinned
    user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Apr 6
    Releasing PufferLib 4.0: Train agents in seconds
    Image
    00:00
    203K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Oct 16, 2025
    I don't like courses. Most were a waste of time. Yes, even at Stanford. If you're new to ML, take CS231N.
    user avatar
    sankalp
    @dejavucoder
    Oct 15, 2025
    your honor i object, i dont know about harvard but stanford literally releases SOTA courses
    Image
    Image
    249K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Jul 11, 2025
    Article cover image
    Article
    My Advice for Programming and ML
    This article is a prequel to my opinionated reinforcement learning guide. It exists because people have asked me for it repeatedly. Start here if you a) do not know how to program b) don't know ML or...
    559K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Nov 1, 2025
    Image
    Image
    user avatar
    Guillermo Rauch
    Vercel
    @rauchg
    Oct 30, 2025
    The world runs on TypeScript & JavaScript. Our bet is that AI engineering will follow suit. The growth in @aisdk downloads and adoption has been astonishing. When we wrote the Ship AI keynote it was at 3.4M weekly downloads. A couple weeks later, itโ€™s now at 4.1M ๐Ÿ˜ณ
    170K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Oct 12, 2025
    You have to have been in ML for over a decade to really understand how bad this was. From 2015-2018ish, any time anything went wrong in an experiment, at least someone would say "local minimum"
    user avatar
    kache
    @yacineMTB
    Oct 12, 2025
    sent this to my dad this morning. It is really incredible how much you can learn today if you want to learn. There are no barriers except for yourself
    Image
    248K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Oct 19, 2025
    I don't care if Karpathy is down on RL. He, Carmack, Ilya, and Alec Radford could all show up in person to tell me I'm wasting my time and I'd still keep doing it. Because damn it this tech is too cool not to exist.
    301K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Jul 19, 2025
    Article cover image
    Article
    The Tragedy of Reinforcement Learning
    Or: how the genie went back into the bottle for years. This is, at least from my perspective, the true story of what happened to reinforcement learning and why it's only really starting to kick off...
    413K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Jul 11, 2025
    Article cover image
    Article
    An Ultra Opinionated Guide to Reinforcement Learning
    Reinforcement learning is about learning through interaction. Applications include robotics, logistics, gaming, and even control problems in science like nuclear fusion. It's an underexplored niche of...
    357K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Nov 16, 2025
    Welcome to RL. If the pink curve overtakes the green curve, we'll have big news
    Image
    437K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Jul 23, 2024
    Whenever there's an Internet spike, it launches flechettes out of the roof
    56K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Nov 2, 2025
    If you ask me to do this I will 1) not be able to 2) assume you're a moron who tf remembers toy algos from CS101 with 0 application
    149K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Oct 19, 2025
    RL really sucks. It takes 10 hours just to learn breakout. ... a few years ago. It's <30 seconds on 1 GPU now in PufferLib and still dropping. Write faster code.
    Image
    00:00
    268K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Jun 23, 2025
    PufferLib 3.0: We trained reinforcement learning agents on 1 Petabyte / 12,000 years of data with 1 server. Now you can, too! Our latest release includes algorithmic breakthroughs, massively faster training, and 10 new environments. Live demos on our site. Volume on for trailer!
    Image
    00:00
    195K
  • user avatar
    Joseph Suarez ๐Ÿก
    @jsuarez
    Oct 15, 2025
    Accidentally said "you all are status obsessed hollywood wannabees" instead of "you're literally building the future bro" and they kicked me out of SF
    27K

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

TermsยทPrivacyยทCookiesยทAccessibilityยทAds Infoยทยฉ 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
Advertisement
Advertisement