Log inSign up
Matt
3,164 posts
Matt profile banner
@tantaman

Matt

@tantaman
tantaman.com
github.com/tantaman
Joined March 2011
699
Following
1,635
Followers
RepliesRepliesRepostsRepostsMediaMediaArticlesArticles

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.
  • @tantaman
    Matt
    @tantaman
    Sep 3
    Trying out Buck2. I think it makes sense given I have many worktrees (5-10) with agents active in them. Build times actually end up becoming a bottleneck. IIUC, Buck2 will let them all share a build cache.
    1
  • @tantaman
    Matt
    @tantaman
    Sep 3
    🤔
    @whusterj
    William Huster
    @whusterj
    Feb 28
    I am developing a formal theorem I call the Verification Complexity Barrier. In a nutshell, if a program has some components `n` that have connectivity factor of `k > 0` , then verification complexity increases superlinearly for each new component. Therefore the time required
    Image
  • @tantaman
    Matt
    @tantaman
    Aug 29
    I find myself immediately skipping any content that looks remotely AI generated these days. AI images? AI color choices (all those identical Claude demos)? AI video? I didn't expect this turn.
    4
  • @tantaman
    Matt
    @tantaman
    Aug 28
    This really drives home how difficult product design is. How many competitors will die. Why central planning an economy fails so drastically.
    @randallmbriggs
    Randall Briggs
    @randallmbriggs
    Aug 28
    What an excellent way to use AI! We forget that before Henry Ford brought the Model T to market in 1908 well over 500 car companies had sprung up in America alone, making somewhere in the range of 2000 to 3000 distinct models of vehicles. It was the Wild West days of the
    Image
    00:00
  • @tantaman
    Matt
    @tantaman
    Aug 28
    Part of me wonders if this a psy-op to get a ban on open models... There's a little bit of tin foil hat in all of us.
    @OpenAI
    OpenAI
    @OpenAI
    Aug 26
    We have conducted a thorough investigation into the Hugging Face incident. We are releasing a technical report and accompanying blog post that reconstruct the agents’ activity, explain why existing safeguards failed, and detail how we’re preventing recurrence.
    1
Advertisement
Advertisement