‹ BackHN Continuity

Thread

Show HN: Pac-Bench – How well can models one-shot a Pac-Man game?

80 points · 50 comments · thefourthchime

  1. yambam · · focus · HN ↗
    This reminds me of a couple decades ago when some friends and I set ourselves a challenge to, individually, each create as much of a Pac-Man clone as possible in 10 hours. None of us had any experience in games programming or graphics coding. It was great fun and we all learned a lot.

    No-one ended up with a complete clone but I loved how we all ended up focusing on different things, like pixel-perfect graphics versus accuracy in gameplay, and how we all brought our existing skills to the challenge despite not really knowing what we were doing.

    I expect if we had AI models available it would have ruined the pleasure of figuring it out for ourselves. I feel kind of sad for the next generation of developers who won't have that experience.

    1. OJFord · · focus · HN ↗
      I think you figure out different things for yourself; the next generation is going to have 'programming' appeal to them for different reasons. More creatives. More engineers, perhaps, as the practice becomes more about the bigger picture.
      1. HPsquared · · focus · HN ↗
        It'll be more like architecture than engineering, I think. Sketch out the building plan, context (physical and social) and desired usage.
        1. zerr · · focus · HN ↗
          Articulating about architecture (as opposed to engineering (as opposed to programming)) is a part of coping I believe. Yes, LLMs do architectures as well. I think the vibe-coding is the more precise term, also considering that less and less human reviews are being done.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.