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

Re:Show HN: Pac-Bench – How well can models one-shot a Pac-M... by shoobiedoo on Tuesday September 29, 2026 @01:10AM (#49888537)

My hope is that this drives a new generation of hyper creative content from those who don't give up. I mean, of course it does pacman well. Pacman and its clones have been done to the death over decades. But what if we ask AI to write finnegan's wake 2?

[ Parent | on HN ]

Re:Show HN: Pac-Bench – How well can models one-shot a Pac-M... by Vakaiser on Tuesday September 29, 2026 @02:25AM (#49889008)

I’m quite optimistic about how AI tooling will raise the floor for creative work.

I personally have been working on a Three.js project with Opus 5 and 5.5 that I never would have continued with had I needed to dive into documentation by hand.

Seeing immediate results is incredibly motivating.

[ Parent | on HN ]

Re:Show HN: Pac-Bench – How well can models one-shot a Pac-M... by 8n4vidtmkvmk on Tuesday September 29, 2026 @02:49AM (#49889173)

I'm finding new things to demotivate me. It's good and quick at doing everything I ask but sometimes as soon as it comes together I realize I didn't really want this or it's just not fun. But maybe iterating quicker and finding that out sooner is still good. I don't know.

[ Parent | on HN ]

Re:Show HN: Pac-Bench – How well can models one-shot a Pac-M... by rico735 on Tuesday September 29, 2026 @04:54PM (#49900375)

I suspect any attempt to market will be where demotivation kicks in. When they entry level is so low, far fewer people are going to bother giving anything a click.

Whilst it is the Astra aesthetic, the expectation of any three.js game will be that it is all surface and no detail, whether someone has put the effort in or not.

[ Parent | on HN ]