Back to News
Advertisement
Advertisement

⚡ Community Insights

Discussion Sentiment

83% Positive

Analyzed from 463 words in the discussion.

Trending Topics

#pac#man#models#pretty#programming#better#seems#prompt#ghost#astra

Discussion (20 Comments)Read Original on HackerNews

strataspace•about 6 hours ago
I tried this with DOOM. Fable 5 did a pretty shit job. Astra made pretty crazy animated sprites and was pretty good considering.

The fact that these are at all playable and 100x my programming skill level is pretty depressing from a certain pov. The ThreeJS dude posted ab how demotivated he was to continue his work, and while I was never a dev that did much with webgl, I commiserate.

acomjean•about 3 hours ago
I wonder if we need better programming abstractions/ languages that can make programming easier for people.

It seems like a lot of the programming is cookie cutter type stuff (where these ai programs shine) and should be easier.

They can be amazing, but promoting “make a pac man game” seems like an exercise in which model has the best training code that was Pac-Man.

jmathai•about 2 hours ago
This prompt is a good way to test how well models fill in missing context because it's so nondescript. They're definitely improving.

Remember when people considered you a genius for prompting with "You are a skilled writer....".

wredcoll•about 2 hours ago
That moment in time was physically painful.
continuational•about 2 hours ago
thefourthchime•about 2 hours ago
I need to add that one! It's the first one I've seen to have almost a drunk Pac-Man. It lags a little bit.
_matthew_•about 2 hours ago
I don't think it makes sense to have the prompt be that short. This is basically a bench.ark of how models interpret an overly vague prompt. It should at least be "Create a pacman clone in a single html page. Make it faithful to the original" if that's what we're scoring it on.
dang•about 3 hours ago
hoistway•about 2 hours ago
Always assumed Pac-Man was an easy solve for modern AI. Guess those ghost patterns are trickier than they look for one-shot learning.
thefourthchime•about 1 hour ago
The game mechanics are shockingly hard for them to get right. You also reveal some of their personality traits. The GPT‑6 and Astra models tend to include a lot of cringe copy as well as their own personal graphics style.
gedy•about 2 hours ago
I did a variant of Pac Man using Claude and pointed it at a thorough blog post about the patterns and that greatly helped.
nedo_var•about 2 hours ago
Curious if models grasp the ghost patterns or just react. Pac-Man's more complex than it seems for one-shot learning.
Stitch4223•about 1 hour ago
Someday we’re gonna miss the times where models create jank.

These results get better and better, but the half-baked pac mans games and pelicans are just funny.

You cannot prompt that level of brokenness. Same for those slop-posters you see everywhere.

blindflag•about 2 hours ago
I'm curious; can you explain why you picked Pac-Man, in particular?
thefourthchime•about 2 hours ago
It was something I randomly tested about a year ago, and no models handled it well, so whenever a new model came out, I tried it.

It has the advantage of taking good screenshots and letting me know if it’s decent within five seconds of playing.

Computer0•about 8 hours ago
Opus 5-5 seemed like a perfect clone, with others displaying flaws in an initial look. Astra notably created a bunch of surrounding ugly crap to look at.
vunderba•about 8 hours ago
I was just coming here to say this. I looked at all of them, and Opus 5.5 at high effort seems significantly better than every other clone.

Buffered controls, different pathfinding AI for each ghost, level transitions, etc.

Gpt-5.6 sol high technically completed the assignment as well, but the gaps within the pipes used to construct the maze, the lack of pause when eating a ghost, etc made it feel far less polished.