Recent submissions

Comment · 3 years ago
I just started using HTMX in new projects and really like it.

The LivewView/Hotwire/LiveWire way of building applications make a really great tradeoff—the ease of building websites with the speed and power of webapp UX.

I wanted something simple to use with Express and it's been very productive.

There's a few things to get used to, but overall like it and plan to keep using it in my projects.

Comment · 3 years ago
Thanks for the support HN! I've burned through almost all of my GPT 3.5/4 credits for the month, so the site might stop working soon.

I've requested an increase, and am looking into other options to keep things functioning.

Comment · 3 years ago
your approach is very cool!
Comment · 3 years ago
sorry about that, the primary issue is the context length gets too long and ChatGPT starts throwing errors

it'd be interesting to create embeddings for the game and try to create longer games that way, though it might hallucinate more frequently.

gpt-4-32k should also be a big help to creating longer games

Comment · 3 years ago
i've experimented with this a little and wrote about the tradeoffs here https://themaximalist.com/infinityarcade/

it's currently pretty difficult to get the models to output sane game state, it should be possible soon though

in the meantime i'm calling this YOLO CODE!

Comment · 3 years ago
thanks! i think the content might be too long, i can look into adding a summarizer first which should help
Comment · 3 years ago
Comment · 3 years ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton