41–50 of 1001 posts
https://github.com/libriscv/godot-sandbox
I originally started on it just to get into Godot.
CV pipeline to get some additional realtime stats for an annual Mario Kart 8 LAN tournament my friends and I run, hoping to be able to get real time race position tracking and other stats like boost/drift %, per-player item distributions, average time to 10 coins, and whatever else we can think of (and make work)
Neat. I’d love something that could watch my wife and I play and confirm I really do get hit by more blue shells than her
it's incomplete but https://github.com/fragmede/pasteboard-image
I'm in the middle of rewriting it in rust so it's easier to install.
The unique angle here is that each article includes a hand-written summary explaining why the article was meaningful to the curator. This gives you a quick window into the piece without being overwhelming.
Since this is a free website mostly to be shared with friends and family, I implemented user login via "phone number" to save and submit articles, but without a one-time token. So it's "password-less" for now; a trust-based system.
It's basically 'done' - but I'm not sure that I want to share it publicly for the aforementioned reasons. I've been using it on my subway rides to read more interesting stuff. So far so good.
screenshot - https://i.imgur.com/8kIrgBt.png
The App is mostly being used for generating NSFW images though (which is ok).
I'm getting LLMs to modify your source code by writing code that modifies the Abstract Syntax Tree of your code rather than the code itself. I wrote a simple blog post to explain it: https://codeplusequalsai.com/static/blog/prompting_llms_to_m... My initial goal is to let users make webapp prototypes and iterate on them by writing tickets for the AI to complete. I for some reason call it Code+=AI: https://codeplusequ…
For example they're oh-so keen on doing math themselves, even though they're shit at it and I instructed them not to do any math.
It's also hit and miss if they implement the right method or not, even with low temperature.
In my case I was experimenting with translating simple word problems into matlab scripts, so a resultcould be computed.
Do you find the AST approach helps? Or is it mostly just throwing compute at it, ie larger more better?
