alt Hacker NewsSounds like OP did some pretty cool engineering to make this run performantly. Definitely not your run of the mill AI slop.
Replies
mentalgear • yesterday at 8:01 PM
why? at least the chart in the docs suggests otherwise.
serf • yesterday at 8:08 PM
eh.
performance is easy. you can craft a test suite that will allow a ralph loop to iterate until it hits the metrics.
the hard part of style/feel/usability. LLMs still suck at that stuff, and crafting tests to produce those metrics is nigh impossible.
It doesn't run at all. If you can get it running, let me know.