[zozbot234]

It will be interesting to compare this to https://news.ycombinator.com/item?id=47476422 and https://news.ycombinator.com/item?id=47490070 . Very similar design except that this is apparently using mmap, which according to the earlier experiment incurs significant overhead.

[salynchnew]

It was written by an LLM, so... yeah.

[jeffybefffy519]

Except this isnt using heavily quantised versions of the model thus reducing quality.