Lozza 2.0 is pretty much unchanged except that material, PSTs and all evaluation params were tuned in one go using Peter O's 'Texel' method. The tuning code is in the repo if any other Javascript developers are interested. It's 'the' +1/-1 slow algorithm, but I was not in a rush and It ran for weeks!
At 60+1 that seems to give +150 elo ish on the previous version. testing results here: https://github.com/op12no2/lozza/blob/m ... esting.log
Repo and download here: https://github.com/op12no2/lozza (you'll also need node.js installed to play in Winboard etc.)
Play online in your browser here: https://op12no2.github.io/lozza-ui (mobile friendly - there are also analysis, console and mate-in-1 UIs)
Now to figure out what all this NNUE noise is about...