Just want to chime in that I’ve seen TabbyML used a fair bit at work. Tabby in particular can run locally on M1/M2/M3 and uses the Neural Engine via CoreML. The performance hit isn’t noticeable at all and most of what we use it for (large autocompletes in serialized formats) it excels at.
I know people still enjoy this game quite a bit and my opinion shouldn’t take anything from that, but this pattern of finally adding new ships to the game but putting them behind “ARX Early Access” is really predatory. I have a hunch that this is done to “encourage” more players to spend cash in the ARX store, but ships shouldn’t be the mechanism to do that.