It could be used for coding if you gave it an AST.
If you work at TypeSafe please try this.
Side note: This is probably how LLMs would perform with better encoders and next-latent prediction, so eventually those will beat this architecture out. Still amazing though.
I saw the CEO reply elsewhere in the comments to some other question. Maybe he can shed some light on it. My gut feeling is that this is non-trivial and they did not get this to work (yet?), otherwise I can’t come up with a good reason as to why they would not demo that as I assume half of the crowd here (myself included) would line up as customers.
Yeah it would be quite trivial to try and implement an auto regressive AST generator for STLC with Jev provided that you had bounded variable names and integers.
As you said, if it worked, they would have demoed it haha
vatsachak · · focus · HN ↗
If you work at TypeSafe please try this.
Side note: This is probably how LLMs would perform with better encoders and next-latent prediction, so eventually those will beat this architecture out. Still amazing though.
Escapado · · focus · HN ↗
vatsachak · · focus · HN ↗
As you said, if it worked, they would have demoed it haha