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.
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.
8note · · focus · HN ↗
youd ask it to pick a location on the ast to add something from the grammar?
i dont see how this stays confined well enough? make a new output space every time? does that end up auto-regressive?