I guess if you tell codex to build a transpiler from a subset of python to brainfuck, then solve in that subset of python, it would work much better. Would that be cheating?
Doing something like that is basically the only way to write unlambda: you start with a lambda calculus (or scheme or whatever) and reduce the lambdas away mechanically. (This is in the unlambda docs!)
It would have been fun to see how AI generated voice (like https://www.enginn.tech ) could be integrated as well (and have an estimate of how much time it saves)
Eh they're forcing people to use a plugin which uses their servers/magic. The real revolution will happen (eventually) with open source models that either run on the player's machine or tools that are used to generate at build time.
I guess it's probably something along the lines of "LaMDA: Language Models for Dialog Applications" (see https://arxiv.org/abs/2201.08239 ). Given that the three first authors are part of the team at Character.ai (see https://beta.character.ai/help)
Although they should not dismiss it at all as it can lead to extremely successful companies. I have Dataiku or UIPath (they did it for years) as good examples. They leveraged their existing customers to test their first product, with success.
That is true up to a certain point (for instance, in my experience, having bounding boxes that are not pixel-perfect acts as a regularizer), but there is also a good chance that you are mislabelling edge cases, situations that happen rarely, and that definitely hurts the performance of the neural network to make a correct prediction on these difficult / uncommon scenarios.
reply