Nit: the author says that supervised fine tuning is a type of RL, but it is not. RL is about delayed reward. Supervised fine tuning is not in any way about delayed reward.

This language seems quite similar to Scallop [1], which was recently posted to HN [2]. Both are extensions of Datalog to arbitrary semirings, meaning that they generalise assigning merely true or false to relational statements, allowing probabilistic reasoning and more (almost arbitrary tagging of statements). Scallop is further focused on being differentiable and being able to integrate Scallop code into a PyTorch function. Both seem to have quite a bit of work put into them and have JIT compilers (Scallop also has a GPU implementation). I like the sound of "I have further modernized Dyna to support functional programming with lambda closures and embedded domain-specific languages." [3]

Going to try it out.

[1] https://www.scallop-lang.org/

[2] https://news.ycombinator.com/item?id=43443640

[3] https://matthewfl.com/research#phd

Ugh hate they used this name

The US has shown absolutely no willingness to carry out antitrust cases the past many years - at a significant harm to a lot of people.

The implied corruption is likely not from these other countries that start making these cases now, but is a persistent feature of US governance.

I owe my entire 20 year career to open source, so if anything, I plan to increase the number of contributions I make as time goes on; it's one of the few areas in life where I feel indebted.