> When multiple moves have the top score, they are all top moves, even if visual markers (like move arrows) suggest the engine prefers one over the other.
Since all moves that checkmate the opponent will have the same score (M1 or -M1) they'll all be illegal.
One use case could be that a complete beginner to programming can enter some natural commands (e.g. "X is a list of numbers", "read 10 values in X") without worrying about the syntax and convert them to a working program in one of the target languages.
Also, the input doesn't have to be in English as it can be easily trained with samples from other languages. So people can write/speak in their native language and get it translated to working code.
At the moment it can recognise the type of statements in the training data set [1] and transpile them to Python, Java or C++ using the mappings defined here [2].
This is very different from how Codex/Autopilot work as it is trained using an NLU framework [3] which is usually used for training chatbots.
In case you're looking for a VS Code extension to quickly preview, filter and plot data from various file formats you can check out vscode-data-preview [0]
It will also save the time and effort currently required for cattle trading by both sellers and buyers.
For instance, Animall (one of the companies mentioned in the article) is working towards building an online marketplace for cattle (like Amazon) rather than just a discovery platform (like eBay or OLX) and will be handling verification and logistics (think "Amazon Fulfilled"). This would solve fraud and also reduce the cost and effort for sellers/buyers in trading cattle.