[onion2k]

I went to the lodash docs and asked about how I'd use the 'pipeline' operator (which doesn't exist) and it correctly pointed out that pipeline isn't a thing, and suggested chain() for normal code and flow() for lodash fp instead. That's pretty much spot on. If I was guessing I'd suggest that the base model has a lot more lodash code examples in the training data, which probably makes a big difference to the quality of the output.

[billyp-rva]

The lack of a pipeline operator in JS (and JS libraries like lodash) has also been discussed online a lot.

[onion2k]

Exactly the point. If there's a lot of data in the training set the results will be better.

[billyp-rva]

I guess I'm trying to emphasize the distinction between information in the repo (code) vs. information elsewhere (discussions) that the model looks at.