Is there a relationship between how good a programming language is for coding agents and how popular it is among humans? If so, wouldn't Python be the best language for agents, since it's is the most popular (and hence has the most context available for models)?

▲

3eb7988a1663 2 hours ago | parent | next [-]

Pick something slightly esoteric (eg Haskell) and the quality of public code is very high, because you only have enthusiasts writing it. Choose something taught in schools (Python) and you are going to find 10,000 traveling salesmen homework problems and Django todo applications.

Not sure how you thread the needle on the quality vs quantity dynamic.

▲

throw-the-towel 2 hours ago | parent | prev | next [-]

As much as I love Python, JavaScript (including TypeScript) is probably more popular.

▲

frollogaston 2 hours ago | parent [-]

That and JS code is more readily available in the source of tons of webpages, not hidden away in some backend

▲

maleldil an hour ago | parent [-]

Wouldn't most frontend JS in Web page sources be minified?

	▲	frollogaston an hour ago \| parent [-]
		The logic is still there, it's not meant as obfuscation. Also plenty of sites don't minify cause that involves a whole toolchain.

▲

Sha1rholder 2 hours ago | parent | prev [-]

There is definitely a relationship. But I personally believe that once the training corpus reaches a certain scale, the returns exhibit diminishing marginal effects, to the point that multiplying the data volume cannot surpass something essential inherent in language design. (Asked an LLM to help me with the translation, so forgive my expression)