I wonder when we'll start to see languages designed exclusively to be easy to write by agent programming.

nemo1618 5 hours ago | parent | next [-]

Here's one attempt: https://x.com/sigilante/status/2013743578950873105

My take: Any gains from an "LLM-oriented language" will be swamped by the massive training set advantage held by existing mainstream languages. In order to compete, you would need to very rapidly build up a massive corpus of code examples in your new language, and the only way to do that is with... LLMs. Maybe it's feasible, but I suspect that it simply won't be worth the effort; existing languages are already good enough for LLMs to recursively self-improve.

▲

gwern 5 hours ago | parent | prev | next [-]

Not going far enough - why would applications be written in either 'systems languages' or 'agent languages' if you have superintelligence too cheap to meter and you will amortize the costs over more than, say, a few days? Just write in raw assembler from a domain-specific design hyperoptimized for solely the task, the way Donald Knuth on steroids would.

▲

Grosvenor 6 hours ago | parent | prev | next [-]

Lisp?

I'm always surprised when agents aren't working directly with the AST.

▲

Rustwerks 6 hours ago | parent | prev | next [-]

There has been at least one posted here in Hacker News, Mojo. Google shows some other similar attempts.

The real issue with doing this is that there is no body of code available to train your models on. As a result the first few look like opinionated Python.

▲

krackers 6 hours ago | parent | prev | next [-]

It seems the language would need to be strongly typed, have good error reporting and testing infrastructure, have a good standard library and high-level abstractions, and be "close enough" to existing languages. Go would seem to already fit that bill, any bespoke language you come up with is going to have less exposure in the training set than Go. Maybe Rust as a second, but Go's memory management might be easier for the LLM (and humans) than Rust's.

▲

wenc 5 hours ago | parent [-]

Rust, Go and TypeScript are good bets.

Python too -- hear me out. With spec-driven development to anchor things, coupled with property-based tests (PBT) using Hypothesis, it's great for prototyping problems.

You wouldn't write mission critical stuff with it, but it has two advantages over so-called "better designed languages": massive ecosystem and massive training.

If your problem involves manipulating dataframes (polars, pandas), plotting (seaborn), and machine learning, Python just can't be beat. You can try using an LLM to generate Rust code for this -- go ahead and try it -- and you'll see how bad it can be.

Better ecosystems and better training can beat better languages in many problem domains.

	▲	Jtsummers 5 hours ago \| parent [-]
		> You wouldn't write mission critical stuff with it People do, they also write mission critical stuff in Lua, TCL, Perl, and plenty of other languages. What they generally won't do is write performance critical stuff in those languages. But there is definitely some critical communication infrastructure out there running with interpreted languages like these out there.

▲

calvinmorrison 6 hours ago | parent | prev [-]

or rather, maybe we stop seeing new features that are mostly there for developers and find some older languages are quite good and capable, maybe even easier since there's less to reason about