[irq-1]

> “We’re heading into a new age of AI-assisted coding, and right now, it’s difficult to predict how that will play out. But if I had to place a bet, I would say that in the long run, AIs are more likely to generate high-quality code in a language like Gleam. Gleam makes it quick and easy for AIs to check their code, get instant feedback, and iterate. That should be an advantage compared to languages that are slow to build, have cryptic error messages, and can’t catch mistakes at build-time.”

Interesting point and one I haven't seen before. Almost like arguing that AI will work best with things it can learn quickly, rather than things that have lots of examples.

[cardanome]

I feel like now that LLMs are getting better the quality of the examples matters more than the quantity.

Garbage in, garbage out. If you confuse it with a lot of Junior-level code and have a languages that constantly changes best practices, the output might not be great.

On the other hand, if you have a languages that was carefully designed from the start and avoids making breaking changes, if it has great first party documentation and a unified code style everyone adheres to, the LLM will have an easier time.

The later also happens to be better for humans. Honestly the best bet is to make a good language for humans. Generative AI is still evolving rapidly so no point in designing the lang for current weaknesses.

[mikepurvis]

If the main win of starting over with a new language is that you don't have a giant glut of legacy example code and documentation targeting no-longer-the-best-practice, maybe there's a solution where you take an established modern language like rust or go and feed the LLM a more curated set of material from which to learn.

Like instead of "the entire internet", here's a few hundred best-practice projects, some known up-to-date documentation/tutorials, and a whitelist of 3rd party modules that you're allowed to consider using.

[lanthissa]

It feels like it should be true that a referentially transparent type safe language would be the 'right' language for ai coding since each code block is stateless you should be able to in parellel decompose problems and test them infinitely down.

[hinkley]

I can’t say where AI will end up but I firmly believe it will pick winners and losers in the next generations of programming languages. Not always for the better.

Any language that is difficult for an AI to understand will have to get popular by needing far less boilerplate code for AIs to write in the first place. We may finally start designing better APIs. Or lean into it and make much worse ones that necessitate AI. Look especially to an AI company to create a free razor and sell you the blades.

[pahbloo]

I believe the best scenario is a language that gives an AI the best environment to train itself in a manner similar to the way a game like Go gave AlphaGo the opportunity to play innumerable times against itself and study the results.

I think the best programming languages of the future will come with their own LLMs, synthetically trained before release.

[WJW]

If you have good enough (LSP+MCP) tooling, I'd expect that the LLM can learning quickly vs the LLM having lots of examples would converge towards being the same thing. At the very least it could generate many potential examples, put them all through the tooling to deterministic to get many "true" examples and then learn from that.

[btschaegg]

> […] rather than things that have lots of examples.

Well, one glaring issue with the assumption of the quality of LLM output being mostly dependent on a large volume of examples online would be Sturgeon's law.