Autolith: A programming agent with a live runtime

a2ff6eeb0•about 3 hours ago

Given that the most important feature for agent performance is the popularity of the language, ie, the amount of training data, (https://danluu.com/pl-tokens/), why would you cause problems for yourself by using Lisp rather than Python/Javascript if you care mainly about results fast, or C/C++/Rust if you care about performance too?

wild_egg•about 1 hour ago

LLMs have been solid at writing Common Lisp since Sonnet 3.5 and have been near flawless since the Opus 4.5 release.

The niche language thing is really not a problem at all any more. If you're working in some esolang it doesn't take more than a 1-2k token primer in the context to get great results, and lisp is popular enough to not even need that.

The benefit of having the agent directly in the image like with Autolith here is that it can directly inspect all defined symbols and explore and orient itself automatically. Really doesn't need much guidance to get great results.

jbott•about 2 hours ago

> the most important feature for agent performance is the popularity of the language

This is explicitly called out as only weakly supported in that blog post:

  - You should use a popular language
    - There's weak support for this statement

a2ff6eeb0•about 2 hours ago

Feel free to do your own analysis -- my informal experiments backs this up, though. I see worse results when I try to do anything in an unpopular language.

It makes sense, needing to train the model on things that aren't already in its weighs takes up valuable context. Until we have models that update their weights based on what they've seen in their recent sessions and learn like people, this will be a problem.

For now, though, between the results I'm seeing here, and the lack of need to look at code, I think this kills off any reason for me to use less popular languages.

jauntywundrkind•about 2 hours ago

Your attempt was probably pretty, ahem, weak. How much support would you say you gave your goes, before you threw in the towel?

I don't think there's really ever a downside to leaning in and making use of a language or system that works for you. Trying to tell people they should just use the popular thing is, imo, bad advice to turn hackers and experimenters into boring people.

yogthos•about 1 hour ago

The obvious reason is that Lisp is perfectly suited for writing self modifying programs in a way pretty much no other language is. And as others pointed out, the evidence that agents work better with other languages is pretty thin. I've been using Claude, GLM, and DeepSeek with Clojure for around a year now, and they certainly do just fine in my experience.

In fact, I've had much easier time maintaining LLM assisted programs in Scheme and Clojure than other languages I've tried using because functional style naturally leads to low coupling. And that makes controlling context far easier than the rats nest of shared state that you have in imperative languages.

rufius•about 3 hours ago

This is an interesting idea. I was thinking about something similar in Smalltalk or Erlang the other day. Mostly building on the actor/object+mailbox concept.

I didn’t actually do anything with that idea yet but may look at the idea in Elixir this weekend.

ggangsir•about 2 hours ago

How do differentiate with cursor ?

yogthos•about 3 hours ago

Amusingly, I started building something very similar in Jolt today :) https://github.com/yogthos/samizdat/

Autolith: A programming agent with a live runtime

⚡ Community Insights

Discussion (12 Comments)Read Original on HackerNews