Hacker News
Autolith: A programming agent with a live runtime
a2ff6eeb0
|next
[-]
jbott
|root
|parent
[-]
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
|root
|parent
[-]
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
|root
|parent
[-]
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.
rufius
|next
|previous
[-]
I didn’t actually do anything with that idea yet but may look at the idea in Elixir this weekend.