My bet is that we'll see a second layer of harness emerge, as self-driving codebases become the target. There will be an application facing harness, orthogonal to the agent facing harness. The app harness will represent the software factory that is emergent for the specific application being developed.
I suspect it won't be a harness, but just a more specific LLM trained in the universe of user-selected context of vetted resources.
Why? Because LLMs are always going to be dumb when they're trained at scale. Their ability to speak software diverges from their friendly user input layer. A harness won't overcome that, but an LLM saddle ontop of a larger model would provide the type of feedback loops you'd want to look into.
I don't think you'll find two deterministic systems will produce much.
I think that dissolves the "self driving" distinction, though? The mechanisms for driving the codebase must be present in the codebase itself. Otherwise its just a regular out-of-band development process.
rrook · · focus · HN ↗
Anyway, here's mine, still wip:
<a href="https://hale-lang.org/docs/dna/" rel="nofollow">https://hale-lang.org/docs/dna/
<a href="https://github.com/hale-lang/hale/issues/690" rel="nofollow">https://github.com/hale-lang/hale/issues/690
cyanydeez · · focus · HN ↗
Why? Because LLMs are always going to be dumb when they're trained at scale. Their ability to speak software diverges from their friendly user input layer. A harness won't overcome that, but an LLM saddle ontop of a larger model would provide the type of feedback loops you'd want to look into.
I don't think you'll find two deterministic systems will produce much.
verdverm · · focus · HN ↗
I'm working towards both in my homelab to see which works better with little qwen
rrook · · focus · HN ↗
cindyllm · · focus · HN ↗
[dead]