Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Harness engineering for self-improvement

lilianweng.github.io

Post reply on HN
Print view View original

41–50 of 96 posts

Re: Harness engineering for self-improvement

#41

Post by bisonbear »

I’ve been thinking about how we practically implement this at an organizational layer for large codebases. There’s clearly alpha to be had in optimizing AGENTS.md / skills / tools / … to improve performance, quality, and cost efficiency of an agent. The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever.

The first step I see towards this is building a generic, reliable, and accurate *fitness function* for codebases - turning PRs into gradeable tasks that an agent can solve, and improve on.

I’m pretty curious how others are optimizing the coding agent harness now, as this has been a huge pain point for my company (we’re pretty much relying solely on vibes).

Re: Harness engineering for self-improvement

#43

Post by zby »

ianm218 wrote: post #40
zby wrote: post #34

IMHO training weights has peaked and now it is time for a training paradigm for prompts and code. We don't have the gradient descent here - but I think it can be more sample efficient because causal theories can be better than just correlations. I am working on a unified theory in https://zby.github.io/commonplace/ - it is all agent edited so it might be hard to read, but hopefully we are catching most logical errors…

Is there any reason to think that training weights has peaked rather than is accelerating? It feels like now they are increasingly able to pick some low hanging fruit by using the models in order to improve themselves and test optimizations.

to be frank - mostly because they are now good enough to unlock the other learning paradigms

Re: Harness engineering for self-improvement

#44

Post by velcrovan »

K0balt wrote: post #20
Drakim wrote: post #9

Earlier quoted context omitted.

If we don't create the Torment Nexus first, somebody else who is much less responsible is gonna create the Torment Nexus before us. It's outright irresponsible to not take the lead, we might have to even give up on all safety concerns to make sure we make it to Torment Nexus IPO first.

Since we all know that at this point, someone is definitely going to build the torment nexus, we all may as well get involved and help, so that at least we can exert some limited degree of control over the eventual character of the torment nexus. At least that way maybe we can make it a little less terrible. At any rate, it can’t make it worse than it would have been if we -didn’t- help build it!

https://fundthebasilisk.com

Re: Harness engineering for self-improvement

#45

Post by clamshelldev »

bisonbear wrote: post #41

I’ve been thinking about how we practically implement this at an organizational layer for large codebases. There’s clearly alpha to be had in optimizing AGENTS.md / skills / tools / … to improve performance, quality, and cost efficiency of an agent. The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever. The first step I see towards this is building a gener…

[flagged]

Re: Harness engineering for self-improvement

#46

Post by sulam »

bisonbear wrote: post #41

I’ve been thinking about how we practically implement this at an organizational layer for large codebases. There’s clearly alpha to be had in optimizing AGENTS.md / skills / tools / … to improve performance, quality, and cost efficiency of an agent. The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever. The first step I see towards this is building a gener…

You've just described what the AI industry refers to as "evals", a collection of which forms a particular benchmark. I definitely encourage you to define your own evals, because the public benchmarks are often either saturated (largely solved and only going to see small improvements going forward) or seemingly not predictive of real world performance. I could also go further and speculate that they are in the training data, although credible benchmarks avoid this, I'm just not sure how successful they are.

Re: Harness engineering for self-improvement

#48

Post by bisonbear »

sulam wrote: post #46
bisonbear wrote: post #41

I’ve been thinking about how we practically implement this at an organizational layer for large codebases. There’s clearly alpha to be had in optimizing AGENTS.md / skills / tools / … to improve performance, quality, and cost efficiency of an agent. The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever. The first step I see towards this is building a gener…

You've just described what the AI industry refers to as "evals", a collection of which forms a particular benchmark. I definitely encourage you to define your own evals, because the public benchmarks are often either saturated (largely solved and only going to see small improvements going forward) or seemingly not predictive of real world performance. I could also go further and speculate that they are in the trainin…

Thanks for the comment - I’ve actually been working on something to generate evals from private repos, as I 100% agree that public benchmarks are either contaminated (as OpenAI found with SWE-bench Verified), not high quality (as OpenAI found with SWE-bench Pro), or in the case of “good” benchmarks (Cognition’s Frontier Code comes to mind), non-representative of a specific repo’s work.

Sharing some challenges / learnings from the journey so far:

* Tests alone are non-representative: an agent can pass tests but write the code in a way that’s subjectively worse than another test-passing result

* However, tests are still important and the best form of deterministic evaluation we have

* Creating executable environments to run the tests is challenging, especially when considering that this should be doable for arbitrary repos

* Selecting tasks that discriminate is an art - they need to be challenging, but not too challenging, represent the variety of work that’s done in the repo, and contain tests that failed prior to the change

* LLMs / agents are very powerful at judging code - but doing so in a way that is calibrated, consistent, and representative of codebase standards requires careful rubric creation and grading

* I’ve shifted towards using agents (from “static” LLM calls) to generate the rubrics, and to later grade the rubrics. This is powerful but even more non-deterministic

Re: Harness engineering for self-improvement

#50

Post by jtr1 »

bisonbear wrote: post #41

I’ve been thinking about how we practically implement this at an organizational layer for large codebases. There’s clearly alpha to be had in optimizing AGENTS.md / skills / tools / … to improve performance, quality, and cost efficiency of an agent. The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever. The first step I see towards this is building a gener…

Just working on my own stuff so YMMV, but from a cost reduction standpoint, the two most outsized ROI wins came from making sure the agent runs all terminal commands in quiet and using a codebase index mcp to speed up understanding and reduce full file reads [0]. I've also found the latter also dramatically improved the quality of output.

[0] https://github.com/DeusData/codebase-memory-mcp

Post reply on HN