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

Building an Advanced Agentic Harness

data4sci.com

Post reply on HN
Print view View original

11–20 of 47 posts

Re: Building an Advanced Agentic Harness

#11

Post by hagen8 »

Axsuul wrote: post #7

Anyone else have related reading that touches on this? I'm building my own custom harness and want to start implementing loop support, etc. But I also want to build some sort of framework so that it's dynamic (e.g. this needs to run x number of iterations, while planning needs to run y number of iterations).

Check out academic papers about:

1. Hierarchical skills, workflow, skill learning 2. Meta Harness, self-learning harnesses 3. Trace/trajectory representation 4. Common agentic benchmarks

But first more basic things like 5. Blog posts form anthropic 6. How Claude Code/PI/ Hermes!! agent works 7. Agent sessions/ Forking/ Hooks

Re: Building an Advanced Agentic Harness

#13

Post by alansaber »

Axsuul wrote: post #7

Anyone else have related reading that touches on this? I'm building my own custom harness and want to start implementing loop support, etc. But I also want to build some sort of framework so that it's dynamic (e.g. this needs to run x number of iterations, while planning needs to run y number of iterations).

Sounds like you want something similar to /goal mode in Codex.

Re: Building an Advanced Agentic Harness

#14

Post by metadat »

Axsuul wrote: post #7

Anyone else have related reading that touches on this? I'm building my own custom harness and want to start implementing loop support, etc. But I also want to build some sort of framework so that it's dynamic (e.g. this needs to run x number of iterations, while planning needs to run y number of iterations).

Check out https://github.com/strongdm/attractor along with the community implementations at https://factory.strongdm.ai/products/attractor#community.

Re: Building an Advanced Agentic Harness

#15

Post by alansaber »

dominotw wrote: post #2

why do i hate skillks, harnesses , memory systems whatever. such ideas that everyone thinks they've discovered but are totally useless in practice.

What each of these is doing, fundamentally, is solving context management in an opinionated way (that and guardrails).

Re: Building an Advanced Agentic Harness

#16

Post by alansaber »

champagnepapi wrote: post #3
dominotw wrote: post #2

why do i hate skillks, harnesses , memory systems whatever. such ideas that everyone thinks they've discovered but are totally useless in practice.

agreed. All of these are trying to get to something that can't really every be achieved with LLMs with is determinism. Folks are trying to constrain the models to behave in a certain way with all of these tools, but there's far too many edge cases for them to be reliable. Doesn't mean they can't add some value, but it seems very limited. Hoping it's only a matter of time before we go back to engineering and step back…

So AI is mostly a thin glue between deterministic processes. Doesn't change the fact that that is enough to achieve an extremely large amount of tasks.

Re: Building an Advanced Agentic Harness

#17

Post by hanneshdc »

Any benchmarks showing if this actually improves problem solving? Or reduces errors?

The idea is cool, but from own experience in harness engineering, lots of cool sounding ideas can have a negative impact on performance due to emergent and confounding effects.

So I'm a bit skeptical!

Re: Building an Advanced Agentic Harness

#20

Post by Yopolo »

dominotw wrote: post #2

why do i hate skillks, harnesses , memory systems whatever. such ideas that everyone thinks they've discovered but are totally useless in practice.

No clue?

I don't think they are totally usesless.

And its clear that progression is happening on a communith level on all of these and they get integrated later on in commercial offerings like from Anthropic and co.

But also doing a opensource harness and not just giing in to the big companies allows us to have all of this open and transparent and with open models locally.

Post reply on HN