Building Autonomous Goal Loops That Deliver | Hacker News Reader

Building Autonomous Goal Loops That Deliver

jx0.ca

54 pointsjarredkenny9 comments

I do sometimes wonder if we are all writing more than we would if we just wrote the code ourselves.

I am asking that partially as a rhetorical question but also wondering your thoughts on when to deploy 'loop engineering' versus 'one-shot' versus writing the code yourself.

Additionally the post seems to talk in broad strokes without a specific proposal on a 'scorer' / determining adherence to the state goal. Do you have a thought on how that should be expressed? Do you feel that a human in the loop slows things down unnecessarily?

> Additionally the post seems to talk in broad strokes

AI slop tends to do that.

This makes sense, but boy would it be easy to mix up something like this with some fancy graphics and sell some snake oil. Stuff that sounds like

"What is therefore required is not merely a more capable agent, but a closed-loop capability orchestration substrate capable of continuously reconciling observed product reality against an evolving demand manifold."

fancy words; it's true, though ~ i think it was clear from the moment LLMs entered the scene that (if) one day they would be able to write code ~ then the real challenge would be to integrate the output into our organizations ~ and this integration would not work without changing the orgs

Sometimes I still feel uncomfortable with letting the project get to this point, where AI builds everything and even controls the product direction to some extent.

But at this point the AI most definitely understands the code and spots bugs better than I can, and it does seem like I can just let an AI bureaucracy run and then have a high-level look over its ideas and things will turn out just fine. If it isn't reliable enough, the problem nowadays is solvable just by adding more review agents.

Sorry, the animated banner at the top makes it hard for me to focus on reading.

I would add security and governance review before the scoring layer and ensure that scoring layer should include those feedbacks into next todos.

Any data pre/post implementation feels like everyone wants to optimise this. Caught myself in this too; how do we actually measure it

Sorry for the non-substantive comment, but I found the animated line at the top very distracting.

Reply on news.ycombinator.com