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

Backpressure is all you need

lucasfcosta.com

Post reply on HN
Print view View original

111–120 of 133 posts

Re: Backpressure is all you need

#111

Post by oblio »

lovich wrote: post #107
ip26 wrote: post #95

Earlier quoted context omitted.

Depends on the quality of your validation loop. Can the agent find the bug in a five second unit test, or does it have to run the full deployment test? It also presents tradeoffs in compute budget. Cycles spent executing large arrays of tests could mean less tokens spent debugging.

> Depends on the quality of your validation loop. Can the agent find the bug in a five second unit test, or does it have to run the full deployment test? I am not asking about time or completeness. I am asking if this person is spending 1 dollar to make more than a dollar, or if they are spending 1 dollar to make less than a dollar. Any other criteria is not necessary to consider, if the activity is not profitable.

Who cares about that?

Vibes, baby, vibes!!!

Re: Backpressure is all you need

#114

Post by khafra »

erooke wrote: post #98
ovi256 wrote: post #83

Earlier quoted context omitted.

It seems the OP agrees with you, and he's proposing a method for how to do so using agents.

> It is the responsibility of the person running the coding agent to make sure the resulting PRs are high quality. And > he's proposing a method for how to do so using agents Are not in agreement. The claim being made is that you shouldn't be sending PRs you haven't personally vetted to be high quality. Definitionally a bot cannot be used to personally vet something.

This is not a contradiction; it's an augmentation. As an operations guy, I can tell you that well-constructed automation to reduce the amount of manual checking a human has to do almost always increases the quality of the overall process's output.

Re: Backpressure is all you need

#116

Post by _zoltan_ »

teleforce wrote: post #102
_zoltan_ wrote: post #9

"In this post, I’ll cover a third, not-so-obvious approach: building ways for the agent to validate more of its own work before a human has to step in. " this has been an obvious thing to do since at least January (since Geoffrey Huntley published "everything is a ralph loop"), and this is how I've been working: build enough orchestration tooling to be able to automate everything: development container bringup, build…

The rest of the paragraph explanations are more important. "The goal to make longer unattended sessions safe enough to be useful without fully removing the human from the loop. It should also reduce the number of low-quality PRs your teammates have to review for details the agent should have caught itself." >safe enough to be useful without fully removing the human from the loop This is the fundamental concept for AI…

it's fine to remove the human from the loop. set a macro goal, tell the agent how you think it could go there, and let it go nuts.

with enough scaffolding around self-reflectivity and metrics, it will converge.

Re: Backpressure is all you need

#118

Post by atq2119 »

khafra wrote: post #114
erooke wrote: post #98

Earlier quoted context omitted.

> It is the responsibility of the person running the coding agent to make sure the resulting PRs are high quality. And > he's proposing a method for how to do so using agents Are not in agreement. The claim being made is that you shouldn't be sending PRs you haven't personally vetted to be high quality. Definitionally a bot cannot be used to personally vet something.

This is not a contradiction; it's an augmentation. As an operations guy, I can tell you that well-constructed automation to reduce the amount of manual checking a human has to do almost always increases the quality of the overall process's output.

Of course it does, but that's beside the point.

As a software developer, you must never subject your team mates to a PR that you yourself believe to be low quality. The point of code review by others is to catch things that you missed.

There are multiple lines of defense for quality. Yes, automation can and should be one of them, but your own self-review always has to come before review by your team mates.

Re: Backpressure is all you need

#119

Post by doom2 »

Yokohiii wrote: post #44
wellpast wrote: post #4

I’m willing to be wrong but this industry-wide emphasis on AI creative/coding workflows seems way over-engineered. Ime successful creative execution looks like micro-iterations where each output informs the next creative move. I can build something incredibly fast from essentially caveman grunt instructions through an LLM harness, iterating as I go. Optimizing for feeding a huge plan to an agent sounds to me like a n…

LLMs are too flaky for high quality code. On tougher problems it's very common for an LLM to contradict itself and run in circles. It simply doesn't know what the right thing is, but on each turn it is super confident to do the right thing. Maybe I've chosen hardmode to learn C with LLM assistance, plus my pet project turned out to be a bit less trivial then anticipated. But I know that I have to think three times ab…

> Maybe I've chosen hardmode to learn C with LLM assistance

May you speak a little more about how you're approaching this? I was thinking of doing similar

Re: Backpressure is all you need

#120

Post by SR2Z »

oblio wrote: post #109
dirtbag__dad wrote: post #53

Earlier quoted context omitted.

You can get really far with the 20x Claude Code and Codex plans. They are many orders of magnitude cheaper than api calls.

Enjoy that until the token economy comes crashing down on you.

Anthropic is profitable. When will people stop pretending like AI has not found real applications where it creates value?

It's here to stay, and IMO once VLA-driven robots enter the real world there will be enough money to pay for the datacenters. This coding stuff is great but there are only so many engineers to sell to.

Satya Nadella once said (more or less) "if AI is so good, why doesn't it show up in GDP?"

That's gonna be the step where it shows up in the GDP. Being able to train a machine to solve any problem that can be phrased in tokens (i.e.: most of them) is going to remake society.

Post reply on HN