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

Harness engineering: Leveraging Codex in an agent-first world

openai.com

Post reply on HN
Print view View original

71–80 of 222 posts

Re: Harness engineering: Leveraging Codex in an agent-first world

#71

Post by cpard »

yurimo wrote: post #41

What I still can't understand is why is massive amount of code generated is a flex? I don't feel that software has gotten a lot better in past 3 years, only sloppier. It's surprising to me that people who know about reward hacking choose a simple objective like lines of code generated as a signal for quality. I'd argue you have to optimize for less lines generated as possible while secondary optimization should be re…

I don’t think the flex here is the amount of code alone. Their goal is to show that AI can improve productivity, the number of lines is just the proxy to that. This article is a marketing piece after all.

Now someone can argue that lines of code are not a good proxy of engineering productivity, but I wouldn’t be surprised if the audience they target with this content is not the HN commenters of this thread.

Re: Harness engineering: Leveraging Codex in an agent-first world

#72

Post by jplusequalt »

linsomniac wrote: post #40
apical_dendrite wrote: post #31

I wonder why we as engineers aren't protesting AI in the same way that artists and people in film and television are. This post should instill the same terror that visual artists feel. If you're a more senior person in tech, this post is effectively saying that a large portion of your skillset is about to become completely worthless. This goes beyond the skills involved in writing the code. Everything that you've lea…

>a large portion of your skillset is about to become completely worthless I'm not convinced of that. I watched a video of an architect using AI to create architectural drawings. It became very clear to me that he has a lot of skills and terminology that helped him produce something very specific, in a few minutes. I've been working on some home improvement stuff including a studio/shed and I've struggled to produce e…

How do you keep your skills if you no longer engage in the activity that keeps them sharp?

Re: Harness engineering: Leveraging Codex in an agent-first world

#73

Post by YZF »

yurimo wrote: post #41

What I still can't understand is why is massive amount of code generated is a flex? I don't feel that software has gotten a lot better in past 3 years, only sloppier. It's surprising to me that people who know about reward hacking choose a simple objective like lines of code generated as a signal for quality. I'd argue you have to optimize for less lines generated as possible while secondary optimization should be re…

Lines of code has always been a terrible metric. But all else being equal it is a measure. If all else is not equal, which is usually the case, then it's not.

A lot of the focus has been on AI recently.

Three years ago we didn't have software where a non-software engineer can describe what they want in English and get working (-ish) software generated by other software? Is that not "software has gotten a lot better"?

Other than that I'm not sure how we measure "software has gotten better". New applications? More features? How do we measure sloppier? Is Google Maps suddenly taking you the wrong way more often? I'm not really doubting your subjective experience but seriously how do tell? I mean a doc is a doc and a spreadsheet is a spreadsheet.

We're also only about 10 months into models that are powerful enough to potentially make a bigger difference and we are still figuring out how to use them best.

Re: Harness engineering: Leveraging Codex in an agent-first world

#74

Post by threethirtytwo »

yurimo wrote: post #41

What I still can't understand is why is massive amount of code generated is a flex? I don't feel that software has gotten a lot better in past 3 years, only sloppier. It's surprising to me that people who know about reward hacking choose a simple objective like lines of code generated as a signal for quality. I'd argue you have to optimize for less lines generated as possible while secondary optimization should be re…

Because sloppy code and doesn't matter. He wrote he completed it in 1/10th time. That's equivalent to 1/10th the engineers.

That is a business win. That is really all that matters in capitalism.

The flex is a direct insult to your face. He is shitting on the faces of all software engineers (me included). It is equivalent to saying we don't need you to code anymore. One man can produce 10x the code.

So why am i voting him up even though he's shitting on my face? Because what he says is true. I value honesty and people who say things like it is. Yes my identity as a software engineer is getting dismantled before my very eyes. But the solution to this problem isn't some delusional statement about not understanding what he's flexing about. We're not stupid. Everyone on this thread understands his flex. The difference is some people like you don't want to understand it.

Like seriously. He literally wrote it was completed in 1/10th of the time and you expect me to believe that YOU don't know what HE is flexing about? Be real. You're not stupid.

Re: Harness engineering: Leveraging Codex in an agent-first world

#75

Post by ajpaulson »

> The diagram below shows the rule: within each business domain (e.g. App Settings), code can only depend “forward” through a fixed set of layers (Types → Config → Repo → Service → Runtime → UI). Cross-cutting concerns (auth, connectors, telemetry, feature flags) enter through a single explicit interface: Providers. Anything else is disallowed and enforced mechanically.

Can anyone give me a simplified explanation of what they’re saying here? Having some trouble understanding.

Re: Harness engineering: Leveraging Codex in an agent-first world

#76

Post by satvikpendem »

esikich wrote: post #29
zatkin wrote: post #23

I worry most about blindspots with this kind of approach. Let's say that this repository goes on for years, at which point the docs folder is several MB in size. Would Codex be able to think outside of the box? Or would the aggregate of the Markdown content fundamentally cover enough ground to prevent it from thinking of novel new approaches to existing problems?

You tell it to update the docs: not append. I've done the same thing with a readme in the root with links to the docs. After every commit, before the push, I have my agent "update all relevant and related docs, add or remove what's needed" or something to that extent. And it works remarkably well. I also have an append only change log it's supposed to add to. Between that, good commit messages, and comprehensive test…

Someone else in the comments said to have it make a static website with the info instead with clickable pages and sections so it reads only the content it needs to rather than dumping a long file into context windows. Although I suppose you can have a ToC in the readme too with multiple smaller markdown files as references.

Re: Harness engineering: Leveraging Codex in an agent-first world

#77

Post by YZF »

apical_dendrite wrote: post #31

I wonder why we as engineers aren't protesting AI in the same way that artists and people in film and television are. This post should instill the same terror that visual artists feel. If you're a more senior person in tech, this post is effectively saying that a large portion of your skillset is about to become completely worthless. This goes beyond the skills involved in writing the code. Everything that you've lea…

What is that protest going to get us? We'll convince or force business leaders to not use a cheaper/better tool and protect our jobs? And nobody else in the world is going to pivot either? And our companies will remain competitive?

Software engineers have always adapted to new technologies. New languages, frameworks, native apps, browser apps etc. So far this doesn't seem to be close to completely removing us from the loop.

If you are smart, educated, and can adapt, you'll figure it out. The economy has to find some stable equilibrium and it's not a zero sum game. Everyone in the economy getting a paycheck is also a consumer. With no consumers there is no business. The companies who are using AI and become more productive can do more things that before were not profitable but now are. Some of the people who are getting laid off are going to start new businesses and hire people. These things always cycle, and they basically have to.

I don't have a crystal ball though.

Re: Harness engineering: Leveraging Codex in an agent-first world

#78

Post by iso1337 »

ajpaulson wrote: post #75

> The diagram below shows the rule: within each business domain (e.g. App Settings), code can only depend “forward” through a fixed set of layers (Types → Config → Repo → Service → Runtime → UI). Cross-cutting concerns (auth, connectors, telemetry, feature flags) enter through a single explicit interface: Providers. Anything else is disallowed and enforced mechanically. Can anyone give me a simplified explanation of…

IIUC its just strict separation of concerns

Eg UI cannot reach down and directly read config files

Configs must be only read by (im assuming) a storage interface layer called repo

There’s a strict directionality of dependency

Somewhat similar to ports and adaptors but presumably more strictly enforced by deterministic linters

Re: Harness engineering: Leveraging Codex in an agent-first world

#79

Post by nullbio »

nimonian wrote: post #68
drivebyhooting wrote: post #62

I wish these breathless blog posts would actually try to be more didactic. For example, actually doing a walkthrough of how to set up these allegedly super powered workflows and concrete demonstrations. I’m not an AI skeptic. Rather I’d don’t want to miss out on any actual super powers.

I do quite a lot of what this post describes in a reasonably large project. Here's what works for me: - write gherkin features for new features; update them for enhancements; don't touch them for refactors. Label your PRs with these nouns. - use pre-push hooks for type checks, linting, unit tests, and other quick, scriptable validations. - make a viteperess subsite in your repo, have the agents maintain it - document…

Can you share your skill please?

Re: Harness engineering: Leveraging Codex in an agent-first world

#80

Post by zahlman »

crdrost wrote: post #59
yurimo wrote: post #41

What I still can't understand is why is massive amount of code generated is a flex? I don't feel that software has gotten a lot better in past 3 years, only sloppier. It's surprising to me that people who know about reward hacking choose a simple objective like lines of code generated as a signal for quality. I'd argue you have to optimize for less lines generated as possible while secondary optimization should be re…

Yeah so all of personal computing—text editing, SVG antialiasing, etc, fits in 20,000 LOC (VPRI's STEPS project) so a million lines of code is 50 reïnventions of personal computing. BUT: it is unlikely that humans would have solved this problem in 20 kLOC. Sussman said “we really don't know how to compute!” as his talk title and LLMs had to ossify some pre-existing voice as the forever programming habitus and it chos…

> VPRI's STEPS project

The what now? Search engines failed me here.

Post reply on HN