Live data from Hacker News

Harness engineering: Leveraging Codex in an agent-first world

openai.com

91–100 of 222 posts

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

#91
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…

The "lines of code" at this point are basically the same thing as binary code that comes out of a compiler - something you almost never look at and certainly won't try to touch by hand. The actual "code" is everything driving the harness. The current problem for this is that the harness is not (yet) deterministic, so it's sort of like having a compiler where your output program works slightly differently every build,…

I think the telling part is in this line:

> Because the repository is entirely agent-generated, it’s optimized first for Codex’s legibility

I asked a question from a perspective of a human engineer, as in, I will have to read the code and understand, fix it once it breaks. OpenAI approach is opposite, even if it is breaking it is the agent that will be doing the fixing, millions of lines and inelegant designs don't matter because human readability doesn't matter. In any case you use more tokens so you fork over more money.

I will say, however, that IMHO there is objectively bad and good code in terms what it can do and performance, if I can do the same thing in 50 lines as opposed to 1000 lines, this difference still matters for the model. Smaller context usage, better approach that informs downstream generation.

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

#92
post #42
post #5

Earlier quoted context omitted.

> ended up being a million lines of code This almost reeks of "I've never cleaned up our code base because there is too much code, and didn't even bother having agents/LLM cleaning them up". You almost never need a million lines of code - this includes your software, infra, testing and operational tools. You didn't ship the linux kernel in 3 weeks and you know it. The code is already speghetti and it achieve the basi…

They directly address routine code cleanup and regularly paying down technical debt near the end of the article.

I stand corrected, but the LOC being advertised still make me doubt the efficacy of their process.

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

#93

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…

Individual voices aren't strong enough to drown the marketing machine.

Artists and writers are unionized, why they have a more powerful collective voice.

Second, there are enough peole for which their jobs are very well paid and too cozy to dare to rock the boat.

The economy and job market isn't so hot either at the moment for people to quickly be able to jump ship.

Can you even be sure that you find a tech company that isn't jumping head first onto the AI hype train? Even politicians can't have enough of AI in their mouth.

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

#95
post #55

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…

It's the other way around, unfortunately. The senior engineers will still be useful for architecture and infrastructure considerations, as well as guiding the agents. It's the junior engineers that get nailed, because there's little incentive to hire one when a LLM does a better job immediately and costs less.

That's true now. But in the world of this article, it's also the senior engineers that get nailed. In the world of this article, all code is like what machine code or bytecode is now - it's designed to be used by the machine, not the human, because the expectation is that humans will rarely, if ever, touch it.

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

#96

This might work only if you have “infinite” compute and infinite tokens. As someone that used the $20 plan, this pure agentic approach is impossible to do because I’d hit the limit fast and I would end up with less outcome. What I found that work incredibly well was to provide a human written code as reference, and ask it to extend it. So I scaffold the entire thing, architect it, write few samples code (controllers,…

You are not going anywhere with $20 plan

Upgrade to $200/month and you should see more usage but even for a hardcore user for me, one can never have enough.

I'm still very jealous of those guys that got 200x usage simply by RSVP'ing to openai party

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

#97
post #73
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"?…

I also can't help but notice they didn't mention how many tokens were burned, or how much that translates to in terms of cost over the 5 months at enterprise AI prices. I'm going to guess this wasn't a cheap demo.

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

#98

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…

engineers undervalue their own process

artists overvalue their own outputs

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

#99
post #80
post #59

Earlier quoted context omitted.

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.

This is a description of Alan Kay’s STEPS project:

https://worrydream.com/refs/Kay_2007_-_STEPS_2007_Progress_R...

This is the final report:

https://tinlizzie.org/VPRIPapers/tr2012001_steps.pdf

Post reply on HN