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

Lessons for Agentic Coding: What should we do when code is cheap?

dbreunig.com

Post reply on HN
Print view View original

251–260 of 260 posts

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#251

Post by tracker1 »

pryelluw wrote: post #233
tracker1 wrote: post #231

Earlier quoted context omitted.

I said 2-4x on value.. which would be development of the feature itself in terms of direct output... not even considering setting up test harnesses and doing more adventurous changes that would take me a lot longer to do.

I was referring to the sentence: I'm getting about 2-4x the value and about 10x the output... the "value" is features landing in code and the difference to the 10x is documentation and testing. What does the 10x imply? And are you saying that you are outputting 2-4x as in: value * value * value * value in the case of 4x? That seems rather high.

10x is 10x the output I could have done by myself. 2-4x is between 2 and 4 times the output I could have done myself. I distinguish "value" as that which is strictly a concern for the users/stakeholders, who themselves don't necessarily consider robust testing harnesses or internal-only documentation a value.

I said 4x as a cap for value, I don't know how you interpret that as x^4 ...

4x is 4 * x, x^4 would be your xxx*x ...

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#252

Post by LEDThereBeLight »

lionkor wrote: post #144
peab wrote: post #122

Earlier quoted context omitted.

"Producing code has always been low cost" Relative to what? I don't understand people dismissing the massive decrease in both cost of producing code and the speed of producing code. Before AI, people running businesses had similar issued as people have with AI now, but the costs were much greater. They could hire someone to write them a prototype for their idea, but it would cost them on the order of 1000s of dollars…

I'm not dismissing it, I'm saying it's never been the bottleneck. Like you said, the feedback loop is A bottleneck, so is figuring out all the nasty things that nobody on HN seems to have heard of before, like "what are the requirements", "which tradeoffs can we make to get this done in time", "what is the architecture for this", and building it in such a way that you can guarantee that it won't fall apart in 20 year…

Code has always been a bottleneck for any product which involves software.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#253

Post by HarHarVeryFunny »

svantana wrote: post #250
HarHarVeryFunny wrote: post #126

Earlier quoted context omitted.

A harness like Claude Code does not turn an LLM into a software developer. If that was the case companies could just have their project managers managing Claude Code instead of developers, and they would immediately realize that using Claude Code to develop software is just as complex and geeky as it ever was - nothing changed in that regard. A harness and a bunch of skills is just the new "think step by step" prompt…

If you prefer staying in denial, be my guest. But I've seen multiple instances of fully functioning software created by people who don't even know what code is. Maybe these creators are now developers, in a sense. But no SWE's were needed.

Sure, and I could buy a model rocket engine, strap it to a stick and launch it hundreds of feet into the air. Would that make me a rocket scientist? Next step Mars?

If you don't appreciate the difference between what an LLM or a coding agent can do, vs what a human can do, then I can't help you.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#254

Post by shakabrah »

spicyusername wrote: post #74

A lot of people down on AI in this thread, but I'm watching the industry slip over the line of trust with these latest frontier models. GPT 5.5 is the first model good enough for me to just let rip. Every jira ticket I see now has acceptance criteria, reproduction steps, and detailed information about why the ticket exists. Every commit message now matches the repo style, and has detailed information about what's con…

5.5 came out two weeks ago. Maybe wait a bit before declaring victory?

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#255

Post by Synthetic7346 »

LtWorf wrote: post #229
ikrenji wrote: post #193

Earlier quoted context omitted.

there are workplaces that trust their employees to do the right thing to higher and lesser level. places that empower the employees the most will see the highest gains from LLMs

After having a job, I do not trust my coworkers. I might trust a few selected ones, but I certainly do not trust all of them.

Just fire them and replace them with agents /s

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#258

Post by svantana »

HarHarVeryFunny wrote: post #253
svantana wrote: post #250

Earlier quoted context omitted.

If you prefer staying in denial, be my guest. But I've seen multiple instances of fully functioning software created by people who don't even know what code is. Maybe these creators are now developers, in a sense. But no SWE's were needed.

Sure, and I could buy a model rocket engine, strap it to a stick and launch it hundreds of feet into the air. Would that make me a rocket scientist? Next step Mars? If you don't appreciate the difference between what an LLM or a coding agent can do, vs what a human can do, then I can't help you.

Most of the time, a hundred feet is enough. 30 years ago, if you needed an aerial photo shot, you needed a helicopter pilot. Today, you just don't.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#259

Post by philwelch »

skydhash wrote: post #195
philwelch wrote: post #171

Earlier quoted context omitted.

As I recall, “No Silver Bullet” fundamentally rested on the assumption that the subroutine was the last word in abstractions to make programming more efficient, which probably wasn’t even defensible at the time because Lisp had already been invented, and is even less defensible after the past several decades of programming language research. Brooks was still onto something when it came to irreducible complexity, but…

The sibling comment to yours (by rafterydj) makes a good point that the surgical team is necessary, but we have eliminated the positions and put the roles on the same person. It’s like the writer being the subject expert, the reviewer, the editor,… which we all knows leads to mediocre work.

No, I think AI actually gets us closer to the surgical team than before. The purpose of the surgical team is to maximize the value of a single individual contributor. Before AI, the only way to do that was to surround him with assistants, which is inherently hierarchical and never really caught on probably for that reason. The value wasn't in the surgical team being entirely human, it was in optimizing for the surgeon's output by offloading tasks that are less valuable for him to perform. Offloading those tasks to AI works just as well without offending our egalitarian sensibilities.

Re: Lessons for Agentic Coding: What should we do when code is cheap?

#260

Post by sunilkumarai »

spicyusername wrote: post #74

A lot of people down on AI in this thread, but I'm watching the industry slip over the line of trust with these latest frontier models. GPT 5.5 is the first model good enough for me to just let rip. Every jira ticket I see now has acceptance criteria, reproduction steps, and detailed information about why the ticket exists. Every commit message now matches the repo style, and has detailed information about what's con…

[flagged]
Post reply on HN