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

Ask HN: Do you have any evidence that agentic coding works?

news.ycombinator.com

Post reply on HN
Print view View original

371–380 of 478 posts

Re: Ask HN: Do you have any evidence that agentic coding works?

#371

Post by ZitchDog »

defatigable wrote: post #205
marcus_holmes wrote: post #200

Earlier quoted context omitted.

This. I use it for coding in a Rails app when I'm not a Ruby expert. I can read the code, but writing it is painful, and so having the LLM write the code is beneficial. It's definitely faster than if I was writing the code, and probably produces better code than I would write. I've been a professional software developer for >30 years, and this is the biggest revolution I've seen in the industry. It is going to change…

Agreed. In the domains where I'm an expert, it's a nice productivity boost. In the domains where I'm not, it's transformative. As a complete aside from the question of productivity, these coding tools have reawakened a love of programming in me. I've been coding for long enough that the nitty gritty of everyday programming just feels like a slog - decrypting compiler errors, fixing type checking issues, factoring out…

> In the domains where I'm an expert, it's a nice productivity boost. In the domains where I'm not, it's transformative.

Is it possible that the code you are writing isn't good, but you don't know it because you're not an expert?

Re: Ask HN: Do you have any evidence that agentic coding works?

#372

Post by grayhatter »

ZitchDog wrote: post #370

I had the same question recently! So I did an experiment to see if I could create something of value using agentic coding. I made the worlds fastest and most accurate JSON Schema validator. https://github.com/sberan/tjs

Why do you say it's the fastest and most accurate? I don't see any raw stats, just AI generated readmes.

you also don't compare it to the top result on Google https://github.com/Stranger6667/jsonschema was that intentional?

Re: Ask HN: Do you have any evidence that agentic coding works?

#373

Post by ZitchDog »

I had the same question recently! So I did an experiment to see if I could create something of value using agentic coding.

I made the worlds fastest and most accurate JSON Schema parser.

https://github.com/sberan/tjs

But, nobody seems to care. The repo only has 18 stars and my Show HN post got no upvotes. I'm not sure what to take away from that.

Re: Ask HN: Do you have any evidence that agentic coding works?

#374

Post by spopejoy »

BrandoElFollito wrote: post #263
xsh6942 wrote: post #249

It really depends by what you mean by "it works". A retrospective of the last 6months. I've had great success coding infra (terraform). It at least 10x the generation of easily verifiable and tedious to write code. Results were audited to death as the client was highly regulated. Professional feature dev is hit and miss for sure, although getting better and better. We're nowhere near full agentic coding. However, by…

> I guess you get the most value out of it when you know exactly what you want. Oh yes. I am amateur-developping for 35 years and when I vibe code I let the basic, generic stuff happen and then tell the AI to refactor the way I want. It usually works. I had the same "too boring to code" approach and AI was a revelation. It takes off the typing but allows, when used correctly, for the creative part. I love this.

The OP question was about agentic utility specifically. I've also gotten great side-project utility from AI codegen without having to marry my project to CC or give up on looking at code by simply prompting when I need something from whatever LLM.

Nothing wrong with CC, but I keep hearing the same kind of app being built -- home automation, side-project CRUD.

What I'm deeply skeptical of is the ability for agentic to integrate with a team maintaining+shipping a critical offering. If you're using LLMs for one-off PRs, great but then agentic seems like a band aid for memory etc.

Meamwhile if you're full CC/agentic it seems like a team would get out of sync.

Re: Ask HN: Do you have any evidence that agentic coding works?

#375

Post by rahimnathwani »

egorfine wrote: post #267

I have tried full-on agentic coding twice in the last month. 1) I needed a tool to consolidate *.dylib on macOS into the app bundle. I wanted this tool to be in JS because of some additional minor logic which would be a hassle to implement in pure bash. 2) I needed a simple C wrapper to parallelize /usr/bin/codesign over cores. Split list of binaries in batches and run X parallel codesigns over a batch. Arguably, bot…

After you created a spec did you ask the Claude to break down the spec into epics and tasks?

I've found that helps a lot.

Re: Ask HN: Do you have any evidence that agentic coding works?

#376

Post by JeremyNT »

fhd2 wrote: post #191

Bear in mind that there is a lot of money riding on LLMs leading to cost savings, and development (seen as expensive and a common bottleneck) is a huge opportunity. There are paid (micro) influencer campaigns going on and what not. Also bear in mind that a lot of folks want to be seen as being on the bleeding edge, including famous people. They get money from people booking them for courses and consulting, buying the…

> This stuff is relatively new, I don't think anyone has truly figured out how to best approach LLM assisted development yet. A lot of folks are on it, usually not exactly following the scientific method. We'll get evidence eventually.

I try to think about other truly revolutionary things.

Was there evidence that GUIs would dramatically increase productivity / accessibility at first? I guess probably not. But the first time you used one, you would understand its value on some kind of intuitive level.

Having the ability to start OpenCode, give it an issue, add a little extra context, and have the issue completed without writing a single line of code?

The confidence of being able to dive into an unknown codebase and becoming productive immediately?

It's obvious there's something to this even if we can't quantify it yet. The wildly optimistic takes end with developers completely eliminated, but the wildly pessimistic ones - if clear eyed - should still acknowledge that this is a massive leap in capabilities and our field is changed forever.

Re: Ask HN: Do you have any evidence that agentic coding works?

#377

Post by spopejoy »

malloryerik wrote: post #333
resonious wrote: post #165

I think one fatal flaw is letting the agent build the app from scratch. I've had huge success with agents, but only on existing apps that were architected by humans and have established conventions and guardrails. Agents are really bad at architecture, but quite good at following suit. Other things that seem to contribute to success with agents are: - Static type systems (not tacked-on like Typescript) - A test suite…

I've found good results with Clojure and Elixir despite them being dynamic and niche.

Not really production level or agentic, but I've been impressed with LLMs for Haskell.

I think that while these langs are "niche" they still have quality web resources and codebases available for training.

I worry about new languages though. I guess maybe model training with synthetic data will become a requirement?

Re: Ask HN: Do you have any evidence that agentic coding works?

#378

Post by grayhatter »

JeremyNT wrote: post #376
fhd2 wrote: post #191

Bear in mind that there is a lot of money riding on LLMs leading to cost savings, and development (seen as expensive and a common bottleneck) is a huge opportunity. There are paid (micro) influencer campaigns going on and what not. Also bear in mind that a lot of folks want to be seen as being on the bleeding edge, including famous people. They get money from people booking them for courses and consulting, buying the…

> This stuff is relatively new, I don't think anyone has truly figured out how to best approach LLM assisted development yet. A lot of folks are on it, usually not exactly following the scientific method. We'll get evidence eventually. I try to think about other truly revolutionary things. Was there evidence that GUIs would dramatically increase productivity / accessibility at first? I guess probably not. But the fir…

> Having the ability to start OpenCode, give it an issue, add a little extra context, and have the issue completed without writing a single line of code?

Is this a good thing? I'm asking why you said it like this, I'm not asking you to defend anything. I'm genuinely curious about your rational/reasoning/context for why you used those words specifically?

I ask, because I wouldn't willingly phrase it like this. I enjoy writing code. The expression of the idea, while not even close to value I assign to fixing the thing, still has meaning.

e.g. I would happily share code my friend wrote that fixed something. But I wouldn't take and pride in it. Is that difference irrelevant to you, or do you still feel that sense of significance when an LLM emits the code for you?

> should still acknowledge that this is a massive leap in capabilities and our field is changed forever.

Equally, I don't think I have to agree with this. Our field is likely changed, arguably for the worse if the default IDE now requires a monthly rent payment. But I have only found examples of AI generating boiler plate. If it's not able to copy the code from some other existing source, it's unable to emit anything functional. I wouldn't agree that's a massive leap. Boilerplate has always been the least significant portion of code, no?

Re: Ask HN: Do you have any evidence that agentic coding works?

#380

Post by egorfine »

rahimnathwani wrote: post #375
egorfine wrote: post #267

I have tried full-on agentic coding twice in the last month. 1) I needed a tool to consolidate *.dylib on macOS into the app bundle. I wanted this tool to be in JS because of some additional minor logic which would be a hassle to implement in pure bash. 2) I needed a simple C wrapper to parallelize /usr/bin/codesign over cores. Split list of binaries in batches and run X parallel codesigns over a batch. Arguably, bot…

After you created a spec did you ask the Claude to break down the spec into epics and tasks? I've found that helps a lot.

I believe that's something it does automatically now.

In the past it did help a lot, but now it's the default behavior.

Post reply on HN