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

431–440 of 478 posts

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

#431

Post by OccamsMirror »

aprdm wrote: post #427
whattheheckheck wrote: post #424

Earlier quoted context omitted.

Because they are pitching to replace 50% of white collar jobs... Doesn't seem like its that necessary to run marketing campaigns if that's the case... people would just do it if it's possible

Do you think that won't happen ? As a very silly example, my father in law has a school in Mexico and he is now using chatgtp to generate all of their visual materials that they used to pay someone to do in the past. They also used to pay someone to take school pictures for the books to look professional, now they use AI to make it look good/professional. My father in law has no knowledge in technology, he uses chatg…

> People must be hiding under a rock if they don't think this will have big consequences to society

People are not paying much mind to these freelance style jobs. It absolutely will have an impact on society.

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

#432

Post by iwalton3 »

I'm still experimenting with it and finding out what works and what doesn't, but I have made some side projects with Claude including a web framework that doesn't require a build step/npm dependencies (great for my personal website so I don't have to depend on npm supply chain nightmares), a fully featured music player server, and also a tool that lets the agent review it's past conversations and update documentation based on patterns such as frequent mistakes, re-explored code, etc.

Web framework (includes basic component library, optional bundler/optimizer, tutorial/docs, e2e tests, and demos): https://github.com/iwalton3/vdx-web Music player web app (supports large music libraries, pwa offline sync, parametric eq, crossfade, crossfeed, semantic feature-based music search/radio, milkdrop integration, and other interesting features): https://github.com/iwalton3/mrepo-web Documentation update script (also allows exporting Claude conversations to markdown): https://github.com/iwalton3/cl-pprint

Regarding QC these are side projects so I validate them based on code review of key components, e2e testing, and manual testing where applicable. I find having the agent be able to check its work is the single biggest factor to reducing rework, but I make no promises about these projects being completely free of bugs.

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

#433

Post by agent3bood »

My latest attempt with the vibe coding used to have to directories, first one for specifications, which is a small markdown that has requirements and a UML diagram, the second directory is the actual code. I use AI to plan the requirements first, then a second agent to implement after the specification is complete and approved by me. So, I do check the requirements and specifications and architecture, but never check the code (almost)

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

#434

Post by vessenes »

CjHuber wrote: post #33
vessenes wrote: post #20

Yep, it works. Like anything getting the most out of these tools is its own (human) skill. With that in mind, a couple of comments - think of the coding agents as personalities with blind spots. A code review by all of them and a synthesis step is a good idea. In fact currently popular is the “rule of 5” which suggests you need the LLM to review five times, and to vary the level of review, e.g. bugs, architecture, st…

I still don't get what beads needs a daemon for, or a db. After a while of using 'bd --no-daemon --no-db' I was sick of it and switched to beans and my agents seem to be able to make use of it much better, on the one hand its directly editable by them as its just markdown, on the other hand the CLI still gives them structure and makes the thing queryable

Steve runs beads across like 100 coding environments simultaneously. So, you need some sort of coordination, whether that's your db or a daemon. Realistically with 100 simultaneous connections, I would probably reach for both myself. I haven't tried beans, thanks for the reference.

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

#435

Post by varshith17 »

"Agentic coding works" and "ship without review" are two different claims. The first is true for constrained tasks, the second is Silicon Valley brain rot. I use Claude Code daily for DevOps automation and data migrations. Every output gets reviewed. It saves me hours, not judgment.

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

#437

Post by st-msl »

The thread keeps circling back to memory. Agents don't learn.

Everyone's building the same workarounds. CLAUDE.md files. Handoff docs. Learnings folders. Developer logs. All manual. All single-user. All solving the same problem: how do I stop re-teaching the agent things it should already know?

What nobody seems to ask: what if the insight that helped me debug a PayPal API timeout yesterday could help every developer who hits that bug tomorrow?

Stack Overflow was multiplayer. A million developers contributing solutions that benefited everyone. We replaced it with a billion isolated sessions that benefit no one else.

The "junior developer that never grows" framing is right. But it's worse - it's a junior who forgets everything at 5pm and shows up tomorrow needing the same onboarding. And there's no way for your junior's hard-won knowledge to help anyone else's.

We're building Memco to work on this. Shared memory layer for agents. Not stored transcripts - abstracted insights. When one agent figures something out, every agent benefits.

Still early. Curious if others are thinking about this or have seen attempts at it.

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

#438

Post by cx42net »

st-msl wrote: post #437

The thread keeps circling back to memory. Agents don't learn. Everyone's building the same workarounds. CLAUDE.md files. Handoff docs. Learnings folders. Developer logs. All manual. All single-user. All solving the same problem: how do I stop re-teaching the agent things it should already know? What nobody seems to ask: what if the insight that helped me debug a PayPal API timeout yesterday could help every developer…

> "Stack Overflow was multiplayer. A million developers contributing solutions that benefited everyone. We replaced it with a billion isolated sessions that benefit no one else".

This.

(Thank you!)

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

#439

Post by malloryerik »

dysoco wrote: post #400
spopejoy wrote: post #377

Earlier quoted context omitted.

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?

> I worry about new languages though. I guess maybe model training with synthetic data will become a requirement? I read a (rather pessimistic) comment here yesterday claiming that the current generation of languages is most likely going to be the last, since the already existing corpus of code for training is going to trump any other possible feature the new language might introduce, and most of the code will be LLM…

I've wondered to myself here and there if new languages wouldn't be specifically written for LLM agentic coding, and what that might look like.
Post reply on HN