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

Opus 4.5 is not the normal AI agent experience that I have had thus far

burkeholland.github.io

Post reply on HN
Print view View original

841–850 of 1001 posts

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#841

Post by alternatex »

enraged_camel wrote: post #760
danfritz wrote: post #733

Every time I see a post like this on HN I try again and every time I come to the same conclusion. I have never see one agent managing to pull something off that I could instantly ship. It still ends up being very junior code. I just tried again and ask Opus to add custom video controls around ReactPlayer. I started in Plan mode which looked overal good (used our styling libs, existing components, icons and so on). I…

I find anecdotes like yours bewildering, because I've been using Opus with Vue.js and it crushes everything I throw at it. The amount of corrections I need to make tend to be minimal, and mostly cosmetic. The tasks I give it are not trivial either. Just yesterday I had it create a full-blown WYSIWYG editor for authoring the content we serve through our app. This is something that would have taken me two weeks, give o…

Created a WYSIWYG editor or copied it off the internet like your average junior would, bugs included?

If that editor is very complicated (as they usually are) it makes sense to just opt for a library. If it's simple then AI is not required and would only reduce familiarity with how it works. The third option is what you did and I feel like it's the option with the lowest probability of ending up with a quality solution.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#842

Post by broken_ceiling »

hollowturtle wrote: post #836
broken_ceiling wrote: post #795

Earlier quoted context omitted.

This argument falls a little flat when you consider how much software may or may not be written inside one's own personal work flow, or to scale that up, inside a small business. The idea that a small business doing >1mil revenue can now hire a dev or two, and build out a fairly functional domain-driven system should not be understated. The democratization of software, and the lowering of the barriers to entry to bas…

Your argument falls a little flat considering that you mention "hire a dev or two" while the whole narrative is "we don't need software engineers anymore" and Anthropic alone declares that "Although engineers use Claude frequently, more than half said they can “fully delegate” only between 0-20% of their work to Claude" https://www.anthropic.com/research/how-ai-is-transforming-wo...

When was I arguing about job displacement or the replacing of engineers? You are projecting hard, and reaching. If anything, I am in the camp that accessibility to custom tooling equals a net positive of devs down the line. In the short term, it may be a bumpy road as the tools progress (even if incrementally), but my long term take is that you may see engineering teams blossom in smaller market operations.

When it comes to objectivity, people with your line of thinking is what I try to avoid, as it is clear you feel threatened by the progress of coding tools. That link doesn't change much about what I said, or for that matter, what you said. You were commenting on the lack of a killer app, and I just said it may be diffusing slowly in different ways.

You are fixating on the "whole narrative" because you feel threatened - rightfully so, but again, that type of hyperbole doesn't belong in a constructive and grounded conversation about the impact AI may or may not have.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#843

Post by hollandburke »

Author of the post here.

I appreciate the spirited debate and I agree with most of it - on both sides. It's a strange place to be where I think both arguments for and against this case make perfect sense. All I have to go on then is my personal experience, which is the only objective thing I've got. This entire profession feels stochastic these days.

A few points of clarification...

1. I don't speak for anyone but myself. I'm wrong at least half the time so you've been warned.

2. I didn't use any fancy workflows to build these things. Just used dictation to talk to GitHub Copilot in VS Code. There is a custom agent prompt toward the end of the post I used, but it's mostly to coerce Opus 4.5 into using subagents and context7 - the only MCP I used. There is no plan, implement - nothing like that. On occasion I would have it generate a plan or summary, but no fancy prompt needed to do that - just ask for it. The agent harness in VS Code for Opus 4.5 is remarkably good.

3. When I say AI is going to replace developers, I mean that in the sense that it will do what we are doing now. It already is for me. That said, I think there's a strong case that we will have more devs - not less. Think about it - if anyone with solid systems knowledge can build anything, the only way you can ship more differentiating features than me is to build more of them. That is going to take more people, not more agents. Agents can only scale as far as the humans who manage them.

New account because now you know who I am :)

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#845

Post by mossTechnician »

weitendorf wrote: post #808
flumpcakes wrote: post #787

Earlier quoted context omitted.

> It’s a bit strange how anecdotes have become acceptable fuel for 1000 comment technical debates. It's a very subjective topic. Some people claim it increases their productivity 100x. Some think it is not fit for purpose. Some think it is dangerous. Some think it's unethical. Weirdly those could all be true at the same time, and where you land on this is purely a matter of importance to the user. > Yet, I’d love to…

How many 1+ hour videos of someone building with AI tools have you sought out and watched? Those definitely exist, it sounds like you didn't go seeking them out or watch them because even with 7 less hours you'd better understand where they add value enough to believe they can help with challenging projects. So why should anybody produce an 8 hour video for you when you wouldn't watch it? Let's be real. You would not…

It could be really beneficial for Anthropic to showcase how they use their own product; since they're developers already, they're probably dogfooding their product, and the effort required should be minimal.

- A lot of skeptics have complained that AI companies aren't specific about how they use their products, and this would be a great example of specificity.

- It could serve as a tutorial for people who are unfamiliar with coding agents.

- The video might not convince people who have already made up their minds, but at least you could point to it as a primary source of information.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#846

Post by swat535 »

Ericson2314 wrote: post #437
FloorEgg wrote: post #333

Earlier quoted context omitted.

There are two types of right/wrong ways to build: the context specific right/wrong way to build something and an overly generalized engineer specific right/wrong way to build things. I've worked on teams where multiple engineers argued about the "right" way to build something. I remember thinking that they had biases based on past experiences and assumptions about what mattered. It usually took an outsider to proacti…

I know what you are talking about, but there is more to life than just product-market fit. Hardly any of us are working on Postgres, Photoshop, blender, etc. but it's not just cope to wish we were. It's good to think about the needs to business and the needs of society separately. Yes, the thing needs users, or no one is benefiting. But it also needs to do good for those users, and ultimately, at the highest caliber,…

Users will not care about the quality of your code, or the backed architecture, or your perfectly strongly typed language.

They only care about their problems and treat their computers like an appliance. They don't care if it takes 10 seconds or 20 seconds.

They don't even care if it has ads, popups, and junk. They are used to bloatware and will gladly open their wallets if the tool is helping them get by.

It's an unfortunately reality but there it is, software is about money and solving problems. Unless you are working on a mission critical system that affects people's health or financial data, none of those matter much.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#847

Post by scotty79 »

UncleMeat wrote: post #200
ac29 wrote: post #125

Earlier quoted context omitted.

> What do you mean by "have it learn your conventions"? I'll give you an example: I use ruff to format my python code, which has an opinionated way of formatting certain things. After an initial formatting, Opus 4.5, without prompting, will write code in this same style so that the ruff formatter almost never has anything to do on new commits. Sonnet 4.5 is actually pretty good at this too.

Isn't this a meaningless example? Formatters already exist. Generating code that doesn't need to be formatted is exactly the same as generating code and then formatting it. I care about the norms in my codebase that can't be automatically enforced by machine. How is state managed? How are end-to-end tests written to minimize change detectors? When is it appropriate to log something?

Memes write themselves.

"AI has X"

"We have X at home"

"X at home: x"

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#848

Post by kaydub »

g947o wrote: post #702
hollowturtle wrote: post #641

I'm tired of constantly debating the same thing again and again. Where are the products? Where is some great performing software all LLM/agent crafted? All I see is software bloatness and decline. Where is Discord that uses just a bunch of hundreds megs of ram? Where is unbloated faster Slack? Where is the Excel killer? Fast mobile apps? Browsers and the web platform improved? Why Cursor team don't use Cursor to get…

This deserves more upvotes. Even if there is a "fully vibe-coded" product that has real customers, the fact that it's vibe-coded means that others can do the same. Unless you have a secret LLM or some magical prompts that make the code better/more efficient than your competitions, your vibe coded product has no advantage over competition and no moat. What actually matters is everything else -- user experience (which…

I'm not sure what point you're making here. Tech is rarely the moat, you even get to that point at the end of your post. The "vibe coding" advantage is faster time to market, faster iterations, etc. These things will help you get that user experience, integrations, etc.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#849

Post by weitendorf »

g947o wrote: post #702
hollowturtle wrote: post #641

I'm tired of constantly debating the same thing again and again. Where are the products? Where is some great performing software all LLM/agent crafted? All I see is software bloatness and decline. Where is Discord that uses just a bunch of hundreds megs of ram? Where is unbloated faster Slack? Where is the Excel killer? Fast mobile apps? Browsers and the web platform improved? Why Cursor team don't use Cursor to get…

This deserves more upvotes. Even if there is a "fully vibe-coded" product that has real customers, the fact that it's vibe-coded means that others can do the same. Unless you have a secret LLM or some magical prompts that make the code better/more efficient than your competitions, your vibe coded product has no advantage over competition and no moat. What actually matters is everything else -- user experience (which…

> Even if there is a "fully vibe-coded" product that has real customers, the fact that it's vibe-coded means that others can do the same.

I think you are strawmanning what "vibe coders" do when they build stuff. It's not simple one-shot generation of eg twitter clones, it's really just iterative product development through an inconsistently capable/spotty LLM developer. It's not really that different from a product manager hiring some cheap developer and feeding them tasks/feature requests. By the way, competitors can hire those and chip away at your moat too!

> Unless you have a secret LLM or some magical prompts that make the code better/more efficient than your competitions, your vibe coded product has no advantage over competition and no moat

This is just not true, and you kind of make my point in the next sentence: many companies competitive advantages come from distribution, trust, integration, regulatory, marketing/sales, network effects. But also, vibe coding is not really about prompts so much as it is product iteration. Anybody product can be copied already, yet people still make way more new products than direct product clones anyway, because it's usually more valuable to go to market with stronger, more focused, or more specialized/differentiated software than a copy.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#850

Post by andai »

weitendorf wrote: post #808
flumpcakes wrote: post #787

Earlier quoted context omitted.

> It’s a bit strange how anecdotes have become acceptable fuel for 1000 comment technical debates. It's a very subjective topic. Some people claim it increases their productivity 100x. Some think it is not fit for purpose. Some think it is dangerous. Some think it's unethical. Weirdly those could all be true at the same time, and where you land on this is purely a matter of importance to the user. > Yet, I’d love to…

How many 1+ hour videos of someone building with AI tools have you sought out and watched? Those definitely exist, it sounds like you didn't go seeking them out or watch them because even with 7 less hours you'd better understand where they add value enough to believe they can help with challenging projects. So why should anybody produce an 8 hour video for you when you wouldn't watch it? Let's be real. You would not…

The honest answer is that I would probably ask AI to analyze the video for me, and that it would probably do a pretty good job.
Post reply on HN