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

451–460 of 1001 posts

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

#451

Post by lillutoo »

YesBox wrote: post #264
simonw wrote: post #248

Earlier quoted context omitted.

It could be that the people who are focused on building monetizable products with LLMs don't feel the need to share what they are doing - they're too busy quietly getting on with building and marketing their products. Sharing how you're using these tools is quite a lot of work!

Agreed! LLMs are a force multiplier for real products too. They're going to augment people who are willing to do the real work. But, Im also wondering if LLMs are going to create a new generation of software dev "brain rot" (to use the colloquial term), similar to short form videos. I should mention in the gamedev world, it's quite common share because sharing is marketing, hence my perspective.

I feel weird when I read comments that have words like "force mulitplier". This sounds like an LLM comment. But you probably are a real person. So are you just becoming more like an LLM because you interact with it so much, or did you always talk like this and LLMs are just replicating that behavior?

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

#452

Post by techblueberry »

ChrisbyMe wrote: post #6

Mm this is my experience as well, but I'm not particularly worried about software engineering a whole. If anything this example shows that these cli tools give regular devs much higher leverage. There's a lot of software labor that is like, go to the lowest cost country, hire some mediocre people there and then hire some US guy to manage them. That's the biggest target of this stuff, because now that US guy can just…

The question I've been wondering is..

I think for a while people have been talking about the fact that as all development tools have gotten better - the idea that a developer is a person who turns requirements into code is dead. You have to be able to operate at a higher level, be able to do some level of work to also develop requirements, work to figure out how to make two pieces of software work together, etc.

But the point is Obviously at an extreme end 1 CTO can't run google and probably not say 1 PM or Engineer per product, but what is the mental load people can now take on. Google may start hiring less engineers (or maybe what happens is it becomes more cuthroat, hire the same number of engineers but keep them much more shortly, brutal up or out.

But essentially we're talking about complexity and mental load - And so maybe it's essentially the same number of teams because teams exist because they're the right size, but teams are a lot smaller.

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

#453

Post by jedberg »

I had an app I wanted for over a decade. I even wrote a prototype 10 years ago. It was fine but wasn't good enough to use, so I didn't use it.

This weekend I explained to Claude what I wanted the app to do, and then gave it the crappy code I wrote 10 years ago as a starting point.

It made the app exactly as I described it the first time. From there, now that I had a working app that I liked, I iterated a few times to add new features. Only once did it not get it correct, and I had to tell it what I thought the problem was (that it made the viewport too small). And after that it was working again.

I did in 30 minutes with Claude what I had try to do in a few hours previously.

Where it got stuck however was when I asked it to convert it to a screensaver for the Mac. It just had no idea what to do. But that was Claude on the web, not Claude Code. I'm going to try it with CC and see if I can get it.

I also did the same thing with a Chrome plugin for Gmail. Something I've wanted for nearly 20 years, and could never figure out how to do (basically sort by sender). I got Opus 4.5 to make me a plugin to do it and it only took a few iterations.

I look forward to finally getting all those small apps and plugins I've wanted forever.

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

#454

Post by Bridged7756 »

whynotminot wrote: post #416
multisport wrote: post #320

What bothers me about posts like this is: mid-level engineers are not tasked with atomic, greenfield projects. If all an engineer did all day was build apps from scratch, with no expectation that others may come along and extend, build on top of, or depend on, then sure, Opus 4.5 could replace them. The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily unde…

> The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily understood way, in a way that's easily extensible. You’re talking like in the year 2026 we’re still writing code for future humans to understand and improve. I fear we are not doing that. Right now, Opus 4.5 is writing code that later Opus 5.0 will refactor and extend. And so on.

Opus 4.5 is writing code that Opus 5.0 will refactor and extend. And Opus 5.5 will take that code and rewrite it in C from the ground up. And Opus 6.0 will take that code and make it assembly. And Opus 7.0 will design its own CPU. And Opus 8.0 will make a factory for its own CPUs. And Opus 9.0 will populate mars. And Opus 10.0 will be able to achieve AGI. And Opus 11.0 will find God. And Opus 12.0 will make us a time machine. And so on.

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

#455

Post by aeternum »

maplethorpe wrote: post #421
whynotminot wrote: post #416

Earlier quoted context omitted.

> The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily understood way, in a way that's easily extensible. You’re talking like in the year 2026 we’re still writing code for future humans to understand and improve. I fear we are not doing that. Right now, Opus 4.5 is writing code that later Opus 5.0 will refactor and extend. And so on.

Yeah I think it's a mistake to focus on writing "readable" or even "maintainable" code. We need to let go of these aging paradigms and be open to adopting a new one.

In my experience, LLMs perform significantly better on readable maintainable code.

It's what they were trained on after-all.

However what they produce is often highly readable but not very maintainable due to the verbosity and obvious comments. This seems to pollute codebases over time and you see AI coding efficiency slowly decline.

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

#456

Post by oldnewthing »

Claude Code is very good; good enough that I upgraded to the Max plan this week. However, it has a long way to go. It's great at one-shotting (with iterations) most ideas. However, it doesn't do as well when the task is complicated in an existing codebase. This weekend I migrated the backend for the SaaS I am building from Python to .NET Core. It did the migration but completely missed the conventions that the frontend was using to call the backend. While the converion itself went OK, every user journey was broken. I am still manually testing every code path and feeding in the errors to get Claude to fix it. My instructions were fairly comprehensive but Claude still missed most of it. My fault that I didn't generate tests first, but after this migration that's my first task.

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

#458

Post by lelandfe »

klaussilveira wrote: post #325
OldGreenYodaGPT wrote: post #33

Most software engineers are seriously sleeping on how good LLM agents are right now, especially something like Claude Code. Once you’ve got Claude Code set up, you can point it at your codebase, have it learn your conventions, pull in best practices, and refine everything until it’s basically operating like a super-powered teammate. The real unlock is building a solid set of reusable “skills” plus a few agents for th…

I made a similar comment on a different thread, but I think it also fits here: I think the disconnect between engineers is due to their own context. If you work with frontend applications, specially React/React Native/HTML/Mobile, your experience with LLMs is completely different than the experience of someone working with OpenGL, io_uring, libev and other lower level stuff. Sure, Opus 4.5 can one shot Windows utilit…

I'm a quite senior frontend using React and even I see Sonnet 4.5 struggle with basic things. Today it wrote my Zod validation incorrectly, mixing up versions, then just decided it wasn't working and attempted to replace the entire thing with a different library.

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

#459

Post by throw234234234 »

ncruces wrote: post #210
structural wrote: post #71

Earlier quoted context omitted.

Yes, but my junior coworkers also don't reliably do edge case testing for user errors either unless specifically tasked to do so, likely with a checklist of specific kinds of user errors they need to check for. And it turns out the quality of output you get from both the humans and the models is highly correlated with the quality of the specification you write before you start coding. Letting a model run amok within…

How will those juniors ever grow up to be seniors now?

My theory is that this (juniors unable to get in) is generally how industries/jobs die and phase out in a healthy manner that causes the least pain to its workers. I've seen this happen to a number of other industries with people I know and when it phases out this way its generally less disruptive to people.

The seniors who have less leeway to change course (its harder as you get older in general, large sunk costs, etc) maintain their positions and the disruption occurs at the usual "retirement rate" meaning the industry shrinks a bit each year. They don't get much with pay rises, etc but normally they have some buffer from earlier times so are willing to wear being in a dying field. Staff aren't replaced but on the whole they still have marginal long term value (e.g. domain knowledge on the job that keeps them somewhat respected there or "that guy was around when they had to do that; show respect" kind of thing).

The juniors move to other industries where the price signal shows value and strong demand remains (e.g. locally for me that's trades but YMMV). They don't have the sunk cost and have time on their side to pivot.

If done right the disruption to people's lives can be small and most of the gains of the tech can still come out. My fear is the AI wave will happen fast but only in certain domains (the worst case for SWE's) meaning the adjustment will be hard hitting without appropriate support mechanisms (i.e. most of society doesn't feel it so they don't care). On average individual people aren't that adaptable, but over generations society is.

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

#460

Post by noodletheworld »

multisport wrote: post #320

What bothers me about posts like this is: mid-level engineers are not tasked with atomic, greenfield projects. If all an engineer did all day was build apps from scratch, with no expectation that others may come along and extend, build on top of, or depend on, then sure, Opus 4.5 could replace them. The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily unde…

It might scale.

So far, Im not convinced, but lets take a look at fundmentally whats happening and why humans > agents > LLMs.

At its heart, programming is a constraint satisfaction problem.

The more constraints (requirements, syntax, standards, etc) you have, the harder it is to solve them all simultaneously.

New projects with few contributors have fewer constraints.

The process of “any change” is therefore simpler.

Now, undeniably

1) agents have improved the ability to solve constraints by iterating; eg. Generate, test, modify, etc. over raw LLm output.

2) There is an upper bound (context size, model capability) to solve simultaneous constraints.

3) Most people have a better ability to do this than agents (including claude code using opus 4.5).

So, if youre seeing good results from agents, you probably have a smaller set of constraints than other people.

Similarly, if youre getting bad results, you can probably improve them by relaxing some of the constraints (consistent ui, number of contributors, requirements, standards, security requirements, split code into well defined packages).

This will make both agents and humans more productive.

The open question is: will models continue to improve enough to approach or exceed human level ability in this?

Are humans willing to relax the constraints enough for it to be plausible?

I would say currently people clambering about the end of human developers are cluelessly deceived by the “appearance of complexity” which does not match the “reality of constraints” in larger applications.

Opus 4.5 cannot do the work of a human on code bases Ive worked on. Hell, talented humans struggle to work on some of them.

…but that doesnt mean it doesnt work.

Just that, right now, the constraint set it can solve is not large enough to be useful in those situations.

…and increasingly we see low quality software where people care only about speed of delivery; again, lowering the bar in terms of requirements.

So… you know. Watch this space. Im not counting on having a dev job in 10 years. If I do, it might be making a pile of barely working garbage.

…but I have one now, and anyone who thinks that this year people will be largely replaced by AI is probably poorly informed and has misunderstood the capabilities on these models.

Theres only so low you can go in terms of quality.

Post reply on HN