Live data from Hacker News

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

burkeholland.github.io

651–660 of 1001 posts

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

#651

Earlier quoted context omitted.

I use pay as you go for this very reason, so the limit is my pocket haha. It does make me conscious to keep it under $20 per month though.

You're overpaying by a factor of 4, easily. I use `ccusage`'s statusline in claude code, and even with my personal $20/mo subscription I don't think there's been a single month where I didn't touch ~$80 of usage. I wasn't even abusing it as bad as some people tend to.

How do you manage that? /ccusage and --ccusage no longer work for me, I can only see the usage bars in /usage

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

#652

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.

In my experience, using LLMs to code encouraged me to write better documentation, because I can get better results when I feed the documentation to the LLM. Also, I've noticed failure modes in LLM coding agents when there is less clarity and more complexity in abstractions or APIs. It's actually made me consider simplifying APIs so that the LLMs can handle them better. Though I agree that in specific cases what's hel…

I've also noticed that going off the rails. At the start of a session, they're pretty sharp and focused, but the longer the session lasts, the more confused they get. At some point they start hallucinating bullshit that they wouldn't have earlier in the session.

It's a vital skill to recognise when that happens and start a new session.

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

#653
post #538

Earlier quoted context omitted.

People are completely missing the points about agentic development. The model is obviously a huge factor in the quality of the output, but the real magic lies in how the tools are managing and injecting context in to them, as well as the tooling. I switched from Copilot to Cursor at the end of 2025, and it was absolute night and day in terms of how the agents behaved.

Interesting you have this opinion yet you're using Cursor instead of Claude Code. By the same logic, you should get even better results directly using Anthropic's wrapper for their own model.

My employer doesn't allow for Claude Code yet. I'm fully aware from speaking to other peers, that they are getting even better performance out of Claude Code.

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

#654
post #517

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…

> 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. Why do they need to be replaced? Programmers are in the perfect place to use AI coding tools productively. It makes them more valuable.

Because we’re expensive and companies would love to get rid of us

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

#655

Earlier quoted context omitted.

https://www.anthropic.com/research/how-ai-is-transforming-wo... see "How much work can be fully delegated to Claude?": "Although engineers use Claude frequently, more than half said they can “fully delegate” only between 0-20% of their work to Claude" There won't be anything like you're asking for, even the vendors themselves (they'll be the most positive and most enthousiastic about using it) can't do this with them…

I'm not asking for it, i'm asking to stop bulshitting about ai

My point is that you can ignore every article about ai being super good as long as you see the vendor research (that you read once a year or less) is still the same. It saves everyone a lot of frustration. As for why it keeps appearing here, people like being excited. It's not about the truth, so asking for it is missing the point.

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

#656

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…

Yeah, all of those applications he shows do not really expose any complex business logic.

With all the due respect: a file converter for windows is glueing few windows APIs with the relevant codec.

Now, good luck working on a complex warehouse management application where you need extremely complex logic to sort the order of picking, assembling, packing on an infinite number of variables: weight, amazon prime priority, distribution centers, number and type of carts available, number and type of assembly stations available, different delivery systems and requirements for different delivery operators (such as GLE, DHL, etc) that has to work with N customers all requiring slightly different capabilities and flows, all having different printers and operations, etc, etc. And I ain't even scratching the surface of the business logic complexity (not even mentioning functional requirements) to avoid boring the reader.

Mind you, AI is still tremendously useful in the analysis phase, and can sort of help in some steps of the implementation one, but the number of times you can avoid looking thoroughly at the code for any minor issue or discrepancy is absolutely close to 0.

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

#657

I've been on a small adventure of posting more actively on HN since the release of Gemini 3, trying to stir debate around the more “societal” aspects of what's going on with AI. Regardless of how much you value Cloud Code technically, there is no denying that it has/will have huge impact. If technology knowledge and development are commoditised and distributed via subscription, huge societal changes are going to happ…

I don't know, I'm a software engineer and I couldn't care less.

It will have impact on me in the long run, sure, it will transform my job, sure, but I'm confident my skills are engineering-related, not coding-related.

I mean, even if it forces me out of the job entirely, so be it, I can't really do anything if the status quo changes, only adapt.

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

#658

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 was expecting a showcase to showcase what you've done with it, not just another person's attempt at instructing an AI to follow instructions.

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

#659
People should finally understand that LLMs are a lossy database of PAST knowledge. Yes, if you throw a task at it that has been done tons of times before, it works. Which is not a surprise, because it takes minutes to Google and index multiple full implementations of "Tool that allows you to right-click on an image to convert it". Without LLM you could do the same: Just copy&paste the implementation of that from Microsoft Powertoys, for example.

What LLMs will NOT do however, is write or invent SOMETHING KNEW.

And parts of our industry still are about that: Writing Software that has NOT been written before.

If you hire junior developers to re-invent the wheels: Sure, you do not need them anymore.

But sooner or later you will run out of people who know how to invent NEW things.

So: This is one more of those posts that completely miss the point. "Oh wow, if I look up on Wikipedia how to make pancakes I suddenly can make and have pancakes!!!1". That always was possible. Yes, you now can even get an LLM to create you a pancake-machine. Great.

Most of the artists and designers I am friends with have lost their jobs by now. In a couple of years you will notice the LLMs no longer have new styles to copy from.

I am all for the "remix culture". But don't claim to be an original artist, if you are just doing a remix. And LLM source code output are remixes, not original art.

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

#660

A couple weeks ago I had Opus 4.5 go over my project and improve anything it could find. It "worked" but the architecture decisions it made were baffling, and had many, many bugs. I had to rewrite half of the code. I'm not an AI hater, I love AI for tests, finding bugs, and small chores. Opus is great for specific, targeted tasks. But don't ask it to do any general architecture, because you'll be soon to regret it.

>> A couple weeks ago I had Opus 4.5 go over my project and improve anything it could find. It "worked" but the architecture decisions it made were baffling, and had many, many bugs. So you gave it an poorly defined task, and it failed?

Exactly, imagine if someone gave you a 100k LOC project and said improve anything you can.
Post reply on HN