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

531–540 of 1001 posts

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

#531

Post by rcarmo »

IgorPartola wrote: post #254
rcarmo wrote: post #205

I had a similar set of experiences with GPT 5.x over the holiday break, across somewhat more disparate domains: https://taoofmac.com/space/notes/2025/12/31/1830 I hacked together a Swift tool to replace a Python automation I had, merged an ARM JIT engine into a 68k emulator, and even got a very decent start on a synth project I’ve been meaning to do for years. What has become immensely apparent to me is that even gpt…

The thing is that CLI utilities code is probably easier to write for an LLM than most other things. In my experience an LLM does best with backend and terminal things. Anything that resembles boilerplate is great. It does well refactoring unit tests, wrapping known code in a CLI, and does decent work with backend RESTful APIs. Where it fails utterly is things like HTML/CSS layout, JavaScript frontend code for SPAs, a…

Since one of my holiday projects was completely rebuilding the Node-RED dashboard in Preact, I have to challenge that a bit. How were you using the model?

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

#532

Post by imp0cat »

zmmmmm wrote: post #495
sfink wrote: post #350

Earlier quoted context omitted.

(I haven't used AI much, so feel free to ignore me.) This is one thing I've tried using it for, and I've found this to be very, very tricky. At first glance, it seems unbelievably good. The comments read well, they seem correct, and they even include some very non-obvious information. But almost every time I sit down and really think about a comment that includes any of that more complex analysis, I end up discarding…

My main experience is with anthropic models. I've had some encounters with inaccuracies but my general experience has been amazing. I've cloned completely foreign git repos, cranked up the tool and just said "I'm having this bug, give me an overview of how X and Y work" and it will create great high level conceptual outlines that mean I can drive straight in where without it I would spend a long time just flailing ar…

But have you actually thoroughly checked the documentation it generated? My experience suggests it can often be subtly wrong.

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

#533

Post by ipaddr »

sreekanth850 wrote: post #494
potamic wrote: post #477

Earlier quoted context omitted.

How did he not share code if you're working together?

yes, it was my mistake. I trusted him because he was my childhood friend and my cousin. He was a tech lead in CMMI Level 5 (serving fortune 500 firms) company at the time he joined with me. I had the trust that he will never ran away with the code and that trust is still there, also the entire feature, roadmap and vision was with me, so I thought code doesn't matter. It was a big learning for me.

Input your roadmap into an llm of your choosing and see if you can create that code.

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

#534

Post by qingcharles »

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…

I had Opus write a whole app for me in 30 seconds the other night. I use a very extensive AGENTS.md to guide AI in how I like my code chiseled. I've been happily running the app without looking at a line of it, but I was discussing the app with someone today, so I popped the code open to see what it looked like. Perfect. 10/10 in every way. I would not have written it that good. It came up with at least one idea I would not have thought of.

I'm very lucky that I rarely have to deal with other devs and I'm writing a lot of code from scratch using whatever is the latest version of the frameworks. I understand that gives me a lot of privileges others don't have.

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

#535

Post by Madmallard »

soulofmischief wrote: post #409
Madmallard wrote: post #406

Earlier quoted context omitted.

Unfortunately what likely will happen is that you miss tons of edge cases and certain implementations within the confines of your language will be basically impossible or horribly inefficient or ineffective and precisely the reason for it will be because you lack that expertise and relied on an LLM to make it up for you.

That's not how this works. Assume less about my level of expertise. By the end of a session, I understand the internals of what I'm implementing. What is shortened is the search space and research/prototyping intervals. If I didn't ultimately understand where I was going, projects like this hit a dead end very quickly, as mentioned in my caveats. These models are not yet ready for large-scale or mission-critical proj…

Are you making a DSL then? That would make more sense.

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

#536

Post by patates »

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…

You can look at my comment history to see the evidence to how hostile I was to agentic coding. Opus 4.5 completely changed my opinion.

This thing jumped into a giant JSF (yes, JSF) codebase and started fixing things with nearly zero guidance.

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

#537

Post by patates »

sksishbs wrote: post #359
fenwick67 wrote: post #336

Earlier quoted context omitted.

Another thing that gets me with projects like this, there are already many examples of image converters, minesweeper clones etc that you can just fork on GitHub, the value of the LLM here is largely just stripping the copyright off

It’s kind of funny - there’s another thread up where a dev claimed a 20-50x speed up. To their credit they posted videos and links to the repo of their work. And when you check the work, a large portion of it was hand rolling an ORM (via an LLM). Relatively solved problem that an LLM would excel at, but also not meaningfully moving the needle when you could use an existing library. And likely just creating more debt…

It seems to me these days, any code I want to write tries to solve problems that LLMs already excel at. Thankfully my job is perhaps just 10% about coding, and I hope people like you still have some coding tasks that cannot be easily solved by LLMs.

We should not exeggarate the capabilities of LLMs, sure, but let's also not play "don't look up".

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

#538

Post by deanc »

mcv wrote: post #133

Opus 4.5 ate through my Copilot quota last month, and it's already halfway through it for this month. I've used it a lot, for really complex code. And my conclusion is: it's still not as smart as a good human programmer. It frequently got stuck, went down wrong paths, ignored what I told it to do to do something wrong, or even repeat a previous mistake I had to correct. Yet in other ways, it's unbelievably good. I ca…

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.

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

#539

Post by zwnow »

melagonster wrote: post #501
fenwick67 wrote: post #336

Earlier quoted context omitted.

Another thing that gets me with projects like this, there are already many examples of image converters, minesweeper clones etc that you can just fork on GitHub, the value of the LLM here is largely just stripping the copyright off

- I cloned a project from GitHub and made some minor modifications. - I used AI-assisted programming to create a project. Even if the content is identical, or if the AI is smart enough to replicate the project by itself, the latter can be included on a CV.

I'd quickly trash your application if I see you just vibe coded some bullshit app. Developing is about working smart, and its not smart to ask AI to code stuff that already exists, its in fact wasteful.

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

#540

Post by jdthedisciple »

To those of you who use it: How much does Claude Code cost you a month on avg?

I only use VS Code with Copilot subscription ($10) and already get quite a lot out of it.

My experience is that Claude Code really drains your pocket extremely fast.

Post reply on HN