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

311–320 of 1001 posts

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

#311

Post by libraryofbabel »

ryandrake wrote: post #198
spaceman_2020 wrote: post #54

Earlier quoted context omitted.

I really think a lof of people tried AI coding earlier, got frustrated at the errors and gave up. That's where the rejection of all these doomer predictions comes from. And I get it. Coding with Claude Code really was prompting something, getting errors, and asking it to fix it. Which was still useful but I could see why a skilled coder adding a feature to a complex codebase would just give up Opus 4.5 really is at a…

This was me. I was a huge AI coding detractor on here for a while (you can check my comment history). But, in order to stay informed and not just be that grouchy curmudgeon all the time, I kept up with the models and regularly tried them out. Opus 4.5 is so much better than anything I've tried before, I'm ready to change my mind about AI assistance. I even gave -True Vibe Coding- a whirl. Yesterday, from a blank dire…

Thanks for posting this. It's a nice reminder that despite all the noise from hype-mongers and skeptics in the past few years, most of us here are just trying to figure this all out with an open mind and are ready to change our opinions when the facts change. And a lot of people in the industry that I respect on HN or elsewhere have changed their minds about this stuff in the last year, having previously been quite justifiably skeptical. We're not in 2023 anymore.

If you were someone saying at the start of 2025 "this is a flash in the pan and a bunch of hype, it's not going to fundamentally change how we write code", that was still a reasonable belief to hold back then. At the start of 2026 that position is basically untenable: it's just burying your head in the sand and wishing for AI to go away. If you're someone who still holds it you really really need to download Claude Code and set it to Opus and start trying it with an open mind: I don't know what else to tell you. So now the question has shifted from whether this is going to transform our profession (it is), to how exactly it's going to play out. I personally don't think we will be replacing human engineers anytime soon ("coders", maybe!), but I'm prepared to change my mind on that too if the facts change. We'll see.

I was a fellow mind-changer, although it was back around the first half of last year when Claude Code was good enough to do things for me in a mature codebase under supervision. It clearly still had a long way to go but it was at that tipping point from "not really useful" to "useful". But Opus 4.5 is something different - I don't feel I have to keep pulling it back on track in quite the way I used to with Sonnet 3.7, 4, even Sonnet 4.5.

For the record, I still think we're in a bubble. AI companies are overvalued. But that's a separate question from whether this is going to change the software development profession.

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

#312

Post by hsn915 »

I had a similar feeling expressed in the title regarding ChatGPT 5.2

I haven't tried it for coding. I'm just talking about regular chatting.

It's doing something different from prior models. It seems like it can maintain structural coherence even for very long chats.

Where as prior models felt like System 1 thinking, ChatGPT5.2 appears like it exhibits System 2 thinking.

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

#313

Post by llmslave2 »

oncallthrow wrote: post #109

Yeah Opus 4.5 is a massive step change in my experience. I feel like I’m working with a peer, not a junior I’m having to direct. I can give it highly ambiguous and poorly specified tasks and it… just does it. I will note that my experience varies slightly by language though. I’ve found it’s not as good at typescript.

> I feel like I’m working with a peer, not a junior I’m having to direct.

I think this says a lot.

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

#314

Post by artdigital »

I switched my subscription from Claude to ChatGPT around 5.0 when SOTA was Sonnet 4.5 and found GPT-5-high (and now 5.2-high) so incredibly good, I could never imagine Opus is on its level. I give gpt-5.2-high a spec, it works for 20 minutes and the result is almost perfect and tested. I very rarely have to make changes.

It never duplicates code, implements something again and leaves the old code around, breaks my convention, hallucinates, or tells me it’s done when the code doesn’t even compile, which sonnet 4.5 and Opus 4.1 did all the time

I’m wondering if this had changed with Opus 4.5 since so many people are raving about it now. What’s your experience?

Claude - fast, to the point but maybe only 85% - 90% there and needs closer observation while it works

GPT-x-high (or xhigh) - you tell it what to do, it will work slowly but precise and the solution is exactly what you want. 98% there, needs no supervision

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

#316

Post by mcv »

HawtAds wrote: post #249
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…

Copilot and many coding agents truncates the context window and uses dynamic summarization to keep costs low for them. That's how they are able to provide flat fee plans. You can see some of the context limits here: https://models.dev/ If you want the full capability, use the API and use something like opencode. You will find that a single PR can easily rack up 3 digits of consumption costs.

Maybe not, then. I'm afraid I have no idea what those numbers mean, but it looks like Gemini and ChatGPT 4 can handle a much larger context than Opus, and Opus 4.5 is cheaper than older versions. Is that correct? Because I could be misinterpreting that table.

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

#317

Post by yieldcrv »

mcv wrote: post #229
yieldcrv wrote: post #213

Earlier quoted context omitted.

It acts differently when using it through a third party tool Try it again using Claude Code and a subscription to Claude. It can run as a chat window in VS Code and Cursor too.

My employer gets me a Copilot subscription with access to Claude, not a subscription to Claude Code, unfortunately.

at this point I would suggest getting a $20 subscription to start, seeing if you can expense it

the tooling is almost as important as the model

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

#318

Post by jsnell »

llmslave2 wrote: post #299
simonw wrote: post #272

Earlier quoted context omitted.

You're only hurting yourself if you decide there's some wild conspiracy afoot here to pay shills to tell people that coding agents are useful... as opposed to people finding them useful enough to want to tell other people about it.

[flagged]

Why is it the people posting positive comments who are "responding to incentives" by posting more, while it's the people posting negative comments who do so by stopping posting? Like, your exact points work equally well with the polarity reversed: the anti-AI influencer/grifter ecosystem is well-developed at this point, and many people desperately want AIs to be useless.

I don't know if the original claim about sentiment is true, but if it is, I don't think yours or blibble's (conflicting) claims about the reason are very believable.

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

#319

Post by Capricorn2481 »

simonw wrote: post #154
AstroBen wrote: post #95

Earlier quoted context omitted.

my issue hasn't been for a long time now that the code they write works or doesn't work. My issues all stem from that it works, but does the wrong thing

If it does the wrong thing you tell it what the right thing is and have it try again. With the latest models if you're clear enough with your requirements you'll usually find it does the right thing on the first try.

> With the latest models if you're clear enough with your requirements you'll usually find it does the right thing on the first try

That's great that this is your experience, but it's not a lot of people's. There are projects where it's just not going to know what to do.

I'm working in a web framework that is a Frankenstein-ing of Laravel and October CMS. It's so easy for the agent to get confused because, even when I tell it this is a different framework, it sees things that look like Laravel or October CMS and suggests solutions that are only for those frameworks. So there's constant made up methods and getting stuck in loops.

The documentation is terrible, you just have to read the code. Which, despite what people say, Cursor is terrible at, because embeddings are not a real way to read a codebase.

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

#320

Post by multisport »

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 understood way, in a way that's easily extensible.

No doubt I could give Opus 4.5 "build be a XYZ app" and it will do well. But day to day, when I ask it "build me this feature" it uses strange abstractions, and often requires several attempts on my part to do it in the way I consider "right". Any non-technical person might read that and go "if it works it works" but any reasonable engineer will know that thats not enough.

Post reply on HN