Opus 4.5 is not the normal AI agent experience that I have had thus far • Hacker News Board

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

#911

Post by flumpcakes » Wed, Jan 07, 2026, 8:14 PM UTC

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…

> How many 1+ hour videos of someone building with AI tools have you sought out and watched?

A lot, they've mostly all been advertising trite and completely useless.

I don't want a demonstration of what a jet-powered hammer is by the sales person or how to oil it, or mindless fluff about how much time it will save me hammering things. I want to see a journeyman use a jet-powered hammer to build a log cabin.

I am personally not seeing this magic utopia. No one wants to show me it, they just want to talk about how better it is.

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

#912

Post by billmalarky » Wed, Jan 07, 2026, 8:18 PM UTC

kypro wrote: post #310

It's been interesting watching HN shift in my direction on this in recent weeks... I had been saying since around summer of this year that coding agents were getting extremely good. The base model improvements were ok, but the agentic coding wrappers were basically game changers if you were using them right. Until recently they still felt very context limited, but the context problem increasingly feels like a solved…

Hi Kypro this is very interesting perspective. Can you reach out to me? I'd like to discuss what you're observing with you a bit in private as it relates heavily to a project I'm currently working on. My contact info is on my profile. Pls shoot me a connection request and just say you're kypro from HN :)

Or is there a good way for me to contact you? Your profile doesn't list anything and your handle doesn't seem to have much of an online footprint.

Lastly, I promise I'm not some weirdo, I'm a realperson™ -- just check my HN comment history. A lot of people in the AI community have met me in person and can confirm (swyx etc).

Look forward to chatting!

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

#913

Post by throw1235435 » Wed, Jan 07, 2026, 8:21 PM UTC

josu wrote: post #411

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…

>So my verdict is that it's great for code analysis, and it's fantastic for injecting some book knowledge on complex topics into your programming, but it can't tackle those complex problems by itself. I don't think you've seen the full potential. I'm currently #1 on 5 different very complex computer engineering problems, and I can't even write a "hello world" in rust or cpp. You no longer need to know how to write co…

If that is true; then all the commentary around software people having jobs still due to "taste" and other nice words is just that. Commentary. In the end the higher level stuff still needs someone to learn it (e.g. learning ASX2 architecture, knowing what tech to work with); but it requires IMO significantly less practice then coding which in itself was a gate. The skill morphs more into a tech expert rather than a coding expert.

I'm not sure what this means for the future of SWE's though yet. I don't see higher levels of staff in big large businesses bothering to do this, and at some scale I don't see founders still wanting to manage all of these agents, and processes (got better things to do at higher levels). But I do see the barrier of learning to code gone; meaning it probably becomes just like any other job.

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

#914

Post by egorfine » Wed, Jan 07, 2026, 8:31 PM UTC

stocksinsmocks wrote: post #909

egorfine wrote: post #906

So I decided to try the revered hands-off approach and have Claude Code create me a small tool in JS for *.dylib bundle consolidation on macOS. I have used AskUserQuestionTool to complete my initial spec. And then Opus 4.5 created the tool according to that extensive and detailed spec. It appeared to work out of the box. Boy how horrific was the code. Unnecessary recursions, unused variables, data structures being bu…

That’s the opposite of my experience. Weird. But I’m also not the kind of person who gets hung up on whether someone used a loop or recursion or if their methods are five times as long as what I would’ve done myself unless there is a performance impact that matters to me as a user. But I’m also the kind of person who doesn’t get paid by the hour to write programs. I use programs in the service of other paid work.

Yes, this experience is unlike most people. Perhaps the problem is that most people are satisfied by the appearance of a working app despite it not working at all. Say, the first tool I was doing, did actually not recurse into subdirs with dylibs which made it useless.

So, AI slop, yes.

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

#915

Post by turkey99 » Wed, Jan 07, 2026, 8:33 PM UTC

JDye wrote: post #813

klaussilveira wrote: post #325

Earlier quoted context omitted.

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…

We have an in-house, Rust-based proxy server. Claude is unable to contribute to it meaningfully outside of grunt work like minor refactors across many files. It doesn't seem to understand proxying and how it works on both a protocol level and business logic level. With some entirely novel work we're doing, it's actually a hindrance as it consistently tells us the approach isn't valid/won't work (it will) and then ent…

Are you still talking about Opus 4.5 I’ve been working on a Rust, kotlin and c++ and it’s been doing well. Incredible at C++, like the number of mistakes it doesn’t make

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

#916

Post by scottyah » Wed, Jan 07, 2026, 8:34 PM UTC

parliament32 wrote: post #867

JDye wrote: post #813

Earlier quoted context omitted.

We have an in-house, Rust-based proxy server. Claude is unable to contribute to it meaningfully outside of grunt work like minor refactors across many files. It doesn't seem to understand proxying and how it works on both a protocol level and business logic level. With some entirely novel work we're doing, it's actually a hindrance as it consistently tells us the approach isn't valid/won't work (it will) and then ent…

> I still believe those who rave about it are not writing anything I would consider "engineering". Correct. In fact, this is the entire reason for the disconnect, where it seems like half the people here think LLMs are the best thing ever and the other half are confused about where the value is in these slop generators. The key difference is (despite everyone calling themselves an SWE nowadays) there's a difference b…

It's how you use the tool that matters. Some people get bitter and try to compare it to top engineers' work on novel things as a strawman so they can go "Hah! Look how it failed!" as they swing a hammer to demonstrate it cannot chop down a tree. Because the tool is so novel and it's use us a lot more abstract than that of an axe, it is taking awhile for some to see its potential, especially if they are remembering models from even six months ago.

Engineering is just problem solving, nobody judges structural engineers for designing structures with another Simpson Strong Tie/No.2 Pine 2x4 combo because that is just another easy (and therefore cheap) way to rapidly get to the desired state. If your client/company want to pay for art, that's great! Most just want the thing done fast and robustly.

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

#917

Post by maxkfranz » Wed, Jan 07, 2026, 8:35 PM UTC

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…

> 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 the stuff you do all the time.

I agree with this, but I haven't needed to use any advanced features to get good results. I think the simple approach gets you most of the benefits. Broadly, I just have markdown files in the repo written for a human dev audience that the agent can also use.

Basically:

- README.md with a quick start section for devs, descriptions of all build targets and tests, etc. Normal stuff.

- AGENTS.md (only file that's not written for people specifically) that just describes the overall directory structure and has a short step of instructions for the agent: (1) Always read the readme before you start. (2) Always read the relevant design docs before you start. (3) Always run the linter, a build, and tests whenever you make code changes.

- docs/*.md that contain design docs, architecture docs, and user stories, just text. It's important to have these resources anyway, agent or no.

As with human devs, the better the docs/requirements the better the results.

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

#918

Post by lisperforlife » Wed, Jan 07, 2026, 8:38 PM UTC

dpc_01234 wrote: post #883

JDye wrote: post #813

Earlier quoted context omitted.

We have an in-house, Rust-based proxy server. Claude is unable to contribute to it meaningfully outside of grunt work like minor refactors across many files. It doesn't seem to understand proxying and how it works on both a protocol level and business logic level. With some entirely novel work we're doing, it's actually a hindrance as it consistently tells us the approach isn't valid/won't work (it will) and then ent…

> We have an in-house, Rust-based proxy server. Claude is unable to contribute to it meaningfully outside I have a great time using Claude Code in Rust projects, so I know it's not about the language exactly. My working model is is that since LLM are basically inference/correlation based, the more you deviate from the mainstream corpus of training data, the more confused LLM gets. Because LLM doesn't "understand" any…

Recently the v8 rust library changed it from mutable handle scopes to pinned scopes. A fairly simple change that I even put in my CLAUDE.md file. But it still generates methods with HandleScope's and then says... oh I have a different scope and goes on a random walk refactoring completely unrelated parts of the code. All the while Opus 4.5 burns through tokens. Things work great as long as you are testing on the training set. But that said, it is absolutely brilliant with React and Typescript.

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

#919

Post by troupo » Wed, Jan 07, 2026, 8:52 PM UTC

pluralmonad wrote: post #890

troupo wrote: post #208

Earlier quoted context omitted.

> Opus 4.5 really is at a new tier however. It just...works. Literally tried it yesterday. I didn't see a single difference with whatever model Claude Code was using two months ago. Same crippled context window. Same "I'll read 10 irrelevant lines from a file", same random changes etc.

I'm not familiar with any form of intelligence that does not suffer from a bloated context. If you want to try and improve your workflow, a good place to start is using sub-agents so individual task implementations do not fill up your top level agents context. I used to regularly have to compact and clear, but since using sub-agents for most direct tasks, I hardly do anymore.

1. It's a workaround for context limitations

2. It's the same workarounds we've been doing forever

3. It's indistinguishable from "clear context and re-feed the entire world of relevant info from scratch" we've had forever, just slightly more automated

That's why I don't understand all the "it's new tier" etc. It's all the same issues with all the same workarounds.

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

#920

Post by gck1 » Wed, Jan 07, 2026, 8:58 PM UTC

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?

The second part is what I'd also like to have.

But I think it should be doable. You can tell it how YOU want the state to be managed and then have it write a custom "linter" that makes the check deterministic. I haven't tried this myself, but claude did create some custom clippy scripts in rust when I wanted to enforce something that isn't automatically enforced by anything out there.