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

#971

Post by maxkfranz » Thu, Jan 08, 2026, 4:29 PM UTC

vidarh wrote: post #966

maxkfranz wrote: post #917

Earlier quoted context omitted.

> 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 t…

I'd really encourage you to try using agents for tasks that are repeatable and/or wordy but where most of the words are not relevant for ongoing understanding. It's a tiny step further, and sub-agents provide a massive benefit the moment you're ready to trust the model even a little bit (relax permissions to not have it prompt you for every little thing; review before committing rather than on every file edit) becaus…

That's a great point. There are a lot of things you can do to optimise things, and your suggestion is one of the lower hanging fruits.

I was trying to get across the point that today you can get a lot of benefit from minimal setup, even one that's vendor-agnostic. (The steps I outlined work for Codex out of the box, too.)

You're right to point out that the more you refine things, the more you'll get out of the tools. It used to be that you had to do a lot of refinements to start getting good results at all. Now, you can get a lot out of even a basic setup like I outlined, which is great for people who are new users -- or people who tried it before and weren't that impressed but are now giving it another try.

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

#972

Post by mcv » Thu, Jan 08, 2026, 4:59 PM UTC

esperent wrote: post #338

mcv wrote: post #316

Earlier quoted context omitted.

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.

I don't know about GPT4 but the latest one (GPT 5.2) has 200k context window while Gemini has 1m, five times higher. You'll be wanting to stay within the first 100k on all of them to avoid hitting quotas very quickly though (either start a new task or compact when you reach that) so in practice there's no difference. I've been cycling between a couple of $20 accounts to avoid running out of quota and the latest of al…

> You'll be wanting to stay within the first 100k on all of them

I must admit I have no idea how to do that or what that even means. I get that bigger context window is better, but what does it mean exactly? How do you stay within that first 100k? 100k what exactly?

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

#973

Post by mcv » Thu, Jan 08, 2026, 5:04 PM UTC

sfink wrote: post #350

zmmmmm wrote: post #173

Earlier quoted context omitted.

yes just using AI for code analysis is way under appreciated I think. Even the most sceptical people on using it for coding should try it out as a tool for Q&A style code interrogation as well as generating documentation. I would say it zero-shots documentation generation better than most human efforts would to the point it begs the question of whether it's worth having the documentation in the first place. Obviously…

(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…

They do have a knack for missing the point. Even Opus 4.5 can laser focus on the wrong thing. It does take skill and experience to interpret them correctly and set them straight when they go wrong.

Even so, for understanding what happens in a big chunk of code, they're pretty great.

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

#974

Post by mcv » Thu, Jan 08, 2026, 5:07 PM UTC

NSPG911 wrote: post #343

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…

> Opus 4.5 ate theough my Copilot quota last month Sure, Copilot charges 3x tokens for using Opus 4.5, but, how were you still able to use up half the allocated tokens not even one week into January? I thought using up 50% was mad for me (inline completions + opencode), that's even worse

I have no idea. Careless use, I guess. I was fixing a bunch of mocks in some once-great but now poorly maintained code, and I wasn't really feeling it so I just fed everything to Claude. Opus, unfortunately. I could easily have downgraded a bit.

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

#975

Post by mcv » Thu, Jan 08, 2026, 5:10 PM UTC

yieldcrv wrote: post #317

mcv wrote: post #229

Earlier quoted context omitted.

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

Security and approval is considered more important here. Just getting approval for neo4j on the clearest ever use case for it, took a year. I'm not going to spend my energy on getting approval for Claude Code.

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

#976

Post by firemelt » Thu, Jan 08, 2026, 6:23 PM UTC

jedberg wrote: post #453

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…

what plan do you have on claude?

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

#977

Post by firemelt » Thu, Jan 08, 2026, 6:26 PM UTC

ben-gy wrote: post #695

I second this article - I built twelve iOS/Mac apps in two weeks with Opus 4.5 - four of them are already in the App Store - I’m a Rails Engineer and never had the time to learn Swift but man does Opus 4.5 make that not even matter - it even handles entitlements, logo & splash screen generation, refactors to remove dead code, edge case assent and hardening, Multiplatform app design, and more - I’m yet to run into a u…

what claude plan are u on?

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

#978

Post by jedberg » Thu, Jan 08, 2026, 6:28 PM UTC

firemelt wrote: post #976

jedberg wrote: post #453

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…

what plan do you have on claude?

The cheapest one above free.

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

#979

Post by 348512469721 » Thu, Jan 08, 2026, 7:33 PM UTC

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…

> It also can't do rust really well

I have not had this experience at all. It often doesn't get it right on the first pass, yes, but the advantage with Rust vibecoding is that if you give it a rule to "Always run cargo check before you think you're finished" then it will go back and fix whatever it missed on the first pass. What I find particularly valuable is that the compiler forces it to handle all cases like match arms or errors. I find that it often misses edge cases when writing typescript, and I believe that the relative leniency of the typescript compiler is why.

In a similar vein, it is quite good at writing macros (or at least, quite good given how difficult this otherwise is). You often have to cajole it into not hardcoding features into the macro, but since macros resolve at compile time they're quite well-suited for an LLM workflow as most potential bugs will be apparent before the user needs to test. I also think that the biggest hurdle of writing macros to humans is the cryptic compiler errors, but I can imagine that since LLMs have a lot of information about compilers and syntax parsing in their training corpus, they have an easier time with this than the median programmer. I'm sure an actual compiler engineer would be far better than the LLM, but I am not that guy (nor can I afford one) so I'm quite happy to use LLMs here.

For context, I am purely a webdev. I can't speak for how well LLMs fare at anything other than writing SQL, hooking up to REST APIs, React frontend, and macros. With the exception of macros, these are all problems that have been solved a million times thus are more boilerplate than novelty, so I think it is entirely plausible that they're very poor for different domains of programming despite my experiences with them.

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

#980

Post by jessoteric » Thu, Jan 08, 2026, 8:50 PM UTC

348512469721 wrote: post #979

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…

> It also can't do rust really well I have not had this experience at all. It often doesn't get it right on the first pass, yes, but the advantage with Rust vibecoding is that if you give it a rule to "Always run cargo check before you think you're finished" then it will go back and fix whatever it missed on the first pass. What I find particularly valuable is that the compiler forces it to handle all cases like matc…

i've also been using opus 4.5 with lots of heavy rust development. i don't "vibe code", but lead it with a relatively firm hand- and it produces pretty good results in surprisingly complicated tasks.

for example, one of our public repos works with rust compiler artifacts and cache restoration (https://github.com/attunehq/hurry); if you look at the history you can see it do some pretty surprisingly complex (and well made, for an LLM) changes. its code isn't necessarily what i would always write, or the best way to solve the problem, but it's usually perfectly serviceable if you give it enough context and guidance.