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

871–880 of 1001 posts

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

#871

Post by ryandrake »

kevin42 wrote: post #860
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…

This isn't meant as a criticism, or to doubt your experience, but I've talked to a few people who had experiences like this. But, I helped them get Claude code setup, analyze the codebase and document the architecture into markdown (edit as needed after), create an agent for the architecture, and prompt it in an incremental way. Maybe 15-30 minutes of prep. Everyone I helped with this responded with things like "This…

Is there any good documentation out there about how to perform this wizardry? I always assumed if you did /init in a new code base, that Claude would set itself up to maximize its own understanding of the code. If there are extra steps that need to be done, why don't Claude's developers just add those extra steps to /init?

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

#872

Post by kaydub »

blahblaher wrote: post #118
6177c40f wrote: post #60

Earlier quoted context omitted.

Cheaper than hiring another developer, probably. My experience: for a few dollars I was able to extensively refactor a Python codebase in half a day. This otherwise would have taken multiple days of very tedious work.

And that's what the C-suite wants to know. Prepare yourself to be replaced in the not so distant future. Hope you have a good "nest" to support yourself when you're inevitably fired.

Homey, we're going to be replacing you devs that can't stand to use LLMs lol

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

#873

Post by elfly »

scosman wrote: post #819
vladsh wrote: post #755

It’s a bit strange how anecdotes have become acceptable fuel for 1000 comment technical debates. I’ve always liked the quote that sufficiently advanced tech looks like magic, but its mistake to assume that things that look like magic also share other properties of magic. They don’t. Software engineering spans over several distinct skills: forming logical plans, encoding them in machine executable form(coding), making…

> It’s a bit strange how anecdotes have become acceptable fuel for 1000 comment technical debates. Progress is so fast right now anecdotes are sometimes more interesting than proper benchmarks. "Wow it can do impressive thing X" is more interesting to me than a 4% gain on SWE Verified Bench. In early days of a startup "this one user is spending 50 hours/week in our tool" is sometimes more interesting than global metr…

At this point I believe the anecdotes more than benchmarks, cause I know the LLM devs train the damn things on the benchmarks.

A benchmark? probably was gamed. A guy made an app to right click and convert an image? prolly true, have to assume it may have a lot of issues but prima facie I just make a mental note that this is possible now.

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

#874

Post by ryandrake »

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…

I don't think it's that helpful to try to gatekeep the "engineering" term or try to separate it into "pure" and "impure" buckets, implying that one is lesser than the other. It should be enough to just say that AI assisted development is much better at non-novel tasks than it is at novel tasks. Which makes sense: LLMs are trained on existing work, and can't do anything novel because if it was trained on a task, that task is by definition not novel.

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

#875

Post by minimaxir »

lagniappe wrote: post #645
minimaxir wrote: post #177

Earlier quoted context omitted.

A Hacker News moderator likely changed the title because it's uninformatively vague.

Rules are rules, and excuses are excuses.

Hacker News mods rewriting titles has been a standard since before I joined HN in 2012.

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

#876

Post by hu3 »

ggregoire wrote: post #857

I'm always surprised to never see any comments in those discussions from people who just like coding, learning, solving problems… I mean, it's amazing that LLMs can build an image converter or whatever you dream of, in a language you don't know, in a field you are not familiar with, in 1 hour, for 30 cents… I'm sure your boss and shareholders love it. But where is the fun in that? For me it kills any interest in doin…

After decade(s) working with either enterprise crud or web agency fancy websites, the novelty wears off.

It's just boring and I'm glad to delegate most of the repetitive work.

But sure, if I'm doing something new, I still like to craft lines of code myself.

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

#877

Post by Wowfunhappy »

ryandrake wrote: post #869
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…

I've found it to be pretty hit-or-miss with C++ in general, but it's really, REALLY bad at 3D graphics code. I've tried to use it to port an OpenGL project to SDL3_GPU, and it really struggled. It would confidently insist that the code it wrote worked, when all you had to do was run it and look at the output to see a blank screen.

I hope I’m not committing a faux pas by saying this—and please feel free to tell me that I’m wrong—but I imagine a human who has been blind since birth would also struggle to build 3D graphics code.

The Claude models are technically multi-modal, but IME the vision side of the equation is really lacking. As a result, Claude is quite good at reasoning about logic, and it can build e.g. simpler web pages where the underlying html structure is enough to work with, but it’s much worse at tasks that inherently require seeing.

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

#878

Post by kaydub »

theanonymousone wrote: post #70
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…

Is Claude "Code" anything special,or it's mostly the LLM and other CLIs (e.g. Copilot) also work?

In my experience the CLI tool is part of the secret sauce. I haven't tried switching models per each CLI tool though. I use claude exclusively at work and for personal projects I use claude, codex, gemini.

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

#879

Post by nycdatasci »

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…

Have you experimented with all of these things on the latest models (e.g. Opus 4.5) since Nov 2025? They are significantly better at coding than earlier models.

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

#880

Post by ryandrake »

Wowfunhappy wrote: post #877
ryandrake wrote: post #869

Earlier quoted context omitted.

I've found it to be pretty hit-or-miss with C++ in general, but it's really, REALLY bad at 3D graphics code. I've tried to use it to port an OpenGL project to SDL3_GPU, and it really struggled. It would confidently insist that the code it wrote worked, when all you had to do was run it and look at the output to see a blank screen.

I hope I’m not committing a faux pas by saying this—and please feel free to tell me that I’m wrong—but I imagine a human who has been blind since birth would also struggle to build 3D graphics code. The Claude models are technically multi-modal, but IME the vision side of the equation is really lacking. As a result, Claude is quite good at reasoning about logic , and it can build e.g. simpler web pages where the unde…

Yea, for obvious reasons, it seems to be best at code that transforms data: text/binary input to text/binary output. And where the logic can be tracked and verified at runtime with sufficient (text) logging. In other words, it's much better close loop than open loop. I tried to help it by prompting it to please take a screen capture of its output to verify functionality, but it seems LLMs aren't quite ready for that yet.
Post reply on HN