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

#211

Post by littlestymaar » Tue, Jan 06, 2026, 10:31 PM UTC

spaceman_2020 wrote: post #54

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 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…

> 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.

It's not just the deficiencies of earlier versions, but the mismatch between the praise from AI enthusiasts and the reality.

I mean maybe it is really different now and I should definitely try uploading all of my employer's IP on Claude's cloud and see how well it works. But so many people were as hyped by GPT-4 as they are now, despite GPT-4 actually being underwhelming.

Too much hype for disappointing results leads to skepticism later on, even when the product has improved.

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

#212

Post by yieldcrv » Tue, Jan 06, 2026, 10:31 PM UTC

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…

I recently replaced my monitor with one that could be vertically oriented, because I'm just using Claude Code in the terminal and not looking at file trees at all

but I do want a better way to glance and keep up with what its doing in longer conversations, for my own mental context window

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

#213

Post by yieldcrv » Tue, Jan 06, 2026, 10:34 PM UTC

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…

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.

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

#214

Post by vbezhenar » Tue, Jan 06, 2026, 10:34 PM UTC

cyberpunk wrote: post #37

tannedNerd wrote: post #4

The problem with this is none of this is production quality. You haven’t done edge case testing for user mistakes, a security audit, or even just maintainability. Yes opus 4.5 seems great but most of the time it tries to vastly over complicate a solution. Its answer will be 10x harder to maintain and debug than the simpler solution a human would have created by thinking about the constraints of keeping code working.

You should try it with BEAM languages and the 'let it crash' style of programming. With pattern matching and process isolated per request you basically only need to code the happy path, and if garbage comes in you just let the process crash. Combined with the TDD plugin (bit of a hidden gem), you can absolutely write production level services this way.

You don't need BEAM languages. I'm using Java and I always write my code in "let it crash" style, to spend time on happy paths and avoid spending time on error handling. I think that's the only sane way to write code and it hurts me to see all the useless error handling code people write.

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

#215

Post by dzonga » Tue, Jan 06, 2026, 10:34 PM UTC

what strikes me about these posts is they praise models for apps | utilities commonly found on GitHub.

ie well known paths based on training data.

what's never posted is someone building something that solves a real problem in the real world - that deals with messy data | interfaces.

I like a.i to do the common routine tasks that I don't like to do like apply tailwind styles but being renter and faking productivity that's not it

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

#216

Post by fractallyte » Tue, Jan 06, 2026, 10:35 PM UTC

That final line: "Disclaimer: This post was written by a human and edited for spelling, grammer by Haiku 4.5"

Yeah, GRAMMAR

For all the wonderment of the article, tripping up on a penultimate word that was supposedly checked by AI suddenly calls into question everything that went before...

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

#217

Post by troupo » Tue, Jan 06, 2026, 10:37 PM UTC

simonw wrote: post #153

Opus 4.5 really is something else. I've been having a ton of fun throwing absurdly difficult problems at it recently and it keeps on surprising me. A JavaScript interpreter written in Python? How about a WebAssembly runtime in Python? How about porting BurntSushi's absurdly great Rust optimized string search routines to C and making them faster ? And these are mostly just casual experiments, often run from my phone!

On the other hand when I tried it just yesterday, I couldn't really see a difference. As I wrote elsewhere: same crippled context window, same "I'll read 10 irrelevant lines from a file", same random changes etc.

Meanwhile half a year to a year ago I could already point whatever model was du jour at the time at pychromecast and tell it repeatedly "just convert the rest of functionality to Swift" and it did it. No idea about the quality of code, but it worked alongside with implementations for mDNS, and SwiftUI, see gif/video here: https://mastodon.nu/@dmitriid/114753811880082271 (doesn't include chromecast info in the video).

I think agents have become better, but models likely almost entirely plateaued.

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

#218

Post by mikestorrent » Tue, Jan 06, 2026, 10:37 PM UTC

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…

I have a few Go projects now and I speak Go as well as you speak Kotlin. I predict that we'll see some languages really pull ahead of others in the next few years based on their advantages for AI-powered development.

For instance, I always respected types, but I'm too lazy to go spend hours working on types when I can just do ruby-style duck typing and get a long ways before the inevitable problems rear their head. Now, I can use a strongly typed language and get the advantages for "free".

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

#219

Post by falloutx » Tue, Jan 06, 2026, 10:38 PM UTC

simonw wrote: post #153

Opus 4.5 really is something else. I've been having a ton of fun throwing absurdly difficult problems at it recently and it keeps on surprising me. A JavaScript interpreter written in Python? How about a WebAssembly runtime in Python? How about porting BurntSushi's absurdly great Rust optimized string search routines to C and making them faster ? And these are mostly just casual experiments, often run from my phone!

I have tried to give it extreme problems like creating slime mold pathing algorithm and creating completely new shoe-lacing patterns and it starts struggling with problems which use visual reasoning and have very little consensus on how to solve them.

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

#220

Post by smusamashah » Tue, Jan 06, 2026, 10:39 PM UTC

What about Sonnet 4.5? I used both Opus and Sonnet on Claude.ai and found sonnet much better at following instructions and doing exactly what was asked.

(it was for single html/js PWA to measure and track heart rate)

Opus seems to go less deep, does it's own things, do not follow instructions exactly EVEN IF I WROTE ALL CAPS. With Sonnet 4.5 I can understand everything author is saying. May be Opus is optimised for Claude code and Sonnet works best on Web.