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

291–300 of 1001 posts

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

#291

Post by bdangubic »

lelanthran wrote: post #23
s-macke wrote: post #8

Opus 4.5 has become really capable. Not in terms of knowledge. That was already phenomenal. But in its ability to act independently: to make decisions, collaborate with me to solve problems, ask follow-up questions, write plans and actually execute them. You have to experience it yourself on your own real problems and over the course of days or weeks. Every coding problem I was able to define clearly enough within th…

> You have to experience it yourself on your own real problems and over the course of days or weeks. How do you stop it from over-engineering everything?

“Everything Should Be Made as Simple as Possible, But Not Simpler” should be the ending of every prompt :)

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

#292

Post by torben-friis »

poisonborz wrote: post #141

I see these posts left and right but no one mentions the _actual_ thing developers are hired for, responsibility. You could use whatever tools to aid coding already, even copy paste from StackOverflow or take whole boilerplate projects from Github already. No AI will take responsibility for code or fix a burning issue that arises because of it. The amount of "responsibility takers" also increases linearly with the si…

>the _actual_ thing developers are hired for, responsibility.

It is a well known fact that people advance their tech careers by building something new and leaving maintenance to others. Google is usually mentioned.

By which I mean, our industry does a piss poor job of rewarding responsibility and care.

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

#293

Post by jolt42 »

soulofmischief wrote: post #179

Opus 4.5 is currently helping me write a novel, comprehensive and highly performant programming language with all of the things I've ever wanted, done in exactly my opinionated way. This project would have taken me years of specialization and research to do right. Opus's strength has been the ability to both speak broadly and also drill down into low-level implementations. I can express an intent, and have some discu…

Long-term maybe we won't care about code because AI will just maintain it itself. Before that day comes, don't you want a coding language that isn't opinionated, but rather able to describe the problem at hand in the most understandable way possible (to a human)?

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

#294

Post by Kerrick »

chaostheory wrote: post #250
Kerrick wrote: post #227

Earlier quoted context omitted.

Gemini 3 Pro (High) via Antigravity has been similarly great recently. So have tools that I imagine call out to these higher-power models: Amp and Junie. In a two-week blur I brought forth the bulk of a Ruby library that includes bindings to the Ratatui rust crate for making TUIs in Ruby. During that time I also brought forth documentation, example applications, build and devops tooling, and significant architectural…

Were they able to link Antigravity to your paid subscription? I have a Google ultra AI sub and antigrav ran out of credits within 30 minutes for me. Of course that was a few weeks ago, and I’m hoping that they fixed this

Yes. I was on a 30-day trial of Google AI Pro and I got a few big wins each out of Gemini 3 Pro (High) and Claude 4.5 Opus (Thinking) before my quota got reset. Then I'd cycle through Gemini 3 Flash and Amp Free (or paid Junie credits if I got antsy) until my quota reset.

You can see this pattern in my AI attribution commit footers. It was such a noticeable difference to me that I signed up for Google AI Ultra. I got the email receipt January 3, 2026 at 11:21 AM Central, and I have not hit a single quota limit since. Yo

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

#295

Post by tezza »

heavyset_go wrote: post #280
rcarmo wrote: post #205

I had a similar set of experiences with GPT 5.x over the holiday break, across somewhat more disparate domains: https://taoofmac.com/space/notes/2025/12/31/1830 I hacked together a Swift tool to replace a Python automation I had, merged an ARM JIT engine into a 68k emulator, and even got a very decent start on a synth project I’ve been meaning to do for years. What has become immensely apparent to me is that even gpt…

To add to the anecdata, today GPT 5.2-whatever hallucinated the existence of two CLI utilities, and when corrected, then hallucinated the existence of non-existent, but plausible, features/options of CLI utilities that do actually exist. I had to dig through source code to confirm whether those features actually existed. They don't, so the CLI tools GPT recommended aren't actually applicable to my use case. Yesterday…

Yeah, it needs a steady hand on the tiller. However throw together improvements of 70%, -15%, 95%, 99%, -7% across all the steps and overall you're way ahead.

SimonW's approach of having a suite of dynamic tools (agents) grind out the hallucinations is a big improvement.

In this case expressing the feeback validation and investing in the setup may help smooth these sharp edges.

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

#297

Post by heavyset_go »

simonw wrote: post #283
heavyset_go wrote: post #280

Earlier quoted context omitted.

To add to the anecdata, today GPT 5.2-whatever hallucinated the existence of two CLI utilities, and when corrected, then hallucinated the existence of non-existent, but plausible, features/options of CLI utilities that do actually exist. I had to dig through source code to confirm whether those features actually existed. They don't, so the CLI tools GPT recommended aren't actually applicable to my use case. Yesterday…

Were you running it inside a coding agent like Codex? If so then it should have realized its mistake when it tried to run those CLI commands and saw the error message. Then it can try something different instead. If you were using a regular chat interface and expecting it to know everything without having an environment to try things out then yeah, you're going to be disappointed.

No, Codex doesn't have permission to install random software on my machine and then execute it to see if it's real or a hallucination.

CLI utility here means software with a CLI, not classic Unix-y CLI tools.

The WebDav hallucinations happened in the chat interface.

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

#298

Post by zoilism »

gingersnap wrote: post #97
Yoric wrote: post #88

Earlier quoted context omitted.

You intrigue me. > have it learn your conventions, pull in best practices What do you mean by "have it learn your conventions"? Is there a way to somehow automatically extract your conventions and store it within CLAUDE.md? > For example, we have a custom UI library, and Claude Code has a skill that explains exactly how to use it. Same for how we write Storybooks, how we structure APIs, and basically how we want ever…

Starting to use Opus 4.5 I'm reduces instrutions in claude.md and just ask claude to look in the codebase to understand the patterns already in use. Going from prompts/docs to instead having code being the "truth". Show don't tell. I've found this patterns has made a huge leap with Opus 4.5.

The Ash framework takes the approach you describe.

From the docs (https://hexdocs.pm/ash/what-is-ash.html):

"Model your application's behavior first, as data, and derive everything else automatically. Ash resources center around actions that represent domain logic."

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

#299

Post by llmslave2 »

simonw wrote: post #272
blibble wrote: post #271

Earlier quoted context omitted.

> I've noticed a huge drop in negative comments on HN when discussing LLMs in the last 1-2 months. real people get fed up of debating the same tired "omg new model 1000x better now" posts/comments from the astroturfers, the shills and their bots each time OpenAI shits out a new model (article author is a Microslop employee)

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]

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

#300

Post by benjiro »

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.

> Prepare yourself to be replaced in the not so distant future.

Ignoring that this same developer, now has access to a tool, that makes himself a team.

Going independent was always a issue because being a full stack dev, is hard. With LLMs, you have a entire team behind you for making graphics, code, documents, etc... YOU becomes the manager.

We will see probably a lot more smaller teams/single devs making bigger projects, until they grow.

The companies that think they can fire devs, are the same companies that are going to go too far, and burn bridges. Do not forget that a lot of companies are founded on devs leaving a company, and starting out on their own, taking clients with them!

I did that years ago, and it worked for a while but eventually the math does not work out because one guy can only do so much. And when you start hiring, your costs balloon. But with LLMs ... Now your a one man team, ... hiring a second person is not hiring a person to make some graphics or doing more coding. Your hiring another team.

This is what people do not realize... they look too much upon this as the established order, ignoring what those fired devs now can do!

Post reply on HN