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

#91

Post by pseidemann » Tue, Jan 06, 2026, 6:39 PM UTC

6177c40f wrote: post #72

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 think we're entering a world where programmers as such won't really exist (except perhaps in certain niches). Being able to program (and read code, in particular) will probably remain useful, though diminished in value. What will matter more is your ability to actually create things, using whatever tools are necessary and available, and have them actually be useful. Which, in a way, is the same as it ever was. Ther…

Isn't there more indirection as long as LLMs use "human" programming languages?

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

#92

Post by square_usual » Tue, Jan 06, 2026, 6:40 PM UTC

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?

I've tried most of the CLI coding tools with the Claude models and I keep coming back to Claude Code. It hits a sweet spot of simple and capable, and right now I'd say it's the best from an "it just works" perspective.

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

#93

Post by jghn » Tue, Jan 06, 2026, 6:41 PM UTC

pyuser583 wrote: post #84

Opus 4.5 burns through tokens really fast.

I've been noticing it's more on par with sonnet these days. I don't know if that means Opus is getting more efficient, sonnet getting less efficient, or perhaps Opus is getting to the answer fast enough to overcome the higher token spend.

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

#94

Post by NewsaHackO » Tue, Jan 06, 2026, 6:41 PM UTC

mpalmer wrote: post #39

After reading that article, I see at least one thing that Opus 4.5 is clearly not going to change. There is no fixed truth regarding what an "app" is, does, or looks like. Let alone the device it runs on or the technology it uses. But to an LLM, there are only fixed truths (and in my experience, only three or four possible families of design for an application). Opus 4.5 produces correct code more often, but when the…

>the code will continue to be boring.

Why would you not want you code to be boring?

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

#95

Post by AstroBen » Tue, Jan 06, 2026, 6:42 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…

my issue hasn't been for a long time now that the code they write works or doesn't work. My issues all stem from that it works, but does the wrong thing

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

#96

Post by stantonius » Tue, Jan 06, 2026, 6:42 PM UTC

_se wrote: post #50

It's always fun to ask Opus what it thinks about articles like this. Here's what I got with no history or system prompt: https://burkeholland.github.io/posts/opus-4-5-change-everyth... Read this article and ultrathink critically about it. Provide your perspective. The article makes a strong experiential case for improved velocity in AI-assisted development but contains several argumentation weaknesses and conflations…

There's something eerily recursive about Opus 4.5’s sensible take calming the anxiety about Opus 4.5’s capabilities and impact. It's probably the right take, but I feel weird the most pragmatic response to this article is from said model.

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

#97

Post by gingersnap » Tue, Jan 06, 2026, 6:42 PM UTC

Yoric wrote: post #88

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…

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.

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

#98

Post by codepoet80 » Tue, Jan 06, 2026, 6:44 PM UTC

nikisil80 wrote: post #11

[flagged]

I don't think you've used it. I used it intensely and mostly autonomously (with clear instructions, including how to measure good output) almost non-stop over the holidays. Its a new abstraction for programming -- it doesn't replace software developers, it gives them a more natural way to describe what they want.

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

#99

Post by square_usual » Tue, Jan 06, 2026, 6:44 PM UTC

michaelsalim wrote: post #47

Herring wrote: post #17

Me and Opus have a lot in common. We both hit our weekly limit on Monday at 10am.

I use pay as you go for this very reason, so the limit is my pocket haha. It does make me conscious to keep it under $20 per month though.

You're overpaying by a factor of 4, easily. I use `ccusage`'s statusline in claude code, and even with my personal $20/mo subscription I don't think there's been a single month where I didn't touch ~$80 of usage. I wasn't even abusing it as bad as some people tend to.

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

#100

Post by fragmede » Tue, Jan 06, 2026, 6:44 PM UTC

jghn wrote: post #77

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…

I find my sweet spot is using the Claude web app as a rubber duck as well as feeding it snippets of code and letting it help me refine the specific thing I'm doing. When I use Claude Code I find that it *can* add a tremendous amount of ability due to its ability to see my entire codebase at once, but the issue is that if I'm doing something where seeing my entire codebase would help that it blasts through my quota to…

By "the website" do you mean you're copy pasting, or are you using the code system where Anthropic clones your code from GitHub and interacts with it in a VM/container for you.