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

121–130 of 1001 posts

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

#121

Post by blahblaher »

OldGreenYodaGPT wrote: post #49
hoten wrote: post #40

Earlier quoted context omitted.

Mind sharing the bill for all that?

My company pays for the team Claude code plan which is like $200 a month for each dev. The workflows cost like 10 - 50 cents a PR

It will have to quintuple or more to make business sense for Anthropic. Sure, still cheaper than a full time developer, but don't expect it to stay at $200 for a long time. And then, when you explain to your boss how amazing it is, and can do all this work so easily and quickly, it's when your boss start asking the real question: what am I paying you for?

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

#122

Post by moltar »

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…

If anyone is excited about, and has experience with this kind of stuff, please DM. I have a role open for setting up these kinds of tools and workflows.

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

#123

Post by Papazsazsa »

NewsaHackO wrote: post #18
Papazsazsa wrote: post #12

"Opus 4.5 feels to me like" The article is fine opinion but at what point are we going to either: a) establish benchmarks that make sense and are reliable , or b) stop with the hypecycle stuff?

>establish benchmarks that make sense and are reliable How aren't current LLM coding benchmarks reliable?

They're manipulated.

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

#124

Post by Loeffelmann »

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…

Why do all these AI generated readmes have a directory structure sections it's so redundant because you know I could just run tree

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

#125

Post by ac29 »

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…

> What do you mean by "have it learn your conventions"?

I'll give you an example: I use ruff to format my python code, which has an opinionated way of formatting certain things. After an initial formatting, Opus 4.5, without prompting, will write code in this same style so that the ruff formatter almost never has anything to do on new commits. Sonnet 4.5 is actually pretty good at this too.

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

#126

Post by fragmede »

adriand wrote: post #53
ChrisbyMe wrote: post #6

Mm this is my experience as well, but I'm not particularly worried about software engineering a whole. If anything this example shows that these cli tools give regular devs much higher leverage. There's a lot of software labor that is like, go to the lowest cost country, hire some mediocre people there and then hire some US guy to manage them. That's the biggest target of this stuff, because now that US guy can just…

> If anything this example shows that these cli tools give regular devs much higher leverage. This is also my take. When the printing press came out, I bet there were scribes who thought, "holy shit, there goes my job!" But I bet there were other scribes who thought, "holy shit, I don't have to do this by hand any more?!" It's one thing when something like weaving or farming gets automated. We have a finite need for…

There was a previous edit that made reference to the water usage of AI datacenter that I'm responding to.

If AI datacenters' hungry need for energy gets us to nuclear power, which gets us the energy to run desalination plants as the lakes dry up because the Earth is warming, hopefully we won't die of thirst.

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

#127

Post by biammer »

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…

[flagged]

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

#128

Post by Gud »

biammer wrote: post #127
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…

[flagged]

Frankly, in this comment thread you appear to be the oppressor.

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

#129

Post by bakies »

Loeffelmann wrote: post #124
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…

Why do all these AI generated readmes have a directory structure sections it's so redundant because you know I could just run tree

comments? also reading into an agent so the agent doesnt have to tool-call/bash out

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

#130

Post by Snuggly73 »

Ok, if its almighty, then why is not the benchmarks at 100%? If you look at the individual issues, those are somewhat small and trivial changes in existing codebases.

https://swe-rebench.com/

(note that if you look at individual slices, Opus is getting often outperformed by Sonnet).

Post reply on HN