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

101–110 of 1001 posts

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

#101

Post by minimaxir »

nikisil80 wrote: post #90
matusp wrote: post #15

Earlier quoted context omitted.

This is a natural response to software enshittification. You can hardly find an iOS app that is not plagued by ads, subscriptions, or hostile data collection. Now you can have your own small utilities that can work for you. This sort of personal software might be very valuable in the world where you are expected to pay 5$ to click any button.

Yeah sure but have you considered that the actual cost of running these models is actually much greater than whatever cost you might be shelling out for the ad-free apps? You're talking to someone who hates the slopification and enshittification of everything, so you don't need to convince me about that. However, everything I've seen described in the replies to my initial comment - while cute, and potentially helpful…

You are attempting to move the goalposts. There are two different points in this debate:

1) Modern LLMs are an inflection point for coding.

2) The current LLM ecosystem is unsustainable.

This submission discussion is only about #1, which #2 does not invalidate. Even if the ecosystem crashes, then open-source LLMs that leverage the same tricks Opus 4.5 does will just be used instead.

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

#102

Post by NitpickLawyer »

manmal wrote: post #32

IMO codex produces working code slowly, while Opus produces superficially working code quickly. I like using Opus to drive codex sessions and checking its output. Clawdbot is really good at that but a long running Claude Code session with codex as sub agents should work well also. The above is for vibe coding; for taking the wheel, I can only use Opus because I suck at prompting codex (it needs very specific instruct…

> I like using Opus to drive codex sessions and checking its output.

Why not the other way around? Have the quick brown fox churn out code, and have codex review it, guide changes, and loop?

I've actually gone one step further down the delegation. I use opus/gemini3 for plan, review, edit plan for a few steps. Then write it out to .md files. Then have GLM implement it (I got a cheap plan for like 28$ for a year on Christmas). Then have the code this produced reviewed and fixed if needed by opus. Final review by codex (for some reason it's very good at review, esp if you have solid checkboxes for it to check during review). Seems to work so far.

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

#103

Post by enum »

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 teach at a university, and spend plenty of time programming for research and for fun. Like many others, I spent some time on the holidays trying to push the current generation of Cursor, Claude Code, and Codex as far as I could. (They're all very good.)

I had an idea for something that I wanted, and in five scattered hours, I got it good enough to use. I'm thinking about it in a few different ways:

1. I estimate I could have done it without AI with 2 weeks full-time effort. (Full-time defined as >> 40 hours / week.)

2. I have too many other things to do that are purportedly more important that programming. I really can't dedicate to two weeks full-time to a "nice to have" project. So, without AI, I wouldn't have done it at all.

3. I could hire someone to do it for me. At the university, those are students. From experience with lots of advising, a top-tier undergraduate student could have achieved the same thing, had they worked full tilt for a semester (before LLMs). This of course assumes that I'm meeting them every week.

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

#104

Post by savanaly »

dmbche wrote: post #34
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…

Oh! An ad!

The most effective kind of marketing is viral word of mouth from users who love your product. And Claude Code is benefiting from that dynamic.

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

#105

Post by manmal »

adriand wrote: post #22
LatencyKills wrote: post #5

I really wonder what means for software moving forward. In the last few months I've used Claude Code to build personalized versions of Superwhisper (voice-to-text), CleanShot X (screenshot and image markup), and TextSniper (image to text). The only cost was some time and my $20/month subscription.

> I really wonder what means for software moving forward. It means that it is going to be as easy to create software as it is to create a post on TikTok, and making your software commercially successful will be basically the same task (with the same uncontrollable dynamics) as whether or not your TikTok post goes viral.

Is that new though? Software has been hype and marketing driven forever.

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

#106

Post by vercaemert »

enum wrote: post #103
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 teach at a university, and spend plenty of time programming for research and for fun. Like many others, I spent some time on the holidays trying to push the current generation of Cursor, Claude Code, and Codex as far as I could. (They're all very good.) I had an idea for something that I wanted, and in five scattered hours, I got it good enough to use. I'm thinking about it in a few different ways: 1. I estimate I…

How do you compare Claude Code to Cursor? I'm a Cursor user quietly watching the CC parade with curiosity. Personally, I haven't been able to give up the IDE experience.

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

#107

Post by jghn »

fragmede wrote: post #100
jghn wrote: post #77

Earlier quoted context omitted.

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.

Just pasting code snippets, and occasionally an entire file or two into the main claude.com site. I usually already know what I want and need, but just want to speed up the process on how to get there, and perhaps I missed something in the process.

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

#108

Post by 6177c40f »

pseidemann wrote: post #91
6177c40f wrote: post #72

Earlier quoted context omitted.

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?

More indirection in the sense that there's a layer between you and the code, sure. Less in that the code doesn't really matter as such and you're not having to think hard about the minutiae of programming in order to make something you want. It's very possible that "AI-oriented" programming languages will become the standard eventually (at least for new projects).

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

#109

Post by oncallthrow »

Yeah Opus 4.5 is a massive step change in my experience. I feel like I’m working with a peer, not a junior I’m having to direct. I can give it highly ambiguous and poorly specified tasks and it… just does it.

I will note that my experience varies slightly by language though. I’ve found it’s not as good at typescript.

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

#110

Post by oncallthrow »

honeycrispy wrote: post #26

A couple weeks ago I had Opus 4.5 go over my project and improve anything it could find. It "worked" but the architecture decisions it made were baffling, and had many, many bugs. I had to rewrite half of the code. I'm not an AI hater, I love AI for tests, finding bugs, and small chores. Opus is great for specific, targeted tasks. But don't ask it to do any general architecture, because you'll be soon to regret it.

In my experience these models (including opus) aren’t very good at “improving” existing code. I’m not exactly sure why, because the code they produce themselves is generally excellent.
Post reply on HN