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

71–80 of 1001 posts

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

#71

Post by structural »

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.

Yes, but my junior coworkers also don't reliably do edge case testing for user errors either unless specifically tasked to do so, likely with a checklist of specific kinds of user errors they need to check for.

And it turns out the quality of output you get from both the humans and the models is highly correlated with the quality of the specification you write before you start coding.

Letting a model run amok within the constraints of your spec is actually great for specification development! You get instant feedback of what you wrongly specified or underspecified. On top of this, you learn how to write specifications where critical information that needs to be used together isn't spread across thousands of pages - thinking about context windows when writing documentation is useful for both human and AI consumers.

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

#72

Post by 6177c40f »

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. There's just less indirection involved now.

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

#74

Post by tannedNerd »

jonas21 wrote: post #30
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.

I can generally get maintainable results simply by telling Claude "Please keep the code as simple as possible. I plan on extending this later so readability is critical."

Yeah some of it is probably related to me primarily using it for swift ui which doesn’t have years of stuff to scrape. But even with those and even telling that ios26 exists it will still at least once a session claim it doesn’t, so it’s not 100%

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

#75

Post by orthoxerox »

Tiberium wrote: post #68
orthoxerox wrote: post #45

What's the best coding agent you can run locally? How far behind Opus 4.5 is it?

The best is probably something like GLM 4.7/Minimax M2.1, and those are probably at most Sonnet 4 level, which is behind Opus 4.1, which is behind Sonnet 4.5, which is behind Opus 4.5 ;) And honestly Opus 4.5 is a visible step change above previous Anthropic models.

Does it even fit into a 5090 or a Ryzen 395+?

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

#76

Post by koiueo »

jama211 wrote: post #41
lawlessone wrote: post #21

Earlier quoted context omitted.

It cloned one of the many open source ones available is what you mean.

To be fair that’s what I’d have done had I had to build it. Use a lot of examples etc and build on what other people have done

I assume, the purpose would be to learn how it's done. There's no place for this when you vibecode. And if not learning, what's the point of implementing something that already exists?

When I'm dying of dehydration because humanity has depleted all fresh water deposits, I'll think of you and your stupid NES emulator which is just an LLM-produced copy of many ones that had already existed.

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

#77

Post by jghn »

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 too fast. And if I'm tightly scoping it, it's just as easy & faster for me to use the website.

Because of this I've shifted back to the website. I find that I get more done faster that way.

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

#78

Post by koiueo »

waynenilsen wrote: post #9

Once you get your setup bulletproof such that you can have multiple agents running at the same time that can run unit tests and close their own loops things get even faster. However you accomplish that. Not as easy as it sounds mostly (and absurdly) due to port collision. E2E testing with playwright is another leap.

Can't you, like, ask Claude to fix port collision for you? Duh

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

#79

Post by Tiberium »

orthoxerox wrote: post #75
Tiberium wrote: post #68

Earlier quoted context omitted.

The best is probably something like GLM 4.7/Minimax M2.1, and those are probably at most Sonnet 4 level, which is behind Opus 4.1, which is behind Sonnet 4.5, which is behind Opus 4.5 ;) And honestly Opus 4.5 is a visible step change above previous Anthropic models.

Does it even fit into a 5090 or a Ryzen 395+?

Oh, of course not, you might need up to 100GB VRAM to have those models at decent speeds even just for low-quant versions.

And all the hype about Macs with unified memory is a bit dishonest because the actual generation speed will be very bad, especially if you fill the context.

One of the things that makes Opus 4.5 special in comparison to e.g. GPT 5.2 is the fact that it doesn't have to reason for multiple minutes to make some simple changes.

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

#80

Post by spaceman_2020 »

halfmatthalfcat wrote: post #66
spaceman_2020 wrote: post #58

Earlier quoted context omitted.

What's even the point of this comment if you self-admittedly don't have access to the flagship tool that everyone has been using to make these big bold coding claims?

Because the same claims of "AI tool does everything" are made over and over again.

The claims are being made for Claude Code, which you don't have access to.
Post reply on HN