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

731–740 of 1001 posts

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

#731

Post by scotty79 »

nine_k wrote: post #438
whynotminot wrote: post #416

Earlier quoted context omitted.

> The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily understood way, in a way that's easily extensible. You’re talking like in the year 2026 we’re still writing code for future humans to understand and improve. I fear we are not doing that. Right now, Opus 4.5 is writing code that later Opus 5.0 will refactor and extend. And so on.

This sounds like magical thinking. For one, there are objectively detrimental ways to organize code: tight coupling, lots of mutable shared state, etc. No matter who or what reads or writes the code, such code is more error-prone, and more brittle to handle. Then, abstractions are tools to lower the cognitive load. Good abstractions reduce the total amount of code written, allow to reason about the code in terms of t…

> For one, there are objectively detrimental ways to organize code: tight coupling, lots of mutable shared state, etc. No matter who or what reads or writes the code, such code is more error-prone, and more brittle to handle.

Guess what, AIs don't like that as well because it makes harder for them to achieve the goal. So with minimal guidance, which at this point could probably be provided by AI as well, the output of AI agent is not that.

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

#732

Post by scotty79 »

fenwick67 wrote: post #336
multisport wrote: post #320

What bothers me about posts like this is: mid-level engineers are not tasked with atomic, greenfield projects. If all an engineer did all day was build apps from scratch, with no expectation that others may come along and extend, build on top of, or depend on, then sure, Opus 4.5 could replace them. The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily unde…

Another thing that gets me with projects like this, there are already many examples of image converters, minesweeper clones etc that you can just fork on GitHub, the value of the LLM here is largely just stripping the copyright off

Have you ever tried to find software for a specific need? I usually spend hours investigating anything I can find only to discover that all options are bad in one way or another and cover my use case partially at best. It's dreadful, unrewarding work that I always fear. Being able to spent those hours to develop custom solution that has exactly what I need, no more, no less, that I can evolve further as my requirements evolve, all that while enjoying myself, is a godsend.

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

#733

Post by danfritz »

Every time I see a post like this on HN I try again and every time I come to the same conclusion. I have never see one agent managing to pull something off that I could instantly ship. It still ends up being very junior code.

I just tried again and ask Opus to add custom video controls around ReactPlayer. I started in Plan mode which looked overal good (used our styling libs, existing components, icons and so on).

I let it execute the plan and behold I have controls on the video, so far so good. I then look at the code and I see multiple issues: Over usage of useEffect for trivial things, storing state in useState which should be computed at run time, failing to correctly display the time / duration of the video and so on...

I ask follow up question like: Hide the controls after 2 seconds and it starts introducing more useEffects and states which all are not needed (granted you need one).

Cherry on the cake, I asked to place the slider at the bottom and the other controls above it, it placed the slider on the top...

So I suck at prompting and will start looking for a gardening job I guess...

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

#734

Post by jf22 »

danfritz wrote: post #733

Every time I see a post like this on HN I try again and every time I come to the same conclusion. I have never see one agent managing to pull something off that I could instantly ship. It still ends up being very junior code. I just tried again and ask Opus to add custom video controls around ReactPlayer. I started in Plan mode which looked overal good (used our styling libs, existing components, icons and so on). I…

So? Getting a months' worth of junior level code in an hour is still unbelievable.

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

#735

Post by danfritz »

jf22 wrote: post #734
danfritz wrote: post #733

Every time I see a post like this on HN I try again and every time I come to the same conclusion. I have never see one agent managing to pull something off that I could instantly ship. It still ends up being very junior code. I just tried again and ask Opus to add custom video controls around ReactPlayer. I started in Plan mode which looked overal good (used our styling libs, existing components, icons and so on). I…

So? Getting a months' worth of junior level code in an hour is still unbelievable.

Whats the improvement here? I spend more time fixing it then doing it myself anyways. And I have less confidence in the code Opus generates

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

#736

Post by mcfedr »

bayindirh wrote: post #677
redhale wrote: post #673

Earlier quoted context omitted.

Not necessarily responding to you directly, but I find this take to be interesting, and I see it every time an article like this makes the rounds. Starting back in 2022/2023: - (~2022) It can auto-complete one line, but it can't write a full function. - (~2023) Ok, it can write a full function, but it can't write a full feature. - (~2024) Ok, it can write a full feature, but it can't write a simple application. - (~2…

Well, the first 90% is easy, the hard part is the second 90%. Case in point: Self driving cars. Also, consider that we need to pirate the whole internet to be able to do this, so these models are not creative. They are just directed blenders.

i like to think of LLMs as random number generators with a filter

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

#737

Post by emodendroket »

throwthrowuknow wrote: post #688
bayindirh wrote: post #677

Earlier quoted context omitted.

Well, the first 90% is easy, the hard part is the second 90%. Case in point: Self driving cars. Also, consider that we need to pirate the whole internet to be able to do this, so these models are not creative. They are just directed blenders.

Even if Opus 4.5 is the limit it’s still a massively useful tool. I don’t believe it’s the limit though for the simple fact that a lot could be done by creating more specialized models for each subdomain i.e. they’ve focused mostly on web based development but could do the same for any other paradigm.

That's a massive shift in the claim though... I don't think anyone is disputing that it's a useful tool; just the implication that because it's a useful tool and has seen rapid improvement that implies they're going to "get all the way there," so to speak.

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

#738

Post by maciejzj »

keybored wrote: post #700
maciejzj wrote: post #604

I've been on a small adventure of posting more actively on HN since the release of Gemini 3, trying to stir debate around the more “societal” aspects of what's going on with AI. Regardless of how much you value Cloud Code technically, there is no denying that it has/will have huge impact. If technology knowledge and development are commoditised and distributed via subscription, huge societal changes are going to happ…

It’s a class war where one side is publicly, openly, without reservation stating their intent to make people’s skillset built up through decades unemployable (those exact skillsets; may get some other work). The other side, meanwhile, are divided between some camps like the hardline skeptics, the people following the LLM evangelists, the one-man startup-with-LLM crowd, and the people worrying about the societal ramif…

I agree with you (and surprisingly so does Warren Buffet [1] if anyone doubts it). To add insult to the injury, I believe that people have lost some sense of basic self preservation instinct. Well being of ordinary people is being directly threatened and all that average person can do is to pick one of several social media camp identities you mentioned and hope that it will somehow pan out for them, while in fact they are at total mercy of the capricious owners class.

[1]: https://www.youtube.com/watch?v=yMD17EIk22c

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

#739

Post by scotty79 »

inopinatus wrote: post #369
throwaway173738 wrote: post #351

Earlier quoted context omitted.

It matters for all the things you’d be able to justify paying a programmer for. What’s about to change is that there will be tons of these little one-off projects that previously nobody could justify paying $150/hr for. A mass democratization of software development. We’ve yet to see what that really looks like.

We already know what that looks like, because PHP happened.

Right. Basically cambrian explosion of internet that spawned things like Facebook and WordPress.

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

#740

Post by shnpln »

I have used Claude Code for a variety of hobby projects. I am truly astounded at its capabilities.

If you tell it to use linters and other kinds of code analysis tools it takes it to the next level. Ruff for Python or Clippy for Rust for example. The LLM makes so much code so fast and then passes it through these tools and actually understands what the tools say and it goes and makes the changes. I have created a whole tool chain that I put in a pre commit text file in my repos and tell the LLM something like "Look in this text file and use every tool you see listed to improve code quality".

That being said, I doubt it can turn a non-dev into a dev still, it just makes competent devs way better still.

I still need to be able to understand what it is doing and what the tools are for to even have a chance to give it the guardrails it should follow.

Post reply on HN