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

771–780 of 1001 posts

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

#771

Post by D-Machine »

krageon wrote: post #644
hollowturtle wrote: post #641

I'm tired of constantly debating the same thing again and again. Where are the products? Where is some great performing software all LLM/agent crafted? All I see is software bloatness and decline. Where is Discord that uses just a bunch of hundreds megs of ram? Where is unbloated faster Slack? Where is the Excel killer? Fast mobile apps? Browsers and the web platform improved? Why Cursor team don't use Cursor to get…

https://www.anthropic.com/research/how-ai-is-transforming-wo... see "How much work can be fully delegated to Claude?": "Although engineers use Claude frequently, more than half said they can “fully delegate” only between 0-20% of their work to Claude" There won't be anything like you're asking for, even the vendors themselves (they'll be the most positive and most enthousiastic about using it) can't do this with them…

Thank you for linking this very useful and much more realistic / grounded stat.

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

#772

Post by nsb1 »

A lot of the complaints about these tools seems to revolve around their current lack of ability to innovate for greenfield or overly complex tasks. I would agree with this assessment in their current state, but this sentiment of "I will only use AI coding tools when they can do 100% of my job" seems short-sighted.

The fact of the matter, in my experience, is that most of the day to day software tasks done by an individual developer are not greenfield, complex tasks. They're boring data-slinging or protocol wrangling. This sort of thing has been done a thousand times by developers everywhere, and frankly there's really no need to do the vast majority of this work again when the AIs have all been trained on this very data.

I have had great success using AIs as vast collections of lego blocks. I don't "vibe code", I "lego code", telling the AI the general shape and letting it assemble the pieces. Does it build garbage sometimes? Sure, but who doesn't from time to time? I'm experienced enough notice the garbage smell and take corrective action or toss it and try again. Could there be strange crevices in a lego-coded application that the AI doesn't quite have a piece for? Absolutely! Write that bit yourself and then get on with your day.

If the only thing you use these tools for is doing simple grunt-work tasks, they're still useful, and dismissing them is, in my opinion, a mistake.

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

#773

Post by doubleorseven »

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…

usually for me, after a good plan is 90% solid working code. the problem do arise when you ask it to change the colors it choose of light grey text over a white background. this thing still can't see and it's a huge drawback for those who got used to just prompting away their problems

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

#774

Post by solumunus »

lucianbr wrote: post #761
ammut wrote: post #752

Earlier quoted context omitted.

I've spent quite a bit of time with Codex recently and come to the conclusion that you can't simply say "Let's add custom video controls around ReactPlayer." You need to follow up with a set of strict requirements to set expectations, guard rails, and what the final product should do (and not do). Even then it may have a few issues, but continuing to prompt with clearly stated problems that don't meet the requirement…

It sounds like it takes you at least 10 minutes to just write the prompt with all the details you mentioned. Especially if you need to continue and prompt again (and again?).

Not the OP but, easily. My tasks are usually taking at least that, but up to hours of brainstorming and planning, sometimes I’ll do this over days in between other tasks just so I can think about all and pros and cons. Of course this has always been the way, but now I have an ongoing Claude session which I can come back to at any point, which is holding the context along with my brain. It’s much easier to keep the thread of what I’m working on across multiple tasks.

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

#775

Post by thewillowcat »

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…

These posts are never, never made by someone who is responsible for shipping production code in a large, heavily used application. It's always someone at a director+ level who stopped production coding years ago, if they ever did, and is tired of their engineers trying to explain why something will take more than an hour.

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

#776

Post by sanderjd »

throwthrowuknow wrote: post #687
sanderjd wrote: post #685

Earlier quoted context omitted.

Yeah maybe, but personally it feels more like a plateau to me than an exponential takeoff, at the moment. And this isn't a pessimistic take! I love this period of time where the models themselves are unbelievably useful, and people are also focusing on the user experience of using those amazing models to do useful things. It's an exciting time! But I'm still pretty skeptical of "these things are about to not require…

I can agree that it doesn’t seem exponential yet but this is at least linear progression not a plateau.

Linear progression feels slower (and thus more like a plateau) to me than the end of 2022 through end of 2024 period.

The question in my mind is where we are on the s-curve. Are we just now entering hyper-growth? Or are we starting to level out toward maturity?

It seems like it must still be hyper-growth, but it feels less that way to me than it did a year ago. I think in large part my sense is that there are two curves happening simultaneously, but at different rates. There is the growth in capabilities, and then there is the growth in adoption. I think it's the first curve that seems to be to have slown a bit. Model improvements seem both amazing and also less revolutionary to me than they did a year or two ago.

But the other curve is adoption, and I think that one is way further from maturity. The providers are focusing more on the tooling now that the models are good enough. I'm seeing "normies" (that is, non-programmers) starting to realize the power of Claude Code in their own workflows. I think that's gonna be huge and is just getting started.

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

#777

Post by weitendorf »

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…

Back in the day when you found a solution to your problem on Stackoverflow, you typically had to make some minor changes and perhaps engage in some critical thinking to integrate it into your code base. It was still worth looking for those answers, though, because it was much easier to complete the fix starting from something 90% working than 0%.

The first few times in your career you found answers that solved your problem but needed non-trivial changes to apply it to your code, you might remember that it was a real struggle to complete the fix even starting from 90%. Maybe you thought that ultimately, that stackoverflow fix really was more trouble than it was worth. And then the next few times you went looking for answers on stackoverflow you were better at determining what answers were relevant to your problem/worth using, and better at going from 90% to 100% by applying their answers.

Still, nobody really uses stackoverflow anymore: https://blog.pragmaticengineer.com/stack-overflow-is-almost-...

You and most of the rest of us are all actively learning how to use their replacement

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

#778

Post by AndrewKemendo »

kaashif wrote: post #425
AndrewKemendo wrote: post #393

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. The number of production applications that achieve this rounds to zero I’ve probably managed 300 brownfield web, mobile, edge, datacenter, data processing and ML applications/products across DoD, B2B, consumer and literally zero of them were built in t…

I think there is a subjective difference. When a human builds dogshit at least you know they put some effort and the hours in. When I'm reading piles of LLM slop, I know that just reading it is already more effort than it took to write. It feels like I'm being played. This is entirely subjective and emotional. But when someone writes something with an LLM in 5 seconds and asks me to spend hours reviewing...fuck off.

Your comment doesn’t address what I said and instead finds a new reason that it’s invalid because “reviewing code from a machine system is beneath me”

Get over yourself

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

#779

Post by encyclopedism »

literalAardvark wrote: post #696
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.

They're not blenders. This is clear from the fact that you can distill the logic ability from a 700b parameter model into a 14b model and maintain almost all of it. You just lose knowledge, which can be provided externally, and which is the actual "pirated" part. The logic is _learned_

It hasn't learned any LOGIC. It has 'learned' patterns from the input.

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

#780

Post by hollowturtle »

weitendorf wrote: post #763
hollowturtle wrote: post #641

I'm tired of constantly debating the same thing again and again. Where are the products? Where is some great performing software all LLM/agent crafted? All I see is software bloatness and decline. Where is Discord that uses just a bunch of hundreds megs of ram? Where is unbloated faster Slack? Where is the Excel killer? Fast mobile apps? Browsers and the web platform improved? Why Cursor team don't use Cursor to get…

Except for maybe an "Excel killer", all those things you listed are not things people are willing to pay for. Also agents are bad at that kind of work (most devs are bad at that stuff, it's why it was something people whined about even before agents). And funnily enough there are products and tools that are essentially less bloated slack/discord. Have you heard of https://stoat.chat/ (aka revolt) or https://pumble.co…

Wrt statue.dev good luck for sure with the project but I personally don't need yet another static site generator, nextjs like but with unpopular svelte, bloated with tons of node modules creating another black hole impossible to escape from. If agents works this well why would I need to use your library? I just tell an agent to maintain my static site who cares which tech stack
Post reply on HN