- does it understand the difference between eslint 8x and eslint 9.x? - or biome 1.x and biome 2.x ? - nah! it never will and that is why it ll never replace mid level engineers, FTFY
it does if you feed docs.
just like humans
Opus 4.5 is not the normal AI agent experience that I have had thus far
901–910 of 1001 posts
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#902Author of the post here. I appreciate the spirited debate and I agree with most of it - on both sides. It's a strange place to be where I think both arguments for and against this case make perfect sense. All I have to go on then is my personal experience, which is the only objective thing I've got. This entire profession feels stochastic these days. A few points of clarification... 1. I don't speak for anyone but my…
What do you think about the market for custom apps? Like one app, one customer? You describe future businesses as having one app/service and using AI to add more features, but you did something very different for your wife with AI and it sounds like it added a lot of value.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#903Sonnet 4.5 did it for me. Cant imagine coding without it now, and if you look at my comments from three months ago, you'll see I'm eating crow now. I easily hit >10x productivity with Sonnet 4.5 and Opus. I use Opus for my industry C and math work and Sonnet 4.5 for my swiftui side project.
I think the gap between Sonnet 4.5 and Opus is pretty small, compared to the absolute chasm between like gpt-4.1, grok, etc. vs Sonnet.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#904The question I keep asking myself is "how feasible will any of this be when the VC money runs out?" Right now tokens are crazy cheap. Will the continue to be?
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#905Earlier quoted context omitted.
> It's pretty clear to me where this is going. The only question is how long it takes to get there. I don't think its a guarantee. all of the things it can do from that list are greenfield, they just have increasing complexity. The problem comes because even in agentic mode, these models do not (and I would argue, can not) understand code or how it works, they just see patterns and generate a plausible sounding expla…
While I do agree with you. To play the counterpoint advocate though. What if we get to the point where all software is basically created 'on the fly' as greenfield projects as needed? And you never need to have complex large long lived codebase? It is probably incredibly wasteful, but ignoring that, could it work?
That sounds like an insane way to do anything that matters.
Sure, create a one-off app to post things to your Facebook page. But a one-off app for the OS it's running on? Freshly generating the code for your bank transaction rules? Generating an authorization service that gates access to your email?
The only reason it's quick to create green-field projects is because of all these complex, large, long-lived codebases that it's gluing together. There's ample training data out there for how to use the Firebase API, the Facebook API, OS calls, etc. Without those long-lived abstraction layers, you can't vibe out anything that matters.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#906So I decided to try the revered hands-off approach and have Claude Code create me a small tool in JS for *.dylib bundle consolidation on macOS.
I have used AskUserQuestionTool to complete my initial spec. And then Opus 4.5 created the tool according to that extensive and detailed spec.
It appeared to work out of the box.
Boy how horrific was the code. Unnecessary recursions, unused variables, data structures being built with no usage, deep branch nesting and weird code that is hard to understand because of how illogical it is.
And yes, it was broken on many levels and did not and could not do the job properly.
I then had to rewrite the tool from scratch and overall I have definitely spent more time spec'ing and understanding Claude code than if I have just written this tool from scratch initially.
Then I tried again for a small tool I needed to run codesign in parallel: https://github.com/egorFiNE/codesign-parallel
Same thing. Same outcome, had to rewrite.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#907Earlier quoted context omitted.
I made a similar comment on a different thread, but I think it also fits here: I think the disconnect between engineers is due to their own context. If you work with frontend applications, specially React/React Native/HTML/Mobile, your experience with LLMs is completely different than the experience of someone working with OpenGL, io_uring, libev and other lower level stuff. Sure, Opus 4.5 can one shot Windows utilit…
I'll second this. I'm making a fairly basic iOS/Swift app with an accompanying React-based site. I was able to vibe-code the React site (it isn't pretty, but it works and the code is fairly decent). But I've struggled to get the Swift code to be reliable. Which makes sense. I'm sure there's lots of training data for React/HTML/CSS/etc. but much less with Swift, especially the newer versions.
I hate "vibe code" as a verb. May I suggest "prompt" instead? "I was able to prompt the React site…."
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#908The question I keep asking myself is "how feasible will any of this be when the VC money runs out?" Right now tokens are crazy cheap. Will the continue to be?
No, they will get even cheaper.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#909So I decided to try the revered hands-off approach and have Claude Code create me a small tool in JS for *.dylib bundle consolidation on macOS. I have used AskUserQuestionTool to complete my initial spec. And then Opus 4.5 created the tool according to that extensive and detailed spec. It appeared to work out of the box. Boy how horrific was the code. Unnecessary recursions, unused variables, data structures being bu…
That’s the opposite of my experience. Weird. But I’m also not the kind of person who gets hung up on whether someone used a loop or recursion or if their methods are five times as long as what I would’ve done myself unless there is a performance impact that matters to me as a user. But I’m also the kind of person who doesn’t get paid by the hour to write programs. I use programs in the service of other paid work.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#910Most 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'm at the point where I say fuck it, let them sleep. The tech industry just went through an insane hiring craze and is now thinning out. This will help to separate the chaff from the wheat. I don't know why any company would want to hire "tech" people who are terrified of tech and completely obstinate when it comes to utilizing it. All the people I see downplaying it take a half-assed approach at using it then dispa…
Not entirely disagreeing with your point but I think they've mostly been forced to pivot recently for their own sakes; they will never say it though. As much as they may seem eager the most public people tend to also be better at outside communication and knowing what they should say in public to enjoy more opportunities, remain employed or for the top engineers to still seem relevant in the face of the communities they are a part of. Its less about money and more about respect there I think.
The "sudden switch" since Opus 4.5 when many were saying just a few months ago "I enjoy actual coding" but now are praising LLM's isn't a one off occurrence. I do think underneath it is somewhat motivated by fear; not for the job however but for relevance. i.e. its in being relevant to discussions, tech talks, new opportunities, etc.