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

981–990 of 1001 posts

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

#981

Post by ben-gy »

noworriesnate wrote: post #701
ben-gy wrote: post #695

I second this article - I built twelve iOS/Mac apps in two weeks with Opus 4.5 - four of them are already in the App Store - I’m a Rails Engineer and never had the time to learn Swift but man does Opus 4.5 make that not even matter - it even handles entitlements, logo & splash screen generation, refactors to remove dead code, edge case assent and hardening, Multiplatform app design, and more - I’m yet to run into a u…

Are there a lot of manual steps in managing an xcode project? E.g. does it say "now go into xcode and change this setting" instead of changing the setting directly? Or are you using a tool like xcodegen?

Very few - the only manual things I do are; - clicking the distribute button to push the bundle to the App Store - filling in the compliance survey and App Store listing content - linking some components together e.g. for creating a VPN installer and tunnel i had to click some things in the Xcode UI I automate as much as possible; -“create 12 app icons for this in SVG and present them to me in a HTML page so I can choose one and then use that for the app icon and splash screen” - “create a demo mode toggle in settings and populate the app with fake data and then open up simulators for the correct image dimensions for the App Store listing so I can crate screenshots” - sometimes it tell me I have to other things like set up the entitlements to which is say “no - you do it and don’t forget to fill in the description that gets shown to the user so the feature actually works” I knew very little about Swift or Xcode profile to this and TBH I still don’t know that much about it, but I’m experienced enough to know when I’m being fed something that doesn’t look or feel right programmatically or architecturally.

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

#982

Post by ben-gy »

firemelt wrote: post #977
ben-gy wrote: post #695

I second this article - I built twelve iOS/Mac apps in two weeks with Opus 4.5 - four of them are already in the App Store - I’m a Rails Engineer and never had the time to learn Swift but man does Opus 4.5 make that not even matter - it even handles entitlements, logo & splash screen generation, refactors to remove dead code, edge case assent and hardening, Multiplatform app design, and more - I’m yet to run into a u…

what claude plan are u on?

Max

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

#983

Post by ben-gy »

bookmark99 wrote: post #835
ben-gy wrote: post #695

I second this article - I built twelve iOS/Mac apps in two weeks with Opus 4.5 - four of them are already in the App Store - I’m a Rails Engineer and never had the time to learn Swift but man does Opus 4.5 make that not even matter - it even handles entitlements, logo & splash screen generation, refactors to remove dead code, edge case assent and hardening, Multiplatform app design, and more - I’m yet to run into a u…

Can you please share the links to these apps in the app store?

https://apps.apple.com/au/app/events-canberra/id6756598656 - you can access the other ones by clicking the developer name in the listing

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

#984

Post by ben-gy »

thesabreslicer wrote: post #862
ben-gy wrote: post #695

I second this article - I built twelve iOS/Mac apps in two weeks with Opus 4.5 - four of them are already in the App Store - I’m a Rails Engineer and never had the time to learn Swift but man does Opus 4.5 make that not even matter - it even handles entitlements, logo & splash screen generation, refactors to remove dead code, edge case assent and hardening, Multiplatform app design, and more - I’m yet to run into a u…

how did you use Opus to build the apps? I tried using Claude Code ~6 months ago to build an iOS app and I was not that impressed with the results, especially compared to this blog post, where the apps look polished and very professional. My biggest issue was limitations around how Claude Code could change Xcode settings and verify design elements in the simulator.

Opus 4.5 got released ~3 months ago - Claude Code started using it automatically (for me anyway) - I also tried iOS prior to that and had a similar experience to you

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

#985

Post by tinodb »

andrekandre wrote: post #940
megalomanu wrote: post #743

Earlier quoted context omitted.

Never tried coderabbit, just because this is already good enough with Claude Code. It helped us to catch dozens of important issues we wouldn't have caught. We gave some instructions in the CLAUDE.md doc in the repository - with including a nice personalized roast of the engineer that did the review in the intro and conclusion to make it fun! :) Basically, when you do a "create PR" from your Claude Code, it will help…

thanks for the reply, yea we have a claude.md file, but coderabbit doesn't seem to pick it up or ignore it... hmmm wish we could try out claude code.

Codex is even better in my experience at reviewing. You can find the prompt it uses in the repo

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

#986

Post by johndough »

josu wrote: post #411
mcv wrote: post #133

Opus 4.5 ate through my Copilot quota last month, and it's already halfway through it for this month. I've used it a lot, for really complex code. And my conclusion is: it's still not as smart as a good human programmer. It frequently got stuck, went down wrong paths, ignored what I told it to do to do something wrong, or even repeat a previous mistake I had to correct. Yet in other ways, it's unbelievably good. I ca…

>So my verdict is that it's great for code analysis, and it's fantastic for injecting some book knowledge on complex topics into your programming, but it can't tackle those complex problems by itself. I don't think you've seen the full potential. I'm currently #1 on 5 different very complex computer engineering problems, and I can't even write a "hello world" in rust or cpp. You no longer need to know how to write co…

All the naysayer here have clearly no idea. Your large matrix multiplication implementation is quite impressive! I have set up a benchmark loop and let GPT-5.1-Codex-Max experiment for a bit (not 5.2/Opus/Gemini, because they are broken in Copilot), but it seems to be missing something crucial. With a bit of encouragement, it has implemented:

    - padding from 2000 to 2048 for easier power-of-two splitting
    - two-level Winograd matrix multiplication with tiled matmul for last level
    - unrolled AVX2 kernel for 64x64 submatrices
    - 64 byte aligned memory
    - restrict keyword for pointers
    - better compiler flags (clang -Ofast -march=native -funroll-loops -std=c++17)
But yours is still easily 25 % faster. Would you be willing to write a bit about how you set up your evaluation and which tricks Claude used to solve it?

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

#987

Post by lomase »

qingcharles wrote: post #831
lomase wrote: post #590

Earlier quoted context omitted.

Can you show us that amazing 10/10 app?

It's a not very exciting C# command-line app that takes a PDF and emits it as a sprite sheet with a text file of all the pixel positions of each page :)

[flagged]

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

#988

Post by michael_forrest »

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…

This! I can count on one hand the number of times I've had a chance to spin up a greenfield project, prototype or proof of concept in my 30 year career. Those were always stolen moments, and the bottleneck was never really coding ability. Most professional software development is wading through janky codebases of others' (or your own) creation, trying to iron out weird little glitches of the kind that LLMs can now generate on an industrial scale (and are incapable of fixing).

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

#989

Post by josu »

johndough wrote: post #986
josu wrote: post #411

Earlier quoted context omitted.

>So my verdict is that it's great for code analysis, and it's fantastic for injecting some book knowledge on complex topics into your programming, but it can't tackle those complex problems by itself. I don't think you've seen the full potential. I'm currently #1 on 5 different very complex computer engineering problems, and I can't even write a "hello world" in rust or cpp. You no longer need to know how to write co…

All the naysayer here have clearly no idea. Your large matrix multiplication implementation is quite impressive! I have set up a benchmark loop and let GPT-5.1-Codex-Max experiment for a bit (not 5.2/Opus/Gemini, because they are broken in Copilot), but it seems to be missing something crucial. With a bit of encouragement, it has implemented: - padding from 2000 to 2048 for easier power-of-two splitting - two-level W…

Thank you. Yeah, I'm doing all those things, which do get you close to the top. The rest of things I'm doing are mostly micro-optimizations such as finding a way to avoid AVX→SSE transition penalty (1-2% improvement).

But I don't want to spoil the fun. The agents are really good at searching the web now, so posting the tricks here is basically breaking the challenge.

For example, chatGPT was able to find Matt's blog post regarding Task 1, and that's what gave me the largest jump: https://blog.mattstuchlik.com/2024/07/12/summing-integers-fa...

Interestingly, it seems that Matt's post is not on the training data of any of the major LLMs.

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

#990

Post by yourapostasy »

gleenn wrote: post #520
yourapostasy wrote: post #384

Earlier quoted context omitted.

> ...multiple engineers argued about the "right" way to build something. I remember thinking that they had biases based on past experiences and assumptions about what mattered. I usually resolve this by putting on the table the consequences and their impacts upon my team that I’m concerned about, and my proposed mitigation for those impacts. The mitigation always involves the other proposer’s team picking up the impa…

That's awesome, but I feel like half the time most people aren't in the position to add requirements so a lot of shenanigans still happens, especially in big corps

I am satisfied when someone tells us we cannot change requirements, to get their acknowledgement that what we bring up does extract a specific trade-off, and their reason for accepting the trade-off, then recording it into design and operational documentation. The moment many people recognize this trade-off will be explicitly documented with their and their team's accountability in detail, is when you surface genuine trade-offs made with the debt to pay off in the future in mind and in the meantime a rationale to grant a ton of leeway to the team burdened with the externality going forward, and trade-offs made without understanding their externalities upon other teams (which happens a tremendous amount in large organizations).

Most of the time, people are just very reasonably and understandably focusing tightly on their lane and honestly had no idea of the externalities of their conclusions and decisions, and I'm happy to have experienced all those times a rebalancing of the trade-offs that everyone can accept and is grateful to have documented to justify spending the story points upon cleaning up later instead of working on new features while the externality debt's unwanted impact keeps piling up.

In fewer than a handful of times, I run into people deliberately, consciously with malice aforethought of the full externalities making trade-offs for the sake of expediently shifting burdens of of them without first consulting with partner teams they want to shift the burdens onto, simply so they can fatten their promo packet sooner at the expense of making other teams look worse. Getting these trade-offs documented about half the time makes them back down to a more reasonable trade-off, about half the time they don't back down but your team is now protected by explicit documentation and caveats upon the externality your team now has to carry, and 100% of the time my team and I put a ring fence upon all future interactions with that personality for at least the remaining duration of my gig.

Post reply on HN