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

191–200 of 1001 posts

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

#191

Post by simonw »

krackers wrote: post #176
simonw wrote: post #153

Opus 4.5 really is something else. I've been having a ton of fun throwing absurdly difficult problems at it recently and it keeps on surprising me. A JavaScript interpreter written in Python? How about a WebAssembly runtime in Python? How about porting BurntSushi's absurdly great Rust optimized string search routines to C and making them faster ? And these are mostly just casual experiments, often run from my phone!

>A JavaScript interpreter written in Python? I'm assuming this refers to the python port of Bellard's MQJS [1]? It's impressive and very useful, but leaving out the "based on mqjs" part is misleading. [1] https://github.com/simonw/micro-javascript ?

That's why I built the WebAssembly one - the JavaScript one started with MQJS, but for the WebAssembly one I started with just a copy of the https://github.com/webassembly/spec repo.

I haven't quite got the WASM one into a share-able shape yet though - the performance is pretty bad which makes the demos not very interesting.

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

#192

Post by burntsushi »

simonw wrote: post #174
burntsushi wrote: post #165

Earlier quoted context omitted.

> How about porting BurntSushi's absurdly great Rust optimized string search routines to C and making them faster? How did it do? :-)

Alarmingly well! https://gisthost.github.io/?1bf98596a83ff29b15a2f4790d71c41d... It couldn't quite beat the Rust implementation on everything, but it managed to edge it out on at least some of the benchmarks it wrote for itself. (Honestly it feels like a bit of an afront to the natural order of things.) That said... I'm most definitely not a Rust or C programmer. For all I know it cheated at the benchmarks and I didn…

Nice. Yeah I'd have to actually look at what it did. For the task of substring search, it's extremely easy to fall into a local optima. The `memchr` crate has oodles of benchmarks, and some of them are very much in tension with others. It's easy to do well on one to the expense of others.

But still, very neat.

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

#193

Post by idiotsecant »

spaceman_2020 wrote: post #161
biammer wrote: post #127

Earlier quoted context omitted.

[flagged]

It's a little weird how defensive people are about these tools. Did everyone really think being able to import a few npm packages, string together a few APIs, and run npx create-react-app was something a large number of people could do forever? The vast majority of coders in employment barely write anything more complex than basic CRUD apps. These jobs were always going to be automated or abstracted away sooner or la…

Agreed, it always seemed a little crazy that you could make wild amounts of money to just write software. I think the music is finally stopping and we'll all have to go back to actually knowing how to do something useful.

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

#194

Post by jack_pp »

oncallthrow wrote: post #114
Yoric wrote: post #88

Earlier quoted context omitted.

You intrigue me. > have it learn your conventions, pull in best practices What do you mean by "have it learn your conventions"? Is there a way to somehow automatically extract your conventions and store it within CLAUDE.md? > For example, we have a custom UI library, and Claude Code has a skill that explains exactly how to use it. Same for how we write Storybooks, how we structure APIs, and basically how we want ever…

When I ask Claude to do something, it independently, without me even asking or instructing it to, searches the codebase to understand what the convention is. I’ve even found it searching node_modules to find the API of non-public libraries.

This sounds like it would take a huge amount of tokens. I've never used agents so could you disclose how much you pay for it?

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

#195

Post by keybored »

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…

> (used voice to text then had claude reword, I am lazy and not gonna hand write it all for yall sorry!)

Reword? But why not just voice to text alone...

Oh but we all read the partially synthetic ad by this point. Psyche.

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

#196

Post by ethbr1 »

Workaccount2 wrote: post #61

Anthropic dropped out of the general "AGI" race and seems to be purely focused on coding, maybe racing to get the first "automated machine learning programmer". Whatever the case, it seems to be paying (coding) dividends to just be focusing on coding.

The benefit of focusing on coding is that it has an attractive non-deterministic / deterministic problem split.

In that it's using a non-deterministic machine to build a deterministic one.

Which gives all the benefits of determinism in production, with all the benefits of non-deterministic creativity in development.

Imho, Anthropic is pretty smart in picking it as a core focus.

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

#197

Post by lawlessone »

soulofmischief wrote: post #179

Opus 4.5 is currently helping me write a novel, comprehensive and highly performant programming language with all of the things I've ever wanted, done in exactly my opinionated way. This project would have taken me years of specialization and research to do right. Opus's strength has been the ability to both speak broadly and also drill down into low-level implementations. I can express an intent, and have some discu…

Why would anyone buy the novel?

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

#198

Post by ryandrake »

spaceman_2020 wrote: post #54
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 really think a lof of people tried AI coding earlier, got frustrated at the errors and gave up. That's where the rejection of all these doomer predictions comes from. And I get it. Coding with Claude Code really was prompting something, getting errors, and asking it to fix it. Which was still useful but I could see why a skilled coder adding a feature to a complex codebase would just give up Opus 4.5 really is at a…

This was me. I was a huge AI coding detractor on here for a while (you can check my comment history). But, in order to stay informed and not just be that grouchy curmudgeon all the time, I kept up with the models and regularly tried them out. Opus 4.5 is so much better than anything I've tried before, I'm ready to change my mind about AI assistance.

I even gave -True Vibe Coding- a whirl. Yesterday, from a blank directory and text file list of requirements, I had Opus 4.5 build an Android TV video player that could read a directory over NFS, show a grid view of movie poster thumbnails, and play the selected video file on the TV. The result wasn't exactly full-featured Kodi, but it works in the emulator and actual device, it has no memory leaks, crashes, ANRs, no performance problems, no network latency bugs or anything. It was pretty astounding.

Oh, and I did this all without ever opening a single source file or even looking at the proposed code changes while Opus was doing its thing. I don't even know Kotlin and still don't know it.

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

#199

Post by haolez »

I have a different concern: the SOTA products are expensive and get dumbed down on busy times. My personal strategy has been to be a late follower, where I adopt new AI tools when the competition has caught up with the previous SOTA, and now there are many tools that are cost effective and equally good.

Can't wait for when the competition catches up with Claude Code, especially the open source/weights Chinese alternatives :)

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

#200

Post by UncleMeat »

ac29 wrote: post #125
Yoric wrote: post #88

Earlier quoted context omitted.

You intrigue me. > have it learn your conventions, pull in best practices What do you mean by "have it learn your conventions"? Is there a way to somehow automatically extract your conventions and store it within CLAUDE.md? > For example, we have a custom UI library, and Claude Code has a skill that explains exactly how to use it. Same for how we write Storybooks, how we structure APIs, and basically how we want ever…

> What do you mean by "have it learn your conventions"? I'll give you an example: I use ruff to format my python code, which has an opinionated way of formatting certain things. After an initial formatting, Opus 4.5, without prompting, will write code in this same style so that the ruff formatter almost never has anything to do on new commits. Sonnet 4.5 is actually pretty good at this too.

Isn't this a meaningless example? Formatters already exist. Generating code that doesn't need to be formatted is exactly the same as generating code and then formatting it.

I care about the norms in my codebase that can't be automatically enforced by machine. How is state managed? How are end-to-end tests written to minimize change detectors? When is it appropriate to log something?

Post reply on HN