Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My article on why AI is great (or terrible) or how to use it

matthewrocklin.com

Post reply on HN
Print view View original

221–230 of 241 posts

Re: My article on why AI is great (or terrible) or how to use it

#221

Post by arach »

davely wrote: post #199
arach wrote: post #146

> My personal favorite hooks though are these: "Stop": [ { "hooks": [ { "type": "command", "command": "afplay -v 0.40 /System/Library/Sounds/Morse.aiff" }]}], "Notification": [ { "hooks": [ { "type": "command", "command": "afplay -v 0.35 /System/Library/Sounds/Ping.aiff" }]}] These are nice but it's even nicer when Claude is talking when it needs your attention Easy to implement -> can talk to ElevenLabs or OpenAI an…

Hah! I’ve done something similar. I created a bunch of pre-defined voice messages with Eleven Labs and then have a script that randomly calls them via the same hooks. https://github.com/daveschumaker/homebrew-claude-sounds

nice, next step is to write a custom function that derives a useful but repeatable message from the hooks and put a little cache in front the Eleven Labs message gen. For example: "In {Project}, Claude needs your permission to run {command}"

That way you can stay comfortably in the free plan with awesome voice messages

I have a different voice for my laptop compared to my main computer and can also pick per project

Re: My article on why AI is great (or terrible) or how to use it

#222

Post by arach »

hmartin wrote: post #216
arach wrote: post #146

> My personal favorite hooks though are these: "Stop": [ { "hooks": [ { "type": "command", "command": "afplay -v 0.40 /System/Library/Sounds/Morse.aiff" }]}], "Notification": [ { "hooks": [ { "type": "command", "command": "afplay -v 0.35 /System/Library/Sounds/Ping.aiff" }]}] These are nice but it's even nicer when Claude is talking when it needs your attention Easy to implement -> can talk to ElevenLabs or OpenAI an…

If you're on a Mac, it can speak the notification instead for more detail! ``` "hooks": { "Notification": [ { "hooks": [ { "type": "command", "command": "jq '.message' | say" } ] } ] } ```

thanks man! I've actually gone a bit further with hooks and speech synthesis

https://hooked.arach.dev/ and https://speakeasy.arach.dev/ - it's a fun setup

Re: My article on why AI is great (or terrible) or how to use it

#223

Post by lazide »

michaelbuckbee wrote: post #202
lazide wrote: post #173

Earlier quoted context omitted.

For some people, code == junk?

Depends on what it is, the quick bash script I write to verify something or the core of SaaS that's being launched have different levels of strictness, style, testing, etc.

Apparently not as much anymore!

Re: My article on why AI is great (or terrible) or how to use it

#224

Post by vlod »

djeastm wrote: post #198
vlod wrote: post #129

Earlier quoted context omitted.

I've always believed that the dozens of 'bitchy little issues' are the means to grow as a developer. Once you've done it, you'll hopefully never have to do it again (or at worse be derivatives). Over time you'll have a collection of 'how to do stuff'. I think this is the path to growth. Letting a LLM do it for you is equivalent to it solving a hard leetcode problem. You're not really taxing your brain.

>Letting a LLM do it for you is equivalent to it solving a hard leetcode problem. You're not really taxing your brain. But things like "hey this array of objects I have, I need sorted by this property" are not hard leetcode problems They're precisely the kind of tedious, but not taxing, problems that we prefer to farm out to someone else. Like asking a junior to do it.

My point is that it's tempting and irresistible (based on other comments in this thread) to move from basic attribute sorting, to basic CRUD, SQL queries, CSS/Tailwind, typescript error resolution then using it for Dijkstra, because why not?, it's so nice.

Then we're just puppetmasters pulling the strings (which some think this is the way the industry is going).

Re: My article on why AI is great (or terrible) or how to use it

#225

Post by AndrewKemendo »

bdauvergne wrote: post #189

Seems people read the blog but not the code, I looked at the stated rewrite of Numpy in Rust: > As an introductory project, I rewrote Numpy in Rust. It was great fun. That's not a rewrite at all it's just a wrapping of an existing linear algebra Rust library (faer, blas, etc..) with a more Numpy like API. It seems to me that every AI project I look at is just a mashup/wrapper over existing things. Where are the real…

> Are so much people in programming implementing middleware / wrapping existing API all day that it gives them a feeling of liberation to be able to delegate those tasks ?

Yes

The overwhelming majority of production code are simply wrappers and APIs calling existing frameworks and libraries

The type of projects you’re talking about are so unbelievably rare that almost nobody starts them or makes progress on them because predominantly they are social organizations that happen to export code

Re: My article on why AI is great (or terrible) or how to use it

#226

Post by AndrewKemendo »

jascha_eng wrote: post #200
bdauvergne wrote: post #189

Seems people read the blog but not the code, I looked at the stated rewrite of Numpy in Rust: > As an introductory project, I rewrote Numpy in Rust. It was great fun. That's not a rewrite at all it's just a wrapping of an existing linear algebra Rust library (faer, blas, etc..) with a more Numpy like API. It seems to me that every AI project I look at is just a mashup/wrapper over existing things. Where are the real…

https://github.com/timescale/pg_textsearch BM25 index for postgres, mostly written by a single (very smart) guy and Claude Code.

I feel like we should pin this or something as a canonical counter to the now excruciatingly tired claim:

“Generative software code doesn’t work”

Re: My article on why AI is great (or terrible) or how to use it

#227

Post by mrocklin »

bdauvergne wrote: post #189

Seems people read the blog but not the code, I looked at the stated rewrite of Numpy in Rust: > As an introductory project, I rewrote Numpy in Rust. It was great fun. That's not a rewrite at all it's just a wrapping of an existing linear algebra Rust library (faer, blas, etc..) with a more Numpy like API. It seems to me that every AI project I look at is just a mashup/wrapper over existing things. Where are the real…

Blas and faer are used only for small corners of the API (linalg and fft) which is exactly what numpy does. I encourage you to follow your own advice and look more closely at the interaction of ufuncs, strides, and dtypes.

Re: My article on why AI is great (or terrible) or how to use it

#228

Post by bandrami »

deergomoo wrote: post #2

I will never as long as I live understand the argument that AI development is more fun. If you want to argue that you’re more capable or whatever, fine. I disagree but I don’t have any data to disprove you. But saying that AI development is more fun because you don’t have to “wrestle the computer” is, to me, the same as saying you’re really into painting but you’re not really into the brush aspect so you pay someone…

And the thing I don't get about how excited people are is that if what LLMs really do is change software development from coding to code review, which is the part of software development that is universally hated.

Re: My article on why AI is great (or terrible) or how to use it

#229

Post by bandrami »

kleinsch wrote: post #16
deergomoo wrote: post #2

I will never as long as I live understand the argument that AI development is more fun. If you want to argue that you’re more capable or whatever, fine. I disagree but I don’t have any data to disprove you. But saying that AI development is more fun because you don’t have to “wrestle the computer” is, to me, the same as saying you’re really into painting but you’re not really into the brush aspect so you pay someone…

AI lets you pick the parts you want to focus on and streamline the parts you don't. I get zero joy out of wrestling build tools or figuring out deploy scripts to get what I've built out onto a server. In the past side projects would stall out because the few hours per week I had would get consumed by all of the side stuff. Now I take care of that using AI and focus on the parts I want to write.

Has anybody tried getting an LLM to pitch them an idea for software that they then implement themselves? I might actually try that now...

Re: My article on why AI is great (or terrible) or how to use it

#230

Post by tptacek »

tqian wrote: post #210
throwup238 wrote: post #196

Earlier quoted context omitted.

> Anecdotally, we use Opus 4.5 constantly on Zed's code base, which is almost a million lines of Rust code and has over 150K active users, and we use it for basically every task you can think of - new features, bug fixes, refactors, prototypes, you name it. The code base is a complex native GUI with no Web tech anywhere in it. https://news.ycombinator.com/item?id=46522437 Zed is open source so you can look at their P…

Zed on Linux is buggy as hell. On macos it's somehow more stable. Maybe Zed is indeed a "good" example of Ai-coded products.

This is a thing you can credibly say only if you've never used a popular new non-mainline editor. Sublime Code was "buggy as hell" too; all new editors are. Editors are incredibly difficult to do well. And Zed is doing it on hard mode, cross-platform.
Post reply on HN