Hacker Newsnew | past | comments | ask | show | jobs | submit | airstrike's commentslogin

I can relate so much to this comment I need to check my house's CO2 level to make sure I didn't write it

Well, the only difference is I'm allergic to Go and just use Rust 99% of the time these days


> is I'm allergic to Go and just use Rust 99% of the time these days

I confess I have not used Go. I am allergic to Typescript, let alone, Javascript, and Node.js should be deleted.

I do mostly real-time audio, so I too am Rust (job control in Shell). But what decent choices are there for garbage collected systems?

And garbage collection, for most systems, is crucial


Leptos etc. WASM is mature enough to just go for it. Same code sharing arrangement as using TS on the backend but using the backend language on the frontend instead.

this post, as many people do rn, conflates Claude Code with Claude

there are many Claude Code variants waiting to be built. not TUI code editors, but environments in which LLMs get superpowers

that's the product you should build rn


You're absolutely right.

I wish they'd at least use something other than ChatGPT. Its "voice" is absolutely grating.


Yes, and a magic fairy creates the economic value that funds the UBI

Every company and their dog is saying that LLMs/"AI" is supposed to be that magic fairy anytime now.

Disable everything. I pretty much only leave them on for one email address, text, Uber Eats and the WSJ/Bloomberg.

Uber Eats is a plague. If you leave notifications on they constantly trigger one to make you open the app and clear it.

There’s a way somewhere deep in settings to disable those. I still have UberEats notifications for food arrival, but was able to disable all other ones while digging through all the settings

If you remember how please let me know because I could not figure it out last time I tried.

yes, it's a tragedy but I need to know my food is arriving lol

Look at the webapp.

Pretty sure they mean the issue is on the agentic loop and related tool calling, not on the model itself

In other words, it was the Claude Code _app_ that was busted


> > This replaces about 500 lines of standard Python

> isn't really a selling point when an LLM can do it in a few seconds.

this is not my area of expertise, but doesn't that still assume the LLM will get it done right?


No, the implicit assumption is that losing these 10k PhDs is worse than not losing them.

2026 will be the year of open and/or small models.

What makes you say that? This is neither open nor small

open as in you can run it yourself

you can't run this yourself... max has no open weights

For now

you have to text it

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: