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

I use this library in production and love it!

Completely agree. And to make matters worse, I can't even switch to android without losing the ability to reliably send quality video to iPhone users.

Apple suffered for decades from Microsoft's anticompetitive OS monopoly, and turned around and did the same thing to the android ecosystem.

I have no idea why this sub is full of Apple fanboys. I was an Apple fan 10 years ago, but these days they no longer deserve your support.


> the ability to reliably send quality video to iPhone users.

Just curious but why? Is it iMessage lock in?


Yes exactly. RCS exists but unless an iPhone user goes and turns it on it won't work. Which means no one has it turned on.

I don't think that's true. Every iPhone user I've texted in the last 6 months at least has had rcs turned on, and that's including some very non tech savvy friends that I doubt did it manually

It's also dependent on the telco supporting it. Australian telcos don't.

RCS compatibility with iMessages relies on the telcos to implement it, particularly for group chats.

iMessages work using SMS 1-to-1, but group chats require the telcos to enable RCS instead of SMS.

Of the 3 telco network operators in Australia, none of them have enabled it.


And no one uses WhatsApp, Telegram, Line or another cross platform messaging service?

Is it okay for human managers to make sure the employees are being polite? But not AI? Why?


What's wrong is the micromanaging, and also the "operationalization" of politeness into the metric of "these specific words and these specific times." Both are dehumanizing with or without AI - both on the employee side and my side - what is the point of politeness if it's basically at gunpoint?

I would equally have a problem with a manager who is threatening to write people up if they don't meet some count of saying the words "please" and "thank you."

I don't want AI to enable micromanagement of stuff that doesn't really need to be micromanaged. How it should be done is this: Print a QR code on the receipt. If I feel the drivethru conversation was bad, let me scan it and notify you. Then you can have AI review that conversation, and we'll also find out who the people are that just like to complain too much and ban them from the establishments.


Anyone who's been to a Chik Fila more than once has experienced how weird and off-putting this kind of micro-management to the point of ensuring certain phrases are always used in particular situations is- every conversation with them ends with them saying "my pleasure" in a rote way.


I definitely agree that is weird and off-putting, but I recently moved to an area with a grocery store that is the complete opposite: the cashiers stand there silently through the whole order. That's also off-putting despite my introversion. I think we need a middle ground with a simple mandatory polite greeting like "Welcome to Hank's" and then after that leave it up to being organic/authentic.


https://marshallbrain.com/manna1

(probably killing a dead horse posting this again in this thread but it's the best response)


When a human makes sure employees are being polite, they're reinforcing the social contract that comes with employment. When you remove the human from the equation it's literally dehumanizing. That's it. Thats the why.


Netscape had a 90% market share in 1995. If OpenAI is metaphorically netscape, what prevents its competitors from prying away customers every day? What prevents google/facebook/microsoft from using their position to bundle chat experiences? Especially if the tech is a commodity and OpenAI's models are about as good as everyone elses?


In 1995 no one used the web still. Sure, we all did, but it was pretty niche. I think you could argue that chatbots are niche as well, but the user base of OpenAI is way larger now than Netscape in 1995. Netscape had probably 25 million users at the end of 1995. ChatGPT has about 800 million.


Why not just use natural language?


Because "latent semantic vectors" sounds way cooler.


I agree completely. I don't know how anyone can be building on these models when all of them are either deprecated or not actually released yet. As someone who has production systems running on the deprecated models, this situation really causes me grief.


I dont think any of them really wants api customers in the end. They are only temporarily useful.


Why's that?


Well let me use llama.cpp to run worlds-smallest-violin-Q8.gguf

When you build on something that can be rugpulled at any moment, that's really kind of on you.


> Achieving the Senior Executive status is often mistaken for a comfortable reward, a final destination with enhanced perks and support. A more fitting analogy is reaching the NFL Super Bowl. You are now part of an elite team where nothing less than peak performance is acceptable. As the Navy SEALs put it...

I can't believe anyone actually wrote this.


In my experience, so many execs love their sportsball and war metaphors.


Social media: the solution to, and source of, all your anxiety!


This doesn’t make sense to me. Of all the things I will delegate to Claude Code, vendor selection would be one of the last.


There are techniques to mitigate this. You can reuse containers instead of creating a new one each time. You can mount in directories (like ~/.claude) from your local machine so you dont have to set claude up each time.


I use agents in a container and persist their config like you suggest. After seeing some interest I shared my setup at https://github.com/asfaload/agents_container It works fine for me on Linux.


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

Search: