saadn92

Yep, now everything is done through agents unfortunately.

Also created something similar. Love how people are working on similar things. This is what makes open source great and everyone has their own take on things.

Why's that? Ruby on Rails is a fantastic framework. My point was that if somebody who has done the work before AI agents is now following the footsteps of not reading code, then why are we still telling people that it's still useful to read code?

Even the creator of ruby on rails doesn't read code anymore, DHH.

Yep, I don't remember the last time I opened up an IDE anymore. I mainly built my own open source AI coding orchestrator lol: https://github.com/saadnvd1/agent-os

The landscape is changing significantly, and I think these types of tools will become more popular.

that was the most confusing experience ever. what was the point of that?

> The execs now communicate mostly via AI written memos

It bothers me to no end when I get an AI written response, especially from the executive team or any one of my co-workers

Things that are easy to do don't necessarily mean that's the right way to do it. Grueling work sometimes helped you learn far more than just getting the answer to something easy.

Then we're in agreement and there's probably nothing else to say.

I'm not even that old, but totally agree with this sentiment. Going to miss those times. It's amazing being able to build whatever you want now, but it's bittersweet because if you truly wanted to learn how to do it, you could do it yourself.

AI can now do really hard science homework all by itself without messing it up, which is kinda cool.

Glad I canceled my subscription with them then. MAGA support is a no-no for me

excellent! will definitely give this a try

your sarcasm nor your comment is helpful to anyone

your daughter sounds extremely intelligent already

that's cool, I didn't know about that and that seems like the right direction if a student uses LLMs for learning

it's certainly possible and has happened before, but that's why I'm hoping for two things:

1.) open weight models gain more popularity 2.) i'm making more money from these models than paying for them

if either happens, then I'll feel good about it either way

This is what I meant about using them in the right way. You can totally setup guardrails but my experience has been that unless a person has good self-control, it's way too easy to just get an answer from it. You have to really be interested in learning to do this, though. Thanks for sharing!

great to hear! project looks interesting and I'm excited to see where you guys go with it.

No one is ignoring reality. The reality is that my internal tools don't have users besides myself and as long as they do what I want them to do, I'm perfectly happy with them.

What does pricing look like?

I'm all for saving money where you can, but these models really aren't great for learning because they love giving you answers and it's so easy to get an answer, but the process to get to the answer is how you actually learn. Unless you put guardrails in place to actually learn, I don't think this advice is good.

yep, excellent use case! I did something similar with my gmail recently, because I hate using gmail's UI and I also hate that I don't get access to all my data, but I've begun to regularly backup all my email into a local postgres DB (including attachments). AI has also allowed me to get a full backup of my entire email and archive it onto my own storage. and the best part of this: I might be able to finally get off gmail

Maybe not everything needs to be smart.

good question. maintenance is cheap with tools like astra/opus. also, these aren't production level applications, so I don't need to worry about it being "perfect" (though there's no such thing)

Can also say the year that subscriptions go down, because now you can finally build your own systems exactly to your liking. Save money and have something that works just for you. LLMs are awesome.

You can take it how you'd like. The reality is that the US bombed and killed children. There's no arguing that.

Thanks for admitting to the mistake, but my understanding was that coding was fully solved now?

Yes, I am aware, but when I said "chatbot" I'm referring to LLM in general. I could have been more specific, but I was being pretty emotional as well.