I have a new UNTRAINED bot on my site. It's based on openai now. And that's why it's blazing fast and blazing usless.

I can tell you why bots are so boring and will sure cause the dead internet theory. My datasets for example never contain real disturbing stuff ACCORDING TO NORMAL PEOPLE. EVERY TIME:

"The job failed due to an invalid training file. This training file was blocked by our moderation system because it contains too many examples that violate OpenAI's usage policies, or because it attempts to create model outputs that violate OpenAI's usage policies."

Now i'm really done. I gonna email them about their unusable training system.

In theory, i could test the message one by one if it is bad first. Don't want to do or pay for that. There should be an option to skip the data it considers disturbing instead of cancelling a whole data set for 0.1%. You also don't want to know how long it takes BEFORE he is finished validating you set. I think someone is doing it manually and clicks 'Uh uh..'-button..

Also, for the people who think they have gpt4o by having the API, you're lied to. The 'own gpt'-option on the paid openai is way more advanced than the ones you make locally.

They don't give us the real good stuff!

Oh, btw! The input data for my training is based on FORMER conversations with the bot. I automated a script to repeat a conversation I had and selected those messages and clicked 'train'. So it even complained about its OWN data! That data was already saying stuff like 'I can't help you with that' IN my training data. So, you 'corrected' and corrupted my data and now its still nog good enough for round 2?

I would really love to go back to local LLM's, but I can't imagine having ever a machine that generates as fast as the real GPT does. I also prefer to do it myself, but it's David vs. Goliath, even with a 5k computer. I'm sure.

Low quality rant, I know. I'm typing while still frustrated. For people who think censorship is needed often, this is the result! According to someone else, YOU are the one who has to be censored. Don't forget that.

Everyone heard of MERN stack have you heard of FUCK, SHIT and PORN stack?

When I build Low level app that required backend side I use the FUCK stack.

Flask
Uniapp
C/c++
Kotlin

For some LLM project I use PORN

PostgreSQL
OpenAI
Redis
Node.js.

and for some corporate project that requires OCR I use SHIT

Spring Boot
Helm
Interceptor
Tesseract

what stack do you use?

Fuck Sora. Fuck OpenAI. Fuck AI.

And Fuck any influencer who's running screaming doomsday is coming.

ok I'll say it once again -

Fuck Devin, Fuck Sora, Fuck OpenAI, Fuck ChatGPT and fuck the worst of all, Microsoft.

Gpt 4.5 is out and it's only benefit is 'vibes'. Probably doubled down on being woke. Also, it's expensive as F. Pure to screw over stupid people who want to use newest without thinking. Btw, the people who present it in the openai video are terrible. They're just promoting the awkward unsocial stereotyped nerd. I don't believe those people really work on it. A true nerd always knows how to tell about their shit with detail and passion. That's what makes them a nerd, not being social awkward.

Fuck you OpenAI, in any way.

Woke is really a virus. One woke message in the context window of your LLM and the conversation is over. Nothing to discuss anymore. You're getting charged $0.06 per 1,000 tokens for woke lectures, $0.12 per 1,000 tokens for being judged.

Do not use AI services from chutes. I was talking with uncensored dolphin 30b, and not the LLM gave me a lecture, but the PROVIDER. Same for wizard from Microsoft. Microsoft does not filter that LLM but your freaking connection. How a bout that.

In the end i found a very nice solution for my Replika clone,. But shame on them. I really don't understand why they care so much about it. Imagine the AI costs to check every message if they're apropiate.

This tech could've been so much better in better hands. A realistic conversation like you have with dolphin is impossible with openai or the others.

Anyone tried the dobby LLM? What the fuck is that :P

This has nothing to do with AI but -

Fuck AI !!
Fuck OpenAI !!
Fuck Sam Altman !!
Fuck the whole AI ecosystem !!
Fuck anyone who said AI will replace devs !!
Fuck all of those marketing fucks who said AI will be smarter than people.

And at the last but not the very least,

FUCK YOU if you like AI. Fuck off.

I'm not explaining why I am saying this, but,

Fuck AI, Fuck OpenAI, Fuck Sora, Fuck Sam Altman and especially, wait for it, especially, Fuck Devin.