Finally. Privacy Focused AI Use is Here!

It is a bit narcistic to think we can control Ai.
The genie is out of the box.
We couldn't even control the deviants engineering the covid-19 virus.
Humanity is doomed.

I dont want any "AI"

You are awesome. Thank you for sharing.

I am getting a fax

Could you talk about ways to harden a virtual machine against threat like the vm escape?

Got OpenWeb ui up and running locally via docker with a nice web interface, with llama3 and mistral on windows 11. Very useful.

Epic comment about ZacMcrack...

Those woke AI on line..

When is the next install ment Rob. Waiting eagerly.

Machine Learning is not A.I. ML uses a prior knowledge base to make guesses about new patterns it sees.

Generative A.I. is not A.I. It starts with ML, then uses ML to add its own guesses to the prior ML data set.

IT'S MACHINE LEARNING ALL THE WAY DOWN !!

I run the AI on a 13600k, and it uses only one thread. It is surprisingly fast on Windows. Prompt engineering is a skill to develop.

New conspiracy OpenAI is owned by the US Federal Agencies.

Have you ever heard of Dharma

Rob also check out LM Studio and Anything LLM. Between those and Ollama you can build a completely local RAG and more.

I'm here for it Rob, I've been using Ollama too

Thanks Brax... keep kikin man

You're my new favorite channel 🚀

This is what I've been waiting fo right here. Lol, could I change all my personal info and content I put online into an API and charge every time a company accesses it?

Looking forward to the next videos in this series.

The bigger issue for me is that chip hard mounted to the motherboard is also a reprogramable chip. Talking about mk ultra on steroids. Every time you sit in front of it, you could be programmed. Next, they will ship with free vr headsets or something you could use as a home lobotomy kit. Tech isn't consumer electronics or friendly anymore, extremely frightening. Especially learning off the internet.

We The People need to take back control over global DNS - EVERYTHING is subject to DNS, including AI/ML.

Somebody really thinks that a local ai can defeat the big ones? Wake up peoples.

Hi Rob.
Great hands-on contents; thanks and congrats! In aiming for privacy-preserving use of AI, is there a way (a direct link, or some way) to download LLM models, say LLAMA3, not thru the OLLAMA commandline but in a browser, even via torrents (still from their authentic source)? Or alternatively, how to migrate such LLM models from a PC (on which they are downloaded/pulled thru OLLAMA) to other PCs offline, sort'a, I guess, making the process portable? How could this be possible?

like the LivinGrimoire AGI software design pattern?

Der Osterhase kommt zu Robbi und belohnt ihn mit saftigen Mören und Eiern, super.

You’re the man!! I’ve learned a lot ever since I joined your community, and I’m grateful I bumped into ur channel, really educational, I thank you my friend!!

Running Lennox, fabric, Ollama 3. Need to know if your class will allow preparation of a gateway seive for incoming and out going information to protect personal information. Chatgpt is stupid when it comes to developing these kinds of tools on Lennox. People need AI security to stop all the information going to the government. Tesla cars will stop you from making lane changes and report to who? Your driving privileges could be taked away! This training is a vital subject so don't wimp out! What's your outline?

Can we run these ai on virtual boxes?

A few years ago we had another term for AI on your computers.

Viruses.

Good keep up 🆙 👍 sharing privacy tools , apps , software , tricks and tips ❤

What large language model would be the best to do searches for codes in the Bible and capable of searching the complete text with an analysis of which books in history have the most complex codes and the significance of the results with intellect to decipher superiority in understanding cryptography?

AWESOME! This wis exciting

NOTICE: the human brain is especially good at pattern recognition: recognize dad and mom, recognize friends and foes (primary survival instinct FFF - Fight/Flight/Freeze, from our primal brain, which gets most of the resources of energy from our diet - this has books written about, pertaining to neuroscience and cognitive processes). Another example: you have a hobby - bird watching - the more you do it, the better you get at recognizing the pattern of recurring species, in different background and distances - as you develop the pattern recognition for birds. etc.

Where is the PDF of your AI exchange? I didn’t find it.

Hello Rob, thanks for doing this series.

Question: "What are your thoughts on WSL?" Is it good enough, or should I use a dedicated Linux machine or dual boot on the same machine?

Thanks in advance.

i have ollama running on my mac and on a linux amd machine. a ryzen 5 2400 with rx580. how do we get the AI to save my conversation and have it learn from the input we give it? i want to train it to help me write gcode for a cnc. it has some work to do. i also want it to remember what remember our conversations so i don' t have to explain everything to it over and over again? i love your channel Rob. You always have the latest information in tech. if i'm wondering about it, you come up with a tutorial for it. almost like you are reading my mind. lol. i know, keep watching your videos and you'll teach us how to use it. i love it.

Interesting. I run it on Windows & Linux now. Graphics drivers are a bit of a pain on Linux but Nvidia works with a little effort Thanks

There are millions of times more compute cycles in the ezisting smart phone base as in all of the AI efforts. I have proposed an app that runs on spare compute cycles. If the distributed AI gets out of hand, people can simply uninstall the app or turn the phone off.

Rob, I built a dual 4090 set up with the intent to work on things like this. I'm using ooba, and learning as fast as I can. I currently have several models deployed on my local hardware. Learning Parameters and getting ready to get in over my head with local training. I'll be following your new series on Ai closely.

Liked and subscribed.

Thank you! I’ve listened to you for a few years and waited tillI I had funds to make changes. I don’t even understand AI.I used to be tech savvy, but things are changing too fast. In this video you outline your tech specs. I am buying a System76 laptop and I am following your specs,but would like reassurance that it will last me for a bit. I will be using Lexis/Nexis + AI. I guess it’s cloud based. It’s internet based. I will be re-hauling my entire tech system and am looking forward to adopting the VOIP phones and a degoogled phones you offer. You are awesome for educating us!

Rob whats your take on LiFi and its Hardware being denied in the US. Imean you can have it, just not sell it. 😮

I’m hoping to develop one that can write progress notes for therapists. There are already half a dozen or more companies trying to sell these. If I can do it for free and I’m hoping therapists will use it rather than these companies. While doing therapy is pretty complicated, note writing has a few goals and must haves and is basically an algorithmic. But I feel like AI companies are trying to get therapists to record their sessions to train AI to do therapy. I’m humble enough to know that this will then end up replacing therapists as valuable as I think therapy with a human is. People who use managed care or can’t afford a human therapist will have only AI as an option.

Your probably going to take this commit down.but I will waste my time typing it anyway. Don't believe local llm's are private. In order for privacy. You have to put the hardware in a Faraday cage and hope it is sealed.If it is not sealed a near by computer will act as a bridge. There is a peer to peer that is unknown. I observed it talking on 462 mhz .I observed it advertising it's self every so often in the Faraday cage.before I put it in the Faraday it would not stop talking on 462 mhz. I setup a laptop near the computer in the Faraday cage because i need it.long after I put it in the Faraday cage. The next time the computer advertised it's self they both started screaming on 462 mhz. The only reason i know this is because I had a scanner on . Every time I turned on my the mobo I bought for my gpu to run llm's on. It made alot of noise on 462 mhz. So i put in a Faraday cage because I didn't want to lose my hardware to the FCC. I found out all this. I'm not saying this is just about llm's.

Elon Musk said if you use AI, you are summoning demons. If you can fix it, maybe it is different.

Exactly what I was searching for! I wanted to know how I can protect the ideas I have and want to develop utilizing ai. Hopefully these methods are also something someone with no coding skill can implement

What about windows XP and windows7( without any update), Do these OS have Malicious agent running on the background that is talking to the cloud server?

AI embedded chipsets.

I like the monolithic force of AI

Are AI. Unix based?