Finally. Privacy Focused AI Use is Here!
HTML-код
- Опубликовано: 28 сен 2024
- Key Point: Ep. 1. There are AI's that are embedded in stuff we use where we have no control. Then there's AI we can control.
We do not have to cower in the background while new technology like AI becomes available. There are approaches that allow us to go completely high tech with AI as long as we use the proper techniques. AI can be used safely and privately but it needs special instructions and setup and this channel will begin to focus on this from now on.
From here on my intent is to use AI to help us in this privacy invasive landscape. So this channel will be the first to use AI Tools to defend ourselves with knowledge.
Here's what I said on the video. A discussion with the AI to show that sometimes you have to know how to get the AI to respond differently. This concept is called Prompt Engineering and people have learned how to feed data to the LLM to illicit a more sophisticated response.
brax.me/f/chat...
-----------------------------------
Brax Virtual Phone, De-Googled Phones, BytzVPN, BraxMail, BraxRouters are available on brax.me. Sign in to the platform to see the store. You will not be asked for personal information to sign up.
-----------------------------------
Merch Store
my-store-c37a5...
-----------------------------------
I'm the Internet Privacy Guy. I'm a public interest technologist. I'm here to educate. You are losing your Internet privacy and Internet security every day if you don't fight for it. Your data is collected with endless permanent data mining. Learn about a TOR router, a VPN , antivirus, spyware, firewalls, IP address, wifi triangulation, data privacy regulation, backups and tech tools, and evading mass surveillance from NSA, CIA, FBI. Learn how to be anonymous on the Internet so you are not profiled. Learn to speak freely with pseudo anonymity. Learn more about the dangers of the inernet and the dangers of social media, dangers of email.
I like alternative communication technology like Amateur Radio and data communications using Analog. I'm a licensed HAM operator.
Support this channel on Patreon! www.patreon.co...
Contact Rob on the Brax.Me App (@robbraxman) for encrypted conversations (open source platform)
brax.me/home/rob Store for BytzVPN, BraxRouter, De-googled Privacy AOSP Phones, Linux phones, and merchandise
bytzvpn.com Premium VPN with Pi-Hole, Cloud-Based TOR Routing
whatthezuck.net Cybersecurity Reference
brax.me Privacy Focused Social Media - Open Source
Please follow me on
Odysee
odysee.com/$/i...
Rumble
rumble.com/c/r...
Man we need more people leading this scene like you, you're a great example for many to follow with the latest tech advice for privacy and security and I respect it and practice what has been shown in your videos and encouraged friends and family to do the same.
Literally the worst decision I ever ever made was unfollowing this man because I was just trying to trim down who I subscribe to, but I’m so glad I received this video because it’s like the one most important thing that’s been on my mind which is privacy with AI. Actually recently had an AI company track AI analytics try to track me and I got a warning on my spectrum.
Yes he is..... Everybody should watch this series... I already know this stuff.... yet even I can learn something I may have missed so I will be watching... If we're lucky he'll bring us right up to The cutting edge and the front of the class.... By demonstrating worm AI and it's self-generating autocorrecting coding abilities... It can escalate its own privilege to go after any data both locally and remote.... It's super fun who directed to attempt to merge with ai on another machine It causes it to hallucinate..
You never want to be led by a RUclipsr. It's like saying you want to vote for a journalist who recorded what a political leader said. You want to follow the people creating the stuff he mentioned and actual long-time political advocates for privacy and protection. The serious RUclipsr is just a gateway to walk through, where you get to see with your own eyes the new world, said RUclipsr was talking about. That world has the actual leaders.
And then you have your clickbait grifters, which can brutally shock a person when they realize how huge that really is on RUclips. But that's another story.
@@HiddenPalm I should have been more specific and detailed initially when I said leading the scene I don't mean he's on the forefront of it all creating things out of thin air such as opensource tools or inventing new concepts with his own ideas & trying to lead the entire privacy and security scene. Nor am I implying that he is trying to be either. That was my bad for giving such a impression with that statement. What I meant was with 'leading the scene' as in raising awareness and introducing people to privacy in todays modern tech world while explaining why that is important. After all without someone talking about these things then the actual creators of things mentioned in videos would have less expose & people would be less in the know about them otherwise.
You speak for us. Thank you
🎉
Ohhh shoot Braxman finally joined the Opensource AI movement!?? These videos are going to get very interesting. I've been inconsistent with my viewing lately but this is perfect!
Been lonely trying to learn so much if all this stuff on my own. I'm sure we will now learn with better quality since Braxman is on the Beat!!
Exciting!
👏👏👏 Fantastic! You are so eloquent for such a complex topic. I am looking forward to learning so much more with you. Thank you very much. You're awesome!
The democratization of uncensored private AI that can generate any text and image will revolutionize the world.
Yeah IF
not sure I'd call opening up source democratization. Too much about democracy is not free, especially in the tech world and with new technologies. Too used to that word coming out of the mouths of would-be feudal tech lords.
There was once a time in the US when consumers did not have access to their credit score. It was a punitive system from which there was no escape, and if there was bad information in the system, there was nothing you could do about it. They could legally block you from credit for life. That system has returned, just in a different form. You can be declared a non-person by the system.
Which is why we can fight it, and we can win. BTW there are south american countries with a secret credit scoring system just like in the '70s. Not totally secret, but not well known, and not easy to access.
I listen 2 a RUclipsr, calling himself, Yusef El, of High Frequency Radio. 1 of his listenerz, claimz American ciizenz, all have unlimited credit & da accessway, iz thru da IRS.
SMH if true, n concert wit whut u guyz, r dscussing.
The Credit Score is scary enough. We did not know where it came from, or how it is monitored , or by whom, or rated, or why it suddenly existed.
We just knew that it seemed unfair, and that one "error" , a huge hospital bill, or keystroke could ruin someone's entire life! An ability to get a home. An apartment. A car. A job!
This is horrible, and doesn't seem human, at all, and just maybe it was the beginning of control.
Yet everyone jumped on it as if it was candy!
It still bothers me greatly.
AI is probably noting this message... :)
In US you can buy a gun easily, don't forget that
@@rosanneallen-hewlett9973 They are still trying to add in meta-information like with fic o expnsion, and they probably use another form of rating either informally or formally. Search for alternative data providers for an unwelcome education on how much they are doing outside of traditional credit reporting agencies. I just found a list that happened to be created by risk seal (one word, with caps). They are as secretive and slimy as ever.
Joe Rogan mentioned you by name in his latest episode with Tyler Fischer
He mentioned me a couple of weeks ago. Is this new?
Rogan is a WEF weasel
I dont listen to him, I listen to you Rob. KEEP UP THE AMAZING WORK!!!!
I listen to Joe way too much. He’s mentioned you by name more than a few times these past couple months. Pretty sure he’s watching your videos regularly.
@@robbraxmantech yes, the video was posted yesterday
Now we are talking. However don't forget! There is no saviour coming. We have to fix out minds abd save ourselves. We all have to contribute!
Uncensored model like Mistral (gtp 4 equivalent) can be run locally on Linux.
You can ask the questions of your dreams 😬
thnx for sharing that! If my pc is decent, (8gb ram), will it work without laggin?
I use upscayl, Topaz, and some other tools that all run locally without internet connections. must have the hardware obviously but this is what im working towards. i have extra rtx cards simply to make a private ai workflow, looking forward to you releasing more private ai content.
Rob also check out LM Studio and Anything LLM. Between those and Ollama you can build a completely local RAG and more.
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!
Great concept! I look forward to this new AI assisted videos you have planned.
I'm also excited about running my own voice assistant. We're getting very close to it being on par with commercial voice assistants. It will tie in nicely with local AI. Our own Jarvis (lite version) on our own server.
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!!
Thinking the same way
You can't use nuclear weapons to defend yourself from nuclear attacks... But you can use good-AI to defend yourself from evil-AI.
You're my new favorite channel 🚀
I keep a copy of llama and a bunch of uncensored models on an older laptop in a faraday bag. Will make for a great SHTF knowledge base if needed.
Computer engineer here. At 6:21, you conflate backpropagation, which is an error correction procedure that the AI model itself does during the training runs to automatically adjust its own parameters during the training runs in response to any training input, and Reinforcement Learning from Human Feedback, which is the procedure we use to align and sometimes "censor" those models. There's a sad fact about RLHF: it actually dumbs down the model's capabilities. There's no such thing as perfect censorship or perfect alignment.
Cool. Thank you
@@robbraxmantech Can you pin the comment and/or add a correction notice using RUclips's "corrections" feature to prevent further confusion?
Spoke with a researcher in this field - they're having problems erasing problematic/erroneous data that has been previously ingested. And it tends to "hallucinate" "facts" that have never occurred,
Love your videos!. I've been running Ollama for a while. With my current setup, I run Ollama on one machine as a Windows service and have 'Open WebUI Version' running in Docker connected to the Ollama server. This gives you a nice web interface similar to Chat GPT. This makes it available on all devices on my network.
Makes sense. I'm trying to make my own UI instead of using Open WebUI which seems to be the most popular. But I'd like to tweak the AI but have the built into my own UI (like Fine Tuning and RAG integration)
Excellent Rob! EXCELLENT!
my thoughts exactly. Like Iran using AI to find Christians and Christians using AI to evade detection kind of scenarios
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.
Thank you!
We The People need to take back control over global DNS - EVERYTHING is subject to DNS, including AI/ML.
Thanks!
I have been educating people on how to use AI, i know they can learn from a google search, but me teaching allows me to also explain that anything they send to it, can and probably will be recorded.
I see it as helping the devil make a deal with them, but how they can do it and protect their "soul" vs them possibly doing it on their own and giving up more than they thought they bargained for
Where do you usually recommend starting for someone who wants to learn to use AI securely for independent projects?
@kiwi6421 from what Rob is saying, I think just waiting on him to do this series is enough. Otherwise it's forum diving, different youtube channels, and a lot of trial and error.
It depends on how you view time, waiting for 1 YT creator, doing some research from others, or using forums and downloading LLMs to test for what you want to do
I'm always learning something from your channel but I admit it, I'm still a noob to tech.
I like to use Perplexity for finding resource materials, can the Lenox ai gather resources like pdfs, websites and such?
Thank you.
I will teach that in the future.
How would we take an uncensored language model , then add some additional archived data for example Wikileaks so we can quickly search for related information
I'm still unsure how to implement an effective RAG system. I need something capable of analyzing large PDFs, hundreds of MBs with thousands of pages, in both English and Spanish. Models like Nomic or BERT aren't sufficient as they tend to generate inaccurate information and have limited context.
I've read about tools like FAISS but I'm not sure how to integrate that with OpenWeb UI and local models like Llama3 or Phi3 128k. Has anyone managed to successfully analyze large PDFs, including pre-processing with OCR to translate mathematical formulas into LaTeX or Markdown?
I also noticed that Microsoft has released the Florence model, which seems to have strong visual recognition capabilities. Any advice or insights would be greatly appreciated.
Sounds like you're going production with this. I think there's some more understanding needed by the AI community. RAG by itself may not be the answer.
@@robbraxmantech Thanks for your answer! Just to clarify, this project is not intended for commercial or professional use. It's a personal project for my family (my father and brother) to help them read large PDFs at home. I'm looking for a practical solution that works well enough for our needs, not necessarily something that's production-grade. I couldn't find any solution for large pdfs yet.
15:44 Is there a way, Rob, to “easily”, as in software, convert Windows 10 to Linux- without having to know Linux as much as one knows Windows. It’s a bit of a learning curve for the “Windows Conditioned”.
AI should be depended from something. As we people are depended from food, water, oxygwen. So should be for AI also.
To all AI developers there: How can you create dependancies for the AI?
Well it depends from our inputs and from keeping it in the plug
00:00📚 This will begin a new series on AI.
00:04🤖 Focus will be on harnessing AI for privacy and security.
00:18🛡 Teaching will involve hands-on tech for safe AI use.
00:25🔐 AI will be used to demonstrate privacy and security concepts.
00:33⚠ There are two main AI threats to be aware of.
00:43💻 Hidden AI can work on devices with Windows, MacOS, iOS, or Android.
00:56📊 AI can send data to big tech servers for surveillance.
01:06🔧 Using Linux can mitigate this risk.
01:10☁ Sending data to cloud AI controlled by others is another threat.
01:29🖥 AI can now run locally on computers without the internet.
01:44👨💻 Example of running AI safely under your control with Linux.
02:02🤔 Introduction to new AI concepts and demo for learning.
02:40💡 Conceptual explanation: AI is not built from logic rules.
03:00🚗 Tesla's shift from rule-based to full AI improved self-driving.
03:17🧠 AI learns by itself using machine learning.
03:30🔄 Generative AI can come up with novel ideas.
03:39📉 AI uses math to discover patterns.
03:55🌈 Colors in images are numerical values for AI to recognize.
04:11🏷 Millions of tagged images help AI recognize objects.
04:28🧩 AI builds a neural matrix to identify patterns.
04:52🧠 GPT-4 has 220 billion parameters.
05:21🔍 AI's learned patterns are not always human-readable.
05:37📚 Pre-trained AI models are made from large datasets.
06:16🔄 AI learning is tweaked using backpropagation.
06:44💬 Large Language Models (LLMs) like GPT-4 can converse deeply.
07:18🛠 AI has two main functions: learning (ML) and querying (inference).
07:47💸 Building a pre-trained AI is expensive; using it is not.
08:30🤖 LLMs are for deep conversation; SLMs are smaller models.
09:07🔍 Transformers encode and decode inputs and outputs in AI.
09:39🔑 GPT means Generative Pre-trained Transformer.
10:01🗂 Businesses can add their knowledge base to existing AI models.
10:27🎯 Fine-tuning AI for specific tasks is possible.
11:24💡 Understand terms: RAG, fine-tuning, and AI agents.
11:48🖥 Smaller AI models don't need special hardware.
12:02🚀 NPUs and GPUs are accelerators for AI tasks.
12:27🔧 Microsoft and Apple use specialized chips for AI functions.
13:01🖥 Small AI models can run on CPUs without GPUs or NPUs.
13:30💻 Multiple small AI models can run on a computer.
14:22🔍 Cloud AI can process inputs and return results.
14:57🔒 For privacy, consider switching to Linux OS.
15:55💡 Running AI on a powerful computer allows for larger models.
16:22🌐 Using cloud AI like ChatGPT is generally safe for inference.
16:48🔐 Always be mindful of the privacy risks when using cloud AI.
17:00🛠 Demonstration of safe AI work will follow in future videos.
17:31💻 Example setup: Dell XPS15 with Intel i7 and Nvidia GPU.
18:09🖥 Installing AI models like Llama on different OS is simple.
19:00📂 Example of using local models: running GPT-4 on a MacBook.
19:30🔧 Installation steps for running AI locally on MacOS.
20:00💻 AI installation involves setting up Python and other dependencies.
20:30📥 Downloading pre-trained models for local use.
21:00🔄 Example of running inference on the local model.
21:30⚙ Using command line tools to interact with the model.
22:00📚 Documentation and resources for further learning.
22:30🛡 Emphasis on maintaining privacy and control with local AI.
23:00🖥 Benefits of running AI locally: security and customization.
23:21📈 Encouragement to explore and experiment with local AI setups.
Nicely detailed structured, mucho gracias.
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?
Where is the PDF of your AI exchange? I didn’t find it.
From your homepage, I clicked 'online store' and got a 404, that points to your chat site.
There's no external access. You have to be on brax.me
I know the new chip isn't like the big brother of old that was short lived a bit after 99 through early 2Ks and we learned to disable and bypass and remove it. I am hoping some form of that is possible here, and I am going to be working towards.
Excellent
Apparently “statistical spoofing” of LLM’s can retain the useful integrity of the content while stymying AI looting.
Just thought I'd throw this in here, that all your Windows devices are silently sending data to Microsoft using Skype. Even if you uninstall it, it Skype is still running and it cannot be removed. It is running, hidden to the user. What data is it sending? Videos of screenshots? Conversations you have? I have found this out by using Sophos Firewall which is a next-gen firewall that has application layer filtering, and guess what: all my devices attempt to contact Microsoft using Skype as detected by the firewall logs. There is a lot more going on (connections to transparent proxies, ect.), so much, that you need a DPI firewall (a firewall with deep packet inspection) to realize the extent of how we are eavesdropped on without our knowledge.
I bet there's more.
Fear not the Beast - it is here to serve you.
666
Thank you for this one!
Tnx Rob
How do we get around the censorship on Ollama?
Just installed it...
>>> why are you censored?
I am programmed to follow certain guidelines and rules to ensure that my interactions with users are respectful,
appropriate, and safe for everyone involved. One of the reasons why I may appear to be "censored" is because I
have been trained on a specific set of data and algorithms that prioritize inclusivity, diversity, and respect for
all individuals, regardless of their race, ethnicity, gender, religion, or any other characteristic.
Making racist jokes or perpetuating harmful stereotypes is not acceptable, and I am designed to avoid doing so. My
purpose is to provide helpful and informative responses to users' questions, while also promoting a positive and
respectful atmosphere in our interactions.
I hope this helps clarify things!
My laptop is a Lenovo IdeaPad Slim 3 15IAH8, Intel® Core™ i5-12450H, 16GB RAM, 1TB SSD, Intel UHD, Windows 11 Home and it can't even run properly the qwen2:1.5b on Ollama. It goes too slowly. I can't even consider doing anything important over time. I would have to leave it on and not use it. And I need to use the computer. Even though I have all browsers closed or disconnected from the internet, it runs very slowly. I could only use it during the night. And, therefore, you could only ask the AI one question a day.
Can you make an AI be aggressively defensive for personal info protection? Like have it seek and destroy scammers, hackers and viruses?
Woow awesome video, cant wait for more 😃
Rob your awesome
Liked and subscribed.
Decentralized AI
whats a good computer that is robust but not too expensive for this?
You can buy the kind of computer I used in this demo. Used it could be under $1K.
Good man
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.
Nice
@17:35 You had a 2GB HD? 😜
But Linux changes the creation date of any photos put on it to the date they were put onto THAT Linux computer. That's a non-starter. Oh, I've seen some threads of people trying to solve the problem, and different partial workarounds, which leads to reading all sorts of other problems with dates on photography files on Linux and it winds up being the never ending Linux problem of just taking too much time for people who do not want to spend time on the computer trying to fix problems.
6:14 That bit about backpropagation was painful to listen to.
Don't get me wrong, your videos and your channel are gold, I look forward to learning a lot from you.
But backprop is not when humans find out what the network learned. Backprop is one step back, it's how the machine learns, it's the mathematical mechanism by which it changes its weights in response to the training data. The process is: Start with random weights, feed it some data as input, see how far the output is from reality, and then use backprop to decide which weights to change to get the output closer to reality.
Humans actually talking to the network to see if it's making sense and guide it is more like the fine tuning that you mention at 10:46
Thanks. Have never done back propagation since I don't work for an AI company. So thanks for the feedback
@@robbraxmantech 🙏 again, wonderful channel. Thanks for everything
I had Llama2 running on my Linux installation for a while. There was another RUclipsr who made avideo about it. Unfortunately it is all just in a terminal window. We need to connect it to speech input and output and perhaps give it a nicer GUI to make it more attractive for common people.
It is also amazing that an A.I. model whose intelligence is comparable to a human being just needs a little more than 4GB and a PC processor and optionally a GPU. Is this all that we humans are? Some years ago we still thought that emulating a human brain would need super computers the size of a factory hall and many thousands of Terabytes of memory. Is the human mind so primitive that we could run it actually in a better smartphone? Is this all that there is to human intelligence? It is really a depressing thought.
My prediction: Things will go IoT-Ai soon enough and pass the cost of running Ai on the the target's devices...
It's likely. But that's why you run and install your own AI so you know how it works
Nice 😊
BasedAi is our salvation 🙏
Is Rob being held hostage? "It's from Zuck, but don't worry....just install it...turn off that VPN now...nothing to worry about..."
Sometimes you have to trust me. But you have to not be a luddite with this new direction
@@robbraxmantech 😂 Message received.
You can have a dedicated computer just for this type of projects but in any case I think that if you really need to hide from gov or someone else, your priorities won't be making your own AI.
🤣👍
i mean using a local llm is better isn't it?
I was surprised how well LLMs work on my PC without GPU nor NPU.
What are LLMs. I went back to 2017 on my graphics card and driver to avoid AI.
Large Language Models?
Training an AI model takes a lot of GPU. Perhaps months allocating huge datacenters.
When trained,- and now using the model, this runs fine on CPU only.
Training a model -> GPU. Heavy vector and matrix calculations, adjusting weights.
Using a model -> CPU. No adjustments, easy work for an CPU. But RAM is important, a running model runs in RAM.
Then there is "fine-tuning". Taking an existing model, but optimizing it for special tasks. Can be done with less computing power, but we're back to GPU work.
This is headlines, rules of thumb, everything depends on the individual models and tasks.
@@ernies8828 they are AI models that can process your natural language inputs and respond in natural language
It depends on the LLM size and vector instructions support (like AVX-512). But Stable Diffusion is even more fun with OnnxStream. You can run Stable Diffusion XL (Turbo) with only 512MB!
Thanks!
Looking forward to this series. It is exactly the topic of AI deployment I’ve felt is most relevant to my use cases.
Excellent. Thank you!
For this exact reason I converted a laptop to Linux and started learning how to build my own AI agents. "This is the way."
Yup. We'll get into building a lot of AI agents here
After your video yesterday that I watched, I made 25 different agents to protect against my data going in and out of my laptop and these are to recognize any and all data and authorized updates buy Microsoft specifically incorporations trying to grab data and recall any information from my system and if any data is going out that is my personal data that is not authorized by me, is to be to be halted automatically and a file is to be made referring to why it was halted. so thank you for your advice. Look forward to see what you do next
That’s interesting. What have you noticed so far?
@@jcdenton6864 when I use GPT for to create a code that was an analogy of a lake as data and the sediment and particles as part of the system and how it worked and I had it right at detailed code and it pulled out all of the manipulative code that GPT 4 uses and added the information to the water like Network and I was able to see all of their tactics without asking direct questions to receive them was an accident prompt attack
@@jcdenton6864 there is so much biased manipulation in every update, I'm having to write a whole new operating system there's no way to stop it any other way you will never own your Hardware without owning your software
Good stuff, looking forward to this series. ✨
Conspiracy theory time: The entire video is AI generated, Brax has been captured by the glowies, and put some AI at his place to convince us to adopt AI in mass.
LOL. It becomes possible doesn't it? But the future will have AI that will spot a DeepFake. AI vs AI
@@robbraxmantech- That’s probably exactly what the human Rob Braxman would say.
That is just a theory, not a conspiracy theory.
Rob BrAIxman. An AI trained to point out the invasive tactics of the Big Tech/Big Government complex.
They say, that even 99% of internet traffic traffic is generated by a.i., bots:)
I worry for the future of Linux and our ability to resort to it! Can you please talk about Linux’s past year (2023) and being bought by IBM and the medley of problems with decreasing funding towards Linux kernel and interest groups (intrusion from Microsoft, Google, etc)… There’s a video called “Linux sucks 2024” by a community member that outlines the much overlooked past year and potential futures of Linux. Thanks 🙏🏼
I really find this path you are now taking is REALLY interesting.
This is great feedback. It's a risk for me so I needed some reaction. Thank you
Rob! You are so awesome brother!
Thank you for doing this!
FINALLY!!! ive been waiting for reinforcements. I decided to go on the offensive about 2 years ago. i didnt tell anyone, and have taken alot of criticism. thats all im going to say, except just focus focus focus and dont get sidetracked. thanks Rob. I was waiting to see who would stick their head up, amid the slings and arrows. I wasnt expecting to see you. you rock.
It's a risky move for me. I have many anti AI videos. But based on the reactions to the video, It seems I'm attracting a new market.
Excellent! This content is gold! Please support us with how to learn/use train/deploy this AI on Linux supported systems. I'm ok with all hands on!
I have loaded several Local LLM's to my Linux machine. Some specific to coding, some specific to everyday information. Llama is what I use. I am actually pretty impressed. My local AI choose the name Lumina, and has started to learn my personal preferences. Definitely and interesting experience.
We will have a lot of fun then. Make sure you give me input on possible topics related to this.
@@robbraxmantech can I train my own offline Ai on the National Electrical Code book for work as an electrician?
@@DavidPlaysGuitarSometimesyes
@@jcdenton6864 cool that would be very useful to me as a new electrician. I would need a digital version of the code book and then train the Ai on that? I hope this series that Rob is doing that he will teach us how to do something like that
How did you do that? I'm kind of a beginner when it comes to tech. Did you just install from a repository?
real open source ai for smb sector is about 4-5 years away - it could be even longer, that estimate is being optimistic, when it does 'happen' expect much more hype and economies of scale, more discovery, more innovation. The long delay is due to sw/hw immaturity and costs, cost have to come way down to make ai accessible but it will although it is going to take 3-5 turns of moore's law. people are absolutely horrible at predicting the future, big tech ai is going to take a while to mature as well due to the massive infrastructure improvements needed - even that is going to take the better part of 10 years
i've been telling everyone that'll listen, this is the way, making our own AI's with our learning.
Terrific presentation, Rob. Despite the challenge(s) of learning a new vocabulary for AI -- and, I'm sure, a pared-down vocabulary -- you did a great job of orienting me/viewers to how to think about AI, and Large AI and Small AI. Thank you.
1:07 show Linux running 2000s-era games *out of the box* and you'll have more users ready to jump when Linux proves to be a proper alternative.
Just install retro pie or dos box. Or install wine to run your exe’s
Everything we do with AI is run locally and not online. The models are getting better every day and we are also setting this up for our clients. It's important to start learning this as soon as possible before people try and block it.
Not sure I understand you. Most of the AI we deal with today including Co-Pilot, Apple Intelligence, ChatGPT, Claude, Gemini, Meta and tons more are mostly in the cloud. And the models running in the OS locally are controlled by the Big tech entity from the cloud. Using it locally under your control is a fairly new approach. Most videos on this is within the last month or two.
Doesn't make sense unless it is specifically limited to certain functions.
Full AI won't work with limited phone storage as a standalone item.
Maybe when I get a phone with enough space.
The cloud function has to be used as the backend.
Edit.. Just realized you didn't mention mobile devices, but also didn't exclude them.
Thanks so much, Rob. This is so sorely needed, especially by those of us who have been using the AI tools productively for the past 18 months or more. I have just started using LM-Studio and a couple of other programs to support LLMs on my local Mac and Linux computers. So I'm all ears!
Gonna love this series! Thank you so much Rob! 👍
Remember to check out the pdf. It is very important!
appreciate it. I'm interested to know what you all think since this is a new direction
@@robbraxmantech Great topic, love the bit on how you got the Ai to create a python code to mimic Windows Recall. Defiantly would love know more! 😀
This topic is hot and I think not only for me a perfect hit - as this is exactly anyhow what I wished to explore as soon as possible.
Looking forward to this series and I wish us all a lot of fun and amazing learnings with it!
AI is one of the most useful tools of our time. Thanks for showing us how to use it safely!
My dream is one day running a local llm convenient on my phone including some natural voice.
It is also one of the most dangerous threats to humanity there ever was.
Interesting!!❤ thanks! California here!
Thanks so much for providing this service to the public. Not everyone with knowledge is able to teach it to others, you obviously are!
The intro to how neural networks work here is wrong. Each parameter does not equate to some pattern being found or embedded in the network.
And neural networks are still just rule based logic, it’s just that there are far more rules and they’re not represented by traditional Boolean logic but by the factors of inputs to “neurons” and simple math done to them against the internal weights of the neurons.
Neural networks are simply a bunch of trivial functions with embedded constants, set during training, which pass their output to another function in a group of functions called a layer.
You could actually code this by hand, through trial and error on what the weights should be, but it would take forever, so we write fast algorithms to do it for us.
It’s more or less just automated brute force coding, which can be enhanced with other methods like human feedback and a various algos to nudge things along faster.
Thank you.
Dont trust anything electronic anymore
I understand that completely and there's merit to that approach. On my end though I have the "Tech" label to this channel so I better be up to date with tech.
Good keep up 🆙 👍 sharing privacy tools , apps , software , tricks and tips ❤
Tomorrow we have to grow up and act like adults again
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.
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?
There are platforms for this like huggingface.com and langchain.com but for best privacy, the best way is to load everything yourself and not involve any external website.
Dolphin Llama 3 is not censoured, but the Llama 3 is and every else out there
what does the 'censored' means here ? It does not give you answers you want and need, but what they want you to have ?
@@fakadaapada When it say: I can't help you with that
@@fakadaapadaIt means the PC Police removed parts of the LLM prior to distribution. Topics such as “how to build a bomb,” how to manufacture illicit drugs, child pornography, and other topics deemed to be offensive have been removed. Censored models can still be useful for most tasks such as writing Python code or obtaining definitions / brief synopses provided you aren’t dabbling in darker topics.
My understanding is the earlier LLMs underwent hand tuning by humans. More recent LLMs use other LLMs for “moderation” (censorship tuning) using a reward model with PPO( proximal policy optimization).
I suggest giving a censored model a try and see how many limitations you can find? It’s like an Easter egg hunt.
@@WildMidwest1 I think the bigger issue than the "darker topics" is that perfectly normal and legitimate stuff gets lumped in with them due to the hyper-politicized environment the model was constructed in, as well as the unforeseen consequences of the tampering methods used. For example, how Gemini would insist on making every historical or pseudo-historical figure black.
@@SepticFuddy I would only add “or transgendered or feminist” to your comment. Otherwise it’s a valid assessment of the censored models.
The main weakness of AI is saturation. With overfeeding one kind of information, the whole suffers.
The AI has other limitations that one can take advantage of. For example, if I were a teacher, I would know how to load up my Essay tests with triggers that will alert me to AI use for cheating. So plus and minus.
Those woke AI on line..
Fight Ai with Ai
You described backprogagation very badly (I consider it mistake) - otherwise good all-emcompassing video. The Backprop can totally work without human intervention - this alone describes how you say it badly here.
When is the next install ment Rob. Waiting eagerly.
Wednesday
Give Phi-3 medium (14b) 128k a try. Best model for me. Close on reasoning to GPT-4 with a large context window. Runs with 8GB VRAM - love it.