Wouldn't one want to use differently trained models for each agent anyway. Models that are trained on the knowledge that an agent should have? Of course, the model one has access to would still be the bottleneck. If the local LLM models are not as good as a paid model from OpenAI or Google, one would always have less good output or should stick to more simple tasks. Nice experiment though and a good start for the innovations to come as more and better LLMs get available. And CrewAI get's improved.
This is so over my head it is not even funny!!! But oh so exciting!!! Need to find some time to look into all this!!! Where does one even start? Thanks so much for the video!!!
You are an idiot if you believe Ai is capable of HIGHER LEVEL THOUGHT. It is NOT. You are being sold a "pack of lies". AI can only do what it's programmers tell it to do....PERIOD. DOT. END. If it's programmers CLAIM AI can think, think again. It cannot. AGAIN, AI can ONLY do what it is told (meaning programmed to do)....period, dot, end. Anyone telling you different....IS A LIAR.
Hello Maja, thank you for the great informative videos you provide here on this platform. I have a question regarding the installation of Autogen Studio 2.0. On their website it is mentioned that you should use conda for the virtuell environments. However, you don't use this in your video. Is there a specific reason for this?
I like your videos! Not only because you go deeper into technical details than many other LLM youtubers but also your style of presentation and voice is very pleasant. Keep on doing more videos 😊
Since we don't have access to the training data, it is simply impossible/unfeasible to choose models based on whether they have or don't have contaminated data.
So much has changed since. One of the executives of OpenAI openly called for genocide in Gaza, and Elon Musk also cheered on the genocide. On top of, Israel's use of AI targeting systems, with daily target numbers that match up with the daily brutal massacres in Gaza. So much to talk about, and so few people talking about it.
Good video but the varied levels of the volume of your voice is all over the map (sometimes super loud, and sometimes way too soft with sudden switches between the two) which makes it difficult to listen to you and hear you clearly at times... Please run your audio through post processing to clean this up
Hey guys! I'm immersed in the study of AI agents and I'm curious: would it be viable to build an agent that prospects customers for freelance professionals? I envision a system capable of exploring Instagram in an automated way, identifying potential customers and even starting conversations to schedule sales meetings. Is it possible to develop such AI agents? If so, do you know of any videos on RU-vid or any mentors that explain how to create AI agents to automatically prospect customers through Instagram? Is there something like this in development or is this an idea for the future of AI?"
Did not find openai_api_key, please add an environment variable `OPENAI_API_KEY` which contains it, or pass `openai_api_key` as a named parameter. (type=value_error) # To Load GPT-4 api = os.environ.get("sk-proj-fNk......")