I just watched OpenAI's first "Apple-style" developer event, and here's what you need to know: GPT4 used to be the best model, but now they have announced GPT4-Turbo, which is: - Better - Faster - Cheaper - Has more functionality - And has 128k input tokens (that’s 300 pages it can analyze at once!) That is incredible. But what does this mean for you? 🤔 Well, ChatGPT and custom AI solutions are going to get a lot better, which can ultimately help you become way more productive. They have also introduced "custom GPTs", a new way for anyone, including you, to create a personalized version of ChatGPT (no coding required) and share them with others. For instance, you can create a custom ChatGPT app using your own data (private, of course) to onboard new employees and provide them with all the necessary information. 🙋🏼‍♀️ And there's much more, which I'll discuss later. Once again, OpenAI has pushed the boundaries of what's possible. What are you most excited about?

Just got this in my inbox today. I signed up and it looks like a quality, free course by Weights & Biases, which I hold in high regard. Check out the training

Not sure why, even though it was just a guide...Somehow i feel good about training a the Mistral 7B model, on AWS Sagemaker, on the Dolly dataset. I felt the need to screenshot it and everything, a whole 3 hours and 41 minutes 15 seconds. Well, here's the guide so you can too! I did end up cloning the entire repo into my SageMake studio, here that is. Next step, figuring out how to sort out these agents datasets so I can train it on them! Happy Teching!

Does anyone else find Autogen super cool? Integrating it with other models outside of gpt-4 is interesting. I used claude-instant via Bedrock Here's some docs to help you utilize other models: https://github.com/microsoft/autogen/issues/46 https://docs.litellm.ai/docs/proxy_server Once you have the proxy, you can run the litellm models from the command line. Then you just create a config_list as such -> config_list=[{"model": "bedrock/anthropic.claude-instant-v1", "api_base": "http://0.0.0.0:8000", "api_type":"open_ai", "api_key":"NULL"}] and an llm config -> llm_config={ "request_timeout": 600, "seed": 42, "config_list": config_list, "temperature": 0, } Then you can pass that LLM config into the agents and start the Autogen agent escapades! Reference: https://github.com/microsoft/autogen/blob/main/notebook/agentchat_web_info.ipynb Try it out and let us know what you come up with! I'm going to do a bit more testing after work today.

I recently came across this list of 60 best AI tools of 2023 for various fields like design, YouTube, research, writing, coding, marketing, sales, Twitter, and music. Inviting you to share your favorite AI tools and help our community discover and harness the potential of these cutting-edge technologies. Your contributions are greatly appreciated!