Naval Ravikant, co-founder of AngelList and well respected entrepreneur and investor, thinks that we are heading towards a future where we will all be freelancers again. He offers valuable insights into why this shift might occur Factors such as the rise of remote work, the emergence of freelance platforms, advancements in AI technology, and evolving cultural norms are all contributing to the gradual transformation of the work landscape, working together to reduce external transaction costs. Naval also makes a fair point about humans not being built to work consistently all the time and still be expected to remain productive. Quality of work output is not linear. He describes how the "modern knowledge worker athlete" is most productive. Which involves training hard, sprinting, resting, and reassessing, then using the feedback loop to prepare for the next sprint. Similar to how freelancers move from project to project. If you purely look at the numbers, Naval might be onto something here. According to a recent study by Upwork: - Freelancers made a significant contribution of $1.27 trillion to the U.S. economy in annual earnings in 2023, which is a substantial increase from $713 billion in 2014. - The study also revealed that the number of professionals freelancing has risen to nearly 64 million Americans, accounting for 38% of the U.S. workforce. This marks a noticeable growth from 34% in 2014. I've been freelancing for a decade, so I might be a bit biased, but I agree with Naval's perspective on the future of work. What do you think? Will the number of freelancers continue to increase in the future? And have you ever considered freelancing? What's holding you back? Let me know your thoughts in the comments below!

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.

Hi Everyone, We are working on video generation but instead of creating abstract videos, I want to focus on an Individual's video sort of like an instructor. What are some of the fastest models you've worked with for such cases? I would love to know about your take on such models.

Hi everyone, I am trying to have a small look at Autogen. And trying out the examples mentioned in Mathews video ... https://www.youtube.com/watch?v=V2qZ_lgxTzg&list=PLp9pLaqAQbY2vUjGEVgz8yAOdJlyy3AQb&index=1 Problem. Even just trying the first example I get nothing but mistakes. And I am absolutely clueless about how to solve them. In Colab the Autogen script works however. Would be great if someone had 15 minutes for a zoom call or some helpful tips.

Hi all, just starting a list of running GitHub repositories for sharing, for both learning and projects. Feel free to drop any of your go-to's in the comments! https://github.com/josephmisiti/awesome-machine-learning https://github.com/natnew/Awesome-Data-Science https://github.com/donnemartin/data-science-ipython-notebooks https://github.com/trekhleb/homemade-machine-learning https://github.com/kmario23/deep-learning-drizzle https://github.com/ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code https://github.com/Machine-Learning-Tokyo/Interactive_Tools