I just checked out the new version of the AutoGen framework, AG2. It feels like I’m always missing something, only to check the docs and realize they mostly add zero value while taking away control over implementation. I get the need for no-code agent frameworks targeting non-engineers, but I don’t understand frameworks like AutoGen that are aimed at developers. Once you’ve built agents from scratch, it’s hard not to see these frameworks as just bad wrappers. The real challenge in building agents isn’t the code—it’s everything around it (evaluation, prompt engineering, memory management, context management etc.). Am I missing something?

The goal of this group is to help you navigate the complex and rapidly evolving world of data science and artificial intelligence. This is your hub to stay up-to-date on the latest trends, learn specialized skills to turn raw data into valuable insights, connect with a community of like-minded individuals, and ultimately, become a Data Alchemist. Together, let's decode the language of data and shape a future where knowledge and community illuminate our way. Rules - Don't sell anything here or use Data Alchemy as any kind of funnel - We delete low effort community posts, and posts with poor English. Proofread your post first. - Help us make the posts high quality. If you see a low quality post, then click on the 3 dots on the post and "Report To Admins". Start by checking out these links - Classroom - Introduction - Roadmap - Contribution Be Aware of Scammers - Please be aware that this is a public group. Unfortunately, some people abuse the Skool platform to send DMs or post comments to trick people. This is the internet, so always do your own due diligence. Never automatically trust someone here on the Skool platform other than @Dave Ebbelaar's official account. To kick things off, please comment below, introducing yourself. Let us know: 1. Your name and where you're from 2. What project(s) you're currently focused on See you in the comments!

I have added chatgpt extension in VS code. It can complete an entire for loop in python, its amazing. Has anyone incorporated DeepSeek into VS code? I know DeepSeek is "free" but there has to be a price. If you use it, how compromised is our data.

For anybody who has just started learning AI agent, It gets very ovewhelming seeing a lot of tools and frameworks in the market. It becomes very important to understand whats really happening inder the hood. I benefitted a lot from this where the creator has taught ReAct agent building using python without any framework from scratch https://www.youtube.com/watch?v=hKVhRA9kfeM

These courses, from DeepLearning AI, are really complementing very well each other and are a GOLDMINE - How transformer LLMs work - Attention in Transformers: Concepts and Code in PyTorch The first one involves Jay Alammar and Maarten Grootendorst, co-authors of the book "Hand-On Large Language Models" (the "framework" followed being HuggingFace) What makes the book and the courses shine are the relevant illustrations. By the way, they're continually adding resources to the book, via their YouTube channels (see above) and their Newsletter (their last article being a "debunking via illustration" of DeepSeek's architecture) The second one involves Joshua Starmer (💥💥💥) from the reknowned StatsQuest channel and LightningAI He has also written several great visual books related to Machine Learning ENJOY!