🔥🔥 crewAI v0.30.10 is out🔥🔥 🧙 Set a manager 📄 Set system, prompt and response templates 👨‍💻 Improved json/pydantic output 🔎 Better tool recognition 🧰 Better tool usage 📄Bring your prompts 🪚 New tools browserbase 🅱️ and Exa And more! Docs will follow RT please?

Convolutional Neural Networks in action

Transformers animated, in 30 seconds. From Grant Sanderson

We've all dealt with activation functions while working with neural nets. - Sigmoid - Tanh - ReLu & Leaky ReLu - Gelu Ever wondered why they are so important❓🤔 Let me explain it to... 👇

llm.c by Hand✍️ C programming + matrix multiplication by hand This combination is perhaps as low as we can get to explain how the Transformer works. Special thanks to Andrej Karpathy for encouraging early feedback and tetsuo - cRc for helping me understand the pragma magic. I hope

5 techniques to fine-tune LLMs, explained visually! Fine-tuning large language models traditionally involved adjusting billions of parameters, demanding significant computational power and resources. However, the development of some innovative methods have transformed this

Individual Neuron: Neural Network A neuron in a neural network performs a weighted sum of inputs, adds a bias, and applies an activation function like sigmoid, ReLU, or tanh, introducing non-linearity. This output helps the neuron learn and represent patterns in the data.

The Transformer's encoder clearly explained 👇🏻

rebranding Linear Algebra as Artificial Intelligence was the most successful marketing campaign of all time.

The Transformer's encoder clearly explained 👇🏻

This paper tells us that KAN (Kolmogorov–Arnold Networks) is not that great in comparison to MLPs (Multi-Layer Perceptrons) 📌 KAN can be viewed as a special type of MLP, with the key difference being KAN's use of learnable B-spline functions as activation functions instead of

Visualization of what a model like ChatGPT does to produce such efficient responses!

Oxford researchers recently unveiled MedGraphRAG, a framework boosting RAG accuracy in medicine. It features hybrid chunking for context-preserving document breakdown, a three-tier hierarchical graph linking entities to core knowledge, and meta-graph tagging for a comprehensive

Transformers visually explained:

Anna Rahn's video demonstration of Multi-Layer Perceptron (MLP) by hand ✍️ Anna made this short video for my computer vision course in the spring semester. Together with the spreadsheet exercise I posted yesterday, I hope they help more people understand deep neural networks!

IBM and CrewAI partner together starting today to help enterprises across the US and the globe on adopting AI Agents at scale. RT Please? We are shipping fast, fastest I've seen! ibm.com/new/announceme…

AI Agents In Production! insights.crewai.com RT Please? 🙏

> be an electric engineering student > team up w/ cracked classmates > start quant trading *we’re so cracked* > founded a quant firm in his 30’s > makes ¥100B trading with ai/ml *we’re even more cracked with ai* > buys thousands of Nvdia GPUs > creates DeepSeek as a side project

OpenAI just dropped a paper that reveals the blueprint for creating the best AI coder in the world. But here’s the kicker: this strategy isn’t just for coding—it’s the clearest path to AGI and beyond. Let’s break it down 🧵👇

For the next 24 hours you can STEAL my n8n swipe file containing 12+ automation's. All of these can be setup within 60 MINS and SAVE you 10+ HOURS per week. Easily worth $997+ Today It's yours for FREE 👉RT + Like & Comment “n8n” and I’ll DM you the file (Must be following)