A technical deep-dive into DeepSeek R1's architecture, training methodology, and performance, exploring how its novel reinforcement learning approach and MoE design advance AI reasoning capabilities.
Analysis of the DarkMind LLM backdoor research paper and why it's interesting but not a cause for immediate concern.
This video explores why testing Large Language Models (LLMs) with simple factual questions misses the point of their true potential. Instead, it demonstrates ho
In this video, I demonstrate how to integrate Hugging Face's newly released Small Agents library with Amazon Bedrock, specifically using the Nova model. The vid
Anthropic's Model Context Protocol (MCP) is a new standard for connecting AI assistants to data sources. In this video I use Amazon Bedrock's Converse API to d
Build a text-based RPG adventure game powered by Amazon Bedrock generative AI with DnD-style mechanics. Full Python setup guide and code walkthrough.
In this video Mike talks to Yuval Belfer from AI21 Labs about LLM model architectures, Mamba, Mixture of Experts, and Jamba at AWS's gen AI loft space in San Fr
In this video Mike experiments with Anthropic's latest model Claude Sonnet 3.5 v2. Sonnet now has support for 'computer use'. Can Claude control Mike's compute
hello and yes the internet is a buzz with the fact that anthropic dropped a new model Sonet 4 is no not Sonet 4 Sonet 3.5 version two is here and it shows some
This is me learning in the open!