PinnedWhy You Need a Custom Domain Chatbot: A DIY Guide Based on OpenAI’s ChatGPTWhat technologies / techniques are behind it ?Feb 9, 2023Feb 9, 2023
Llama 3.1 is out. How important is it? What can we do with it?.. ( is ) something that basically like lifts all boats around the world and just has a massive kind of equalizing effect³.Jul 24, 2024Jul 24, 2024
LLM AgentsLLM agents planning and executing complex activities like organize one week Paris holiday for NYC based family of four depends on LLM…Jul 12, 2024Jul 12, 2024
Google Gemma — Open Source Game ChangerGoogle just released Gemma 2 , a family of little big open source models. It offers impressive customizaton capabilites, making it look…Jul 3, 2024Jul 3, 2024
Diffusion Gen AI ModelsDiffusion models are a family of probabilistic generative models that progressively destruct data by injecting noise, then learn to reverse…May 9, 2024May 9, 2024
Llama3 — What We Know So FarLlama3 is #1 open source¹ and top 10 overall ranked model.May 2, 2024May 2, 2024
Infinite Context TransformersTransformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a fnite context…Apr 21, 2024Apr 21, 2024
Q* or What Comes Next in LLM LandIt is relatively obvious ( bar emerging surprises ) that brute force LLM scaling won’t get us to LLMs capable of planning and reasoning…Apr 3, 2024Apr 3, 2024
OpenAI Sora and Open Source Efforts to Catch UpMy mental model of Sora is that it is the “GPT-2 moment” for video generation.Feb 17, 2024Feb 17, 2024
OLMo — Interesting PointsOLMo was trained on both NVIDIA A100 and AMD MI250X hardware. This is of huge importance, given the current shortages of NVIDIA GPU and…Feb 2, 2024Feb 2, 2024