Tech

Day 69 of 100 Days of AI

Michael Tefula

02 Jun 2024 — 1 min read

I’m completely “coursed out”!

Over the last 2 and a bit months I finished 7 online courses:

IBM Machine Learning Professional Certificate (Started on Day 1, finished on Day 17)
AI for Everyone (Started on Day 28, finished on Day 33)
Python for Data Science, AI & Development (Started on Day 33, finished on Day 53)
Multi AI Agent Systems with crewAI (Started on Day 54, finished on Day 64)
ChatGPT Prompt Engineering for Developers (Started on Day 58, finished on Day 61)
StatQuest Book (Ordered the book on Day 2, finished on Day 65)
Building Agentic RAG with LlamaIndex (Started on Day 66, finished on Day 69)

The final online programme I completed today was this course on “Building Agentic RAG with Llamaindex“. Unlike other courses I rushed through this one because I wanted to get a quick overview and see if the framework taught is relevant for where I’m at with LLMs.

The short answer to the above question is that I won’t need this framework for now since between Langchain and CrewAI, I have enough to keep me busy.

In the coming days I’ll work on some side projects, proof of concept ideas, and share snippets on the blog. I’ll also continue to share daily learnings about AI.

A Goldilocks Introduction to AI Agents: Opportunities, Challenges, and Everyday Impact

AI agents have quickly evolved from obscure technical experiments to mainstream buzz. In the last 18 months, new automation capabilities have captured the imagination of entrepreneurs and established organizations alike. While it’s possible that we’re in another AI bubble, the early adopters of AI agents are reporting impressive

Open Problems (& Opportunities) for AI: Summary Notes from the Conference

Last week I attended the Algorithmic Innovation & Entrepreneurship Summit on Open Problems for AI. That’s a bit of a mouthful but in essence, it was a 2-day conference covering the challenges and opportunities for AI over the next 5 years. Day 1 was focussed on algorithms and AI

The Software Engineer is Dead, Long Live the Software Engineer!

An undeniable killer use case for large language models is code generation. It’s already helping software developers write code up to twice as fast and with more delight. As LLM models improve with each release, they can write better software and handle more complex architectures at a fraction of

Day 100 of 100 Days of AI 🎉

AI agents have been getting a lot of attention but they can be expensive to run. This is because they use a lot of tokens and make multiple calls to LLMs. Some AI developers have beat performance benchmarks by using exceptionally expensive agentic runs. However, this is unrealistic because in

Read more

A Goldilocks Introduction to AI Agents: Opportunities, Challenges, and Everyday Impact

Open Problems (& Opportunities) for AI: Summary Notes from the Conference

The Software Engineer is Dead, Long Live the Software Engineer!

Day 100 of 100 Days of AI 🎉