Tech
Today was AI reading day. The question to explore: “When will AI systems be able to do all jobs better than humans?” Initially, I was unsure how to approach this question. However, findings from a comprehensive survey of 2,778 AI experts from the top AI journals and conferences provide
Tech
I’m working through a short course on agentic RAG and in my research, I came across a detailed article that explains how and why agentic RAG is better than traditional RAG. (RAG stands for retrieval augmented generation — it’s a way to provide knowledge to LLMs so that their
Tech
I’m completing just one more short course at DeepLearning.ai before getting to personal projects. So I made a start today on the “Building Agentic RAG with LlamaIndex” course. The key topic is a data framework called LlamaIndex. It helps developers and enterprises load, index, and query their data
Tech
I completed reading and working through the StatQuest book I bought on Day 2 of this challenge. “Completed” is a stretch word in this context, though! I could barely follow the final chapter on neural networks. Still, I did get an appreciation for how much of an art form building
Tech
One of the best things I did last year was to get into Python programming. I want to get better at it, and so will continue to build side projects with it. For example, today I automated something that could take many hours to process and instead, I got a
Tech
I’m now 69% of the way through the AI agents course, and I added a new idea to the list of side projects I’d like to build after the course. I look forward to this because I can already see how agents can automate both personal and work-related
Tech
I was very short on time today but I went through a primer on neural networks (I still don’t fully understand them) and made progress on the AI Agents course. I’ve completed about 40% of the agents course and should be fully done with it by day 70.
Tech
I completed the short course on prompt engineering that I started 3 days ago. It was a light introduction to prompt engineering and the key ideas I took away were: * Write clear and specific instructions. * Note: clear and specific doesn’t mean short. In this course and in other areas,
Tech
I watched a video lesson on prompt engineering today. I’m 23% of the way through this short course and already have a few useful tips on how to get more from LLMs. Basics include: * Clear instructions. * They can be short, but often need to be long for more complex
Tech
Today I continued the online course for building agentic AI systems with LLMs. It’s a really simple course. I’m a third of the way through it, and should complete it by the weekend. I already have a list of ideas I’ll get building (and hopefully share here)
Tech
I’ve previously been sceptical about the effectiveness of prompt engineering as a deep specialism, but I’ve changed my views somewhat on “prompt engineering” as a skill set. Which is why today, I enrolled in this short course on ChatGPT prompt engineering. I use ChatGPT mostly when writing code,
Tech
Back propagation is one of those cool machine learning terms that sounds intimidating. And rightly so. The full maths behind it isn’t for everyone. However, knowing the basics is achievable, and I found the video below especially helpful today. I also like this video on gradient descent, which is