{"id":805,"date":"2024-04-13T17:08:13","date_gmt":"2024-04-13T17:08:13","guid":{"rendered":"http:\/\/morganredfield.com\/blog\/?p=805"},"modified":"2026-02-27T17:20:01","modified_gmt":"2026-02-27T17:20:01","slug":"learning-from-an-llm","status":"publish","type":"post","link":"https:\/\/morganredfield.com\/blog\/2024\/04\/learning-from-an-llm\/","title":{"rendered":"Learning from an LLM"},"content":{"rendered":"\n
\"\"<\/a><\/figure>\n\n\n\n

After a lot of flailing, I’ve finally found a method of learning from ChatGPT (or other LLMs) that’s helpful for complex subjects.<\/p>\n\n\n\n

In the past few years, I’ve gotten a lot of use from LLMs for small bounded problems. It’s been great if I have a compiler error, or need to know some factoid about sharks, or just want to check an email for social niceties before I send it.<\/p>\n\n\n\n

Where I’ve struggled is in using it to learn something complicated. Not just a piece of syntax or a fact, but a whole discipline. For a while, my test of a new LLM was to try to learn about beta-voltaic batteries from it. This was interesting, and I did learn a bit. The problem was that I felt adrift and didn’t know how to go past a few responses to dig into what really mattered in the physics of the topic. It worked as a test of the LLM, but not for learning the topic.<\/p>\n\n\n\n

Today I tried having ChatGPT teach me about SLAM, and it worked surprisingly well. The main difference was that I went in with an outline of what I wanted to learn. Specifically, I used this list of 100 interview questions<\/a>. This gave me a sense of progress – I knew I was learning something relevant to my topic. It also gave me a sense of what done looked like – it was very obvious that I still had 46 questions to go, so I hadn’t explored everything yet.<\/p>\n\n\n\n

My overall method was:<\/p>\n\n\n\n