Personal tutors for everyone

Status: I built it and shut it down after — here’s a demo video

Being question driven

The fastest and most fun way for me to learn is to shoot a whole bunch of questions. That's why I love office hours. Imagine being able to show up to an expert's office, and ask any question. I am so grateful that most of the people discovering things on the cutting edge are also educators.

I don't think a structured, sequential syllabus is not the best way to learn. Motivation to learn: curiosity, comes from asking questions. Maybe I just want to learn how the COVID-19 vaccine works — I don't need to study a whole introductory biology course to learn about this. But maybe I run into the fact that the best vaccines are mRNA based, and then learn about what mRNA is, then the central dogma. All my learning started with a question I had — not one that was presented to me. I was in charge of my learning, not a syllabus.

Personal tutors

It's pretty well established that the average student learns much better when they have a personal tutor, that they can ask questions to.

The average student tutored one-to-one using mastery learning techniques performed two standard deviations better than students educated in a classroom environment with one teacher to 30 students

Historically, this has been prohibitively expensive to do. Hiring an expert for every student gets very costly very quickly. Students are left to watch lectures and fend for themselves.

They're still curious though! They'll google questions they have — sometimes not getting anywhere close, because they just don't know how to phrase questions. Or maybe, the answers are just plain incomprehensible.

The next step may be asking a question online on Quora or Stack overflow. This means waiting several days before you get an answer, and can continue discourse. The feedback loops from question -> reply is incredibly slow.

Enter large language models

Today though, I think we might have a real shot to get everyone a personal tutor. Large language models like GPT-3 are getting really good. These are big neural nets (175B+ parameters), trained on a corpus of text representing a significant percentage of the internet. They're trained to essentially autocomplete text.

The prototype on lets you ask questions like you're in office hours. It combines several LLM completions along with querying the internet on each message to fetch relevant information through semantic search, and then generates a relevant reply.


There's also promising progress on understanding the accuracy of LLMs. That means this AI tutor will be able to actually know when they're wrong!

I think we might just have enough technology development to make it feasible to give every student a personal tutor to enable question driven learning.

What's next?

I want to get people using Riff immediately. The product is incredibly basic, and will break often right now, but I think it's still usable and helpful. I think a good target to start with is curious high schoolers, but I'd love to have any self motivated learners on!

I'm also starting to build out a team that is excited about the things talked about on this page, and wants to work on this stuff! It'll mostly be part time hacking to build tech that actually helps with education.

Please get in touch if you either want to start using this or working on it — especially get in touch if you're an education company, or in any way work in education :)