Want to get notified about new posts? Join the mailing list and follow on X/Twitter.
Raphael Traviss used Deep Research + The Math Academy Way to generate a structured progression for improving his painting skills, and then followed it for 5 months (10h/week).
End result was a transformation so pronounced that a pro-level artist in his painting group took notice.
Best part is that these aren’t just beginner gains. He was already impressive to begin with (at least, to me).
But then he hit a years-long plateau. And this is what broke him out of it and took him to the next level.
He explained his workflow here, including the actual prompt links.
If you want to know more, then go follow him and pester him to make a hyper-detailed longform post covering all aspects of the journey!;)
x.com/raphaeltraviss/status/1925366765200015638
Follow-Up Questions
Do you think it os easier to form a MA style curriculum for a subject with LLMs now with the newer models compared to when you tried using them to learn biology?
Raphael demonstrated that you can get a solid syllabus, which is half the battle in something like portrait painting where the dependency graph “is not known ahead of time, or at least is not well articulated” (quote from Raphael’s prompt).
However, this is different from the actual instruction & practice arena.
I’m still of the opinion that
- LLMs themselves are not the optimal environment for the arena (elaborated here),
- but you can use them more efficiently than most static materials (e.g., textbooks) if you really know what you’re doing from a pedagogy/learning efficiency standpoint — but you really really need to know what you’re doing and very few learners do.
In more detail, my overall conclusion is this:
- IF you could learn successfully, long-term, by self-studying textbooks on your own, and the only thing keeping you from learning a new subject is a slight lack of time,
- THEN you can probably use LLM prompting to speed up that process a bit, which can help you pull the trigger on learning some stuff you previously didn’t have time for.
- BUT the vast, vast majority of people are going to need a full-fledged learning system.
- And even for that miniscule portion of people for whom the “IF” applies… whatever the efficiency gain of LLM prompting over standard textbooks, there’s an even bigger efficiency gain of full-fledged learning system over LLM prompting.
Want to get notified about new posts? Join the mailing list and follow on X/Twitter.