Search through your saved bookmarks
1267 items — page 5 of 26
Getting useful results from your AI assistant often comes down to the instructions you give it. Most developers treat that step casually, then wonder why the output is mediocre. One of the simplest ways1 to improve this is to keep one set of master instructions in an AGENTS.md file. In it, you define persistent rules that shape every interaction with the agent. Writing those instructions once is easy enough. Keeping them in sync is the annoying part. If you use more than one tool, things drift fast. So I keep one repo as the source of truth for my AI setup, then wire my tools and projects back to it. This post is the simple version of that setup.
Jul 3, 2025
Jul 1, 2025
You will have to work harder than others.
Jun 29, 2025
The way you increase your ability to make mental leaps is not actually by jumping farther, but rather, by building bridges that reduce the distance you need to jump.
Jun 29, 2025
To build automaticity: instead of deriving/reasoning a result before applying it, force yourself to first recall the result from memory, and then justify the it afterwards. Recall first, reason second.
Jun 26, 2025
Jun 24, 2025
Jun 18, 2025
Jun 17, 2025
@DamiDina Even then it’s just text-in, video-out. Everything (ChatGPT included!) has a simple interfaces. Meanwhile all these startups are theorycrafting about weird agent UIs that nobody wants to u…
Way too many people overthink AI user interfaces. The most popular new AI tool (Claude Code) literally just runs in your terminal. It’s gonna be hilarious when AGI is just a CLI.
Jun 13, 2025
Jun 12, 2025
Strategies and tactics for staying productive.
Jun 12, 2025
Jun 10, 2025
May 31, 2025
May 31, 2025
May 30, 2025
May 29, 2025
May 27, 2025
May 27, 2025
Use case or problem I have a few properties I would like to display in bases that can quickly cause the base to scroll horizontally. It would be far better to read these cells if they didn’t occupy a single line. Propos…
May 26, 2025
May 26, 2025
May 25, 2025
May 21, 2025
May 20, 2025
You’d think that teacher training programs would focus on the mechanics of learning, but instead they typically focus on ritualistic compliance. If we trained doctors like we do teachers, then we’d still be bloodletting. Teacher credentialing severely lacks rigor, and this lack of rigor leads to a massive loss in human potential. Students suffer for it, and it drives serious educators out of the profession. It attracts and supports the type of people who think it’s more important to practice sharing circles than to learn about the importance and implementation of spaced review. When you make it your mission to maximize student learning – including leveraging the learning-enhancing practice techniques that have been known, reproduced, and yet ignored by the education system for decades – you realize that there is a massive amount of human potential being left on the table. Students can be learning way, way, way more than they currently are.
May 14, 2025
May 13, 2025
More volume equals more progress provided that you’re working productively and not burning yourself out.
May 12, 2025
May 11, 2025
If you’ve done honest work, you should be able to back it up.
May 6, 2025
When the time comes to get back into the swing of things, it’s a lot easier to speed up a slow wagon that you’re on, than to get back on a wagon that you’ve completely fallen off of.
May 4, 2025
May 3, 2025
Apr 26, 2025
Asking a model to extrapolate is like asking a pig to fly.
Apr 18, 2025
… is that it has to be robust to all sorts of behavior arising from the various human emotional experiences associated with learning & intense training.
Apr 6, 2025
We tend to vastly underestimate how much of our problem-solving ability comes down to accumulated domain expertise.
Apr 5, 2025
“Wait, am I… cracked? No way. But I just did this thing that I’ve seen cracked people do and I wasn’t able to that before. Holy shit I’m actually getting cracked.”
Apr 4, 2025
Apr 3, 2025
It makes sense when you think about the underlying interests that shape the behavior of students and teachers.
Mar 24, 2025
… is to skip over computational practice and lose touch with the concrete meaning of things.
Mar 23, 2025
Mar 21, 2025
Mar 21, 2025
A simple but powerful approach to note taking
Mar 19, 2025
Mar 19, 2025
Mar 16, 2025
Mar 13, 2025
During its operation from 2020-23, Eurisko was the most advanced high school math/CS track in the USA. It culminated in high school students doing masters/PhD-level coursework (reproducing academic research papers in artificial intelligence, building everything from scratch in Python). It’s still early and the first cohort hasn’t even graduated from college yet, but there have already been some amazing student outcomes in terms of college admissions, accelerated graduate degrees, research publications, and science fairs.
Mar 12, 2025
Mar 3, 2025
Mar 2, 2025
Mastery learning – one of the most reliable, largest-effect-size techniques for elevating student learning outcomes – centers on learning prerequisites. In fact, the famous Two-Sigma Problem is centered around the effectiveness of mastery learning.
Feb 28, 2025