I finally hit 1,000 days of doing math daily! Early on in my journey I was a lot more aggressive with my XP targets, but settled into a low-volume rhythm as my goals evolved. I worked from MF1 (Math Foundations 1, lowest level) into MF3, then about halfway through MF3 I started M4ML (Mathematics for Machine Learning). But it got really hard and my progress started to slow…
I’m working on a new app called Main Character. It’s a gamified productivity app where you earn XP and level up for completing tasks & tracking habits. Tasks run on a kanban board and habits show up on a GitHub-style consistency graph. Basic tasks + habit tracking are live today and I use it daily. Long term I’m turning it into an AI orchestration…
Over the last few months I went deep burning ~$1,000/month on tokens building various ‘agent-native’ products and trying new things. I finally realized what ‘agent-native’ means through trial and error. I couldn’t believe how simple it was. I’ll explain the gist here to save you the hassle, and hopefully you’ll use it to build something awesome. Current (pre-AI) software assumes the…
Over the last few months I went deep burning ~$1,000/month on tokens building various ‘agent-native’ products and trying new things. I finally realized what ‘agent-native’ means through trial and error. I couldn’t believe how simple it was. I’ll explain the gist here to save you the hassle, and hopefully you’ll use it to build something awesome. Current (pre-AI) software assumes the…
HaaS will be the new SaaS…but we’ll still call it SaaS because it’s all just software. I had this realization when I tried using GPT Codex and Gemini in Cursor with plan mode. Opus/Sonnet are insanely good with Cursor plan mode, but Codex/Gemini are pretty bad in that harness. What I learned is that the models work different in how they plan execute, which makes sense.
The AI boom is exciting, there’s so much opportunity and so much to build at the application layer. But the question is: what to build? Two theses I’ve seen for AI application startups: On the first one, I don’t consider luck a strategy. This could work, but as a founder I’d have a hard time building something that isn’t sustainable or without a long-term vision. On the second…
Most of my experience with AI had been retrofitting: Incorporating AI into existing software and codebases. Yeah, what a mess. I imagine it’s like it was trying to electrify existing factories. The habits, workflows, assumptions, etc. were just too different. Contrast that with starting a new project with AI so everything is AI-native and code is AI-maintainable from the start.
If AI isn’t writing 50%+ of your code by the end of the year, you’re moving too slow and you’ll get lapped by the next competitor who does. The bar will be 90%+ soon after (for me it’s over 99%). There may have been an excuse before, but not since Sonnet 4.5 released. If you try it and think it’s still not good enough, you’re probably using it wrong. And it’ll only get harder to adapt as…
Time-based estimates don’t make sense when your pair programmer is an AI. So, I switched to ETM (estimated tokens to merge). It’s the agent’s token budget to design, implement, and polish a feature until it’s merge-ready. Doing that helped flip to more of an AI native, agent first mindset that’s helping me embrace a new way of working. By default Cursor always gave me…
Time-based estimates don’t make sense when your pair programmer is an AI. So, I switched to ETM (estimated tokens to merge). It’s the agent’s token budget to design, implement, and polish a feature until it’s merge-ready. Doing that helped flip to more of an AI native, agent first mindset that’s helping me embrace a new way of working. By default Cursor always gave me…
The biggest bet in tech right now isn’t a deliberate decision, but rather the result of company cultures that were a benefit until they weren’t. The result? Apple and Amazon will miss AI like Intel missed mobile. Tim Cook and Andy Jassy “CEOs of Apple and Amazon” both agree that AI is a paradigm shift, “as big or bigger than the internet.” But the strategies their companies are…
The biggest bet in tech right now isn’t a deliberate decision, but rather the result of company cultures that were a benefit until they weren’t. The result? Apple and Amazon will miss AI like Intel missed mobile. Tim Cook and Andy Jassy “CEOs of Apple and Amazon” both agree that AI is a paradigm shift, “as big or bigger than the internet.” But the strategies their companies are…
This is my 3-year investment update following buying the dip on ‘pandemic stocks’ that declined (70%+) in 2022. I started sharing public updates 1-2 times a year. Data in this update is as of June 2025. In early 2023 I built one of the first AI products at my company and my head exploded with the possibilities. So later that year I started reallocating into AI-related stocks.
This is my 3-year investment update following buying the dip on ‘pandemic stocks’ that declined (70%+) in 2022. I started sharing public updates 1-2 times a year. Data in this update is as of June 2025. In early 2023 I built one of the first AI products at my company and my head exploded with the possibilities. So later that year I started reallocating into AI-related stocks.
Heuristic ([H]) or bot ([B]) contests are a killer way to improve your programming, problem-solving, and prototyping skills. It’s best to just dive in and focus on rapid improvement. Here are my notes from this tweet storm on the topic, credit to Psyho for the insights. Make touch typing your top priority. Spending 10-30 hours mastering this skill drastically improves…
Heuristic ([H]) or bot ([B]) contests are a killer way to improve your programming, problem-solving, and prototyping skills. It’s best to just dive in and focus on rapid improvement. Here are my notes from this tweet storm on the topic, credit to Psyho for the insights. Make touch typing your top priority. Spending 10-30 hours mastering this skill drastically improves…
I was having trouble charging my phone (iPhone 12 Pro Max) yesterday and wondered how old it was. It’s 5 years old I was shocked, that’s the longest I’ve ever had a phone. Before this one I was on the Apple upgrade program for years, so I got a new phone every year. Then I stopped because setting things up on a new phone became more trouble than the benefit of getting a new phone.
I was having trouble charging my phone (iPhone 12 Pro Max) yesterday and wondered how old it was. It’s 5 years old I was shocked, that’s the longest I’ve ever had a phone. Before this one I was on the Apple upgrade program for years, so I got a new phone every year. Then I stopped because setting things up on a new phone became more trouble than the benefit of getting a new phone.
I recently crossed 500 days of practicing math daily with Math Academy. I wrote about my experience after 100 days here. TL;DR: I am still very impressed by the Math Academy system and highly recommend it, but you get out of it what you put in. My consistency has been exceptional, but my volume has been frequently low, which has had a cascading impact on my progress. To help…
I recently crossed 500 days of practicing math daily with Math Academy. I wrote about my experience after 100 days here. TL;DR: I am still very impressed by the Math Academy system and highly recommend it, but you get out of it what you put in. My consistency has been exceptional, but my volume has been frequently low, which has had a cascading impact on my progress. To help…
Machine Learning
Gaming
AI
Programming
Tutorial
Business
Career
Data Analysis
Hardware
Mobile