May 6 · 8 min read · Previously when talking about AI coding, most of the discussion was about what it can do and how beautifully it does it. Today I'll flip the coin and record two things I recently couldn't solve: one barely made it to the finish line, the other was sh...
Join discussionMay 6 · 8 min read · The density of model releases this April was a bit insane. Opus 4.7 dropped on April 16, the same day Codex CLI launched Goal Mode. On April 23, GPT-5.5 (codename "Spud") went live, followed on May 5 by GPT-5.5 Instant replacing ChatGPT's default mod...
Join discussionMay 2 · 6 min read · Today we are deconstructing the 4-Star Dragon Ball shader (available on Shadertoy here). This shader is a good example of using 2D math to drive 3D optical effects. To understand it, we must reference
Join discussion
May 1 · 8 min read · Today, I ran into two things—one that made this era feel a little unreal, and one that made it feel very real. I. A 23-Year-Old Outsider Cracked a 60-Year-Old Conjecture Liam Price, 23, with no advanced mathematical training. On a Monday afternoon a ...
Join discussionMay 1 · 11 min read · A few days ago, I attended a conference where the topic shifted to how AI is changing scientific research. It was supposed to be a closing session, but the conversation wouldn't stop. Several interesting points didn't get fully explored, so I've been...
Join discussionMay 1 · 11 min read · In early April, a company called Belo was banned by Anthropic overnight. More than 60 employee accounts were deactivated simultaneously, and the entire team's workflow built on Claude instantly collapsed. Appeal? No customer service, no email—only a ...
Join discussionApr 21 · 6 min read · The debate over vibe coding never stops. On one side, it's treated like a wishing well—throw every task into it; on the other, it's slapped with a "trash code factory" label. I can't accept either. Tools aren't a matter of faith. Rather than picking ...
Join discussionApr 14 · 6 min read · Recently, I've been working intensively with coding agents, and I made a surprising discovery. AI excels at getting things to 80% or even 90%. Give it a task, and it quickly produces something that looks good. But "looking good" isn't the same as bei...
Join discussionApr 14 · 4 min read · Lately I've been thinking about a problem. I've thought about it for a long time, but haven't figured it out. How to lead a team, how to divide work—these are things I used to think had established patterns. Now I'm finding those patterns don't work ...
Join discussion
