I used pi to create a compact home page for media.s-anand.net using these prompts: Create index.html - a simple, elegant page that says that this page (media.s-anand.net) serves large media files for Anand - that’s where they should look instead. … followed by: Skip the part that says “Please visit …” … then: Shorten index.html to just 2-3 elegant rules of CSS. I want it MUCH smaller and simpler. … and finally: Center vertically and horizontally. ...
I wrote about my changing AI opinions. At least some of this is because the industry is moving so fast that the bottlenecks keep shifting. Here are four examples of how we AI couldn’t do something (the bottleneck), but that became possible, and the bottleneck shifted - changing the way we work. It’s good to keep this in mind when thinking about AI. Coding: “It can’t write useful code. We can’t get real help.” But in Sep 2022: GitHub finds Copilot developers are 55% faster. “It writes code but doesn’t know our codebase. We can’t let it touch real projects.” But in Feb 2024: Gemini 1.5 Pro has 1M-token context ~ 30K LOC". Cursor indexes code. “It understands the repo but can’t ship a fix on its own. We can’t hand it a whole issue.” But in Mar 2024: Devin solves 14% of SWE-bench - up from 2%.. Verified SWE-Bench is now 70%+. “It ships fixes, but we can’t review them fast enough or trust they’re stable.” Oct 2024: DORA 2024 finds AI hurt both throughput and stability. Now: Sep 2025: DORA 2025 finds is positive but stability stayed negative. Now: Jul 2025: METR’s RCT finds experienced devs 19% slower. Agents ...
On the Indigo 1026 from Singapore to Chennai, I saw a passenger two seats in front of me watch videos in an interesting way. She had wrapped her phone in a plastic cover, wedged it behind the tray table so that it would appear at a comfortable viewing position, and watched an Asian movie (presumably with bluetooth headphones). At first, I wondered if she travels with a plastic wrapper for this purpose. Then I realized it was from the Indigo safety instructions kit. ...
I asked Claude about my AI opinions. Based on my transcripts and blog posts, find the three claims I make most consistently, the three I’ve quietly reversed, and the one assumption I’ve never questioned but everything depends on. Here are things I’ve changed my opinion on: THEN: One frontier model will win - not specialization. NOW: Gemini for media, Claude for strategy/style, GPT for rigor. SLMs as tools. THEN: Carefully curate my course content. NOW: Give students prompts directly. THEN: Web apps are differentiated artifacts. NOW: HTML is easier to generate than PPT - a signal of slop, not craft. THEN: Human in the loop. NOW: Human NOT in the loop, bottlenecking it. On-the-loop, etc. is fine. THEN: Minimal single-agent loop, avoid sub-agents" NOW: Multi-agent, sub-agent, and agent teams. THEN: Avoid MCP, prefer SKILLS.md. NOW: Use MCP because integrating with Claude / ChatGPT / … is easy. There are the top contradictions in my opinions. ...