S Anand

I ran npx -y ccusage monthly --compact to get the following break-up of my AI coding agent costs. Month Codex Claude 2025-09 $37.47 $2.29 2025-10 $106.79 $9.13 2025-11 $100.35 $14.24 2025-12 $240.69 $24.88 2026-01 $100.89 $20.28 2026-02 $323.21 $29.46 2026-03 $1996.32 $134.87 2026-04 $401.36 $47.07 2026-05 $378.20 $45.13 This shows the ROI of my $20 subscriptions to each. I get ~$35 worth of API calls for my $20 Claude Pro subscription and ~$400 of API calls for my $20 ChatGPT Plus subscription (on top of my ChatGPT chats.) ...

My post “Add a Verify Button” has a problem. When Rohit requested hyperlocal news for every PIN code in Mumbai, we’d need a “verify” button on every Statoistics card - hundreds of PIN codes, every day. Verifying every output introduces new bottleneck: a person inspecting every unit. That’s 100% inspection - which you do when you don’t yet trust the process. Manufacturing solved this a century ago. At Western Electric’s Hawthorne Works (famous for the Hawthorne Effect), quality control meant inspecting finished products and pulling the defective ones. Walter Shewhart sent his boss a one-page memo; about a third of it was a control chart. ...

Rohit Saran looked at the Statoistics cards my AI agents are generating for The Times of India, and asked about a small button under each one. In the list of Statoistics that you had put, I saw there’s a button called ‘Verify.’ What was that meant to be or will do in future? That verify button explains the claim, mentions the sources, and shows how to check the claim. One card said “9 in 10 Indians want a family doctor and barely 1 in 35 has one”. The button breaks that down: ...

I’m doing one extra push-up every day. One of my 2026 goals is to build muscles. I haven’t done anything about it until May. This month, I figured I would do the absolute minimum, at least to get started, because I seem to have starting trouble more than anything else. I asked ChatGPT: I want to build muscles. What’s the most effective thing that I can do that would take no more than one minute that I can practice every day without any equipment and I can do this anywhere and will have the most impact on building muscles? Research, give me the top five options and recommend one for me. ...

I asked ChatGPT to play chess with Stockfish. Stockfish is a “strong open-source chess engine”. It has 8 levels of difficulty, which roughly maps to these FIDE levels: Stockfish FIDE Player Level & Description Level 1 ~1000 Beginner: Constantly blunders, hangs pieces deliberately. Level 2 ~1100 Advanced Beginner: Fewer obvious tactical mistakes, plays completely aimlessly. Level 3 ~1200 Early Intermediate: Punishes very basic errors but regularly drops pieces. Level 4 ~1350 Intermediate: Plays standard opening moves; requires solid, blunder-free play to beat. Level 5 ~1450 Advanced Intermediate: Rarely hangs single pieces; you need positional advantages. Level 6 ~1650 Strong Club Player: Highly tactical. Aggressively exploits your mistakes. Level 7 ~1950 Expert: Exceptionally strong. Requires precise positional mastery and deep calculation. Level 8 ~2400 Grandmaster: Invincible for most humans. Plays with ruthless perfection. Full Engine ~3600 Our of human reach completely, “like a smart ant trying to debate physics with a human.” In the first iteration, here were the results: ...

Imagine you’re an information anarchist. You undermine Wikipedia pages by nuking references. A genie has granted you a wish: you can nuke one entire domain. Just one. As a data-driven decision maker (who is also an information anarchist 🤷), which would you pick? A common choice is The Internet Archive. 2.9 million Wikipedia pages reference it. But, you’re sneakier than that. A page isn’t undermined just because some references are gone. It’s undermined when all the references are gone. ...

An OpenAI model solved the Erdos unit distance problem. Erdos roughly said, “The number of edges of the same distance between N points can’t compound faster than close to 0%.” The model found a method of placing points so that it compounds at about 1.4%. This visualization is a crude way of visualizing how that works.

What is the most frequently occurring sentence in Wikipedia? ANS: A 213-word paragraph about how minor planets are named, which appears in 418 Wikipedia articles, word-for-word! There are ~380,000 asteroids. Wikipedia has 418 pages for these - including one for each thousand-range of asteroids. Every single one of these pages includes the phrase: As minor planet discoveries are confirmed, they are given a permanent number by the IAU’s Minor Planet Center (MPC), and the discoverers can then submit names for them, following the IAU’s naming conventions. The list below concerns those minor planets in the specified number-range that have received names, and explains the meanings of those names. ...

Here’s another AI-generated post, with Anand editor notes. But I’ve also added my own version of the post below. I told my “find a free calendar slot” script to “Avoid weekends and holidays”. Wednesday vanished. Turns out it’s a Singapore holiday (Anand: It’s Eid al-Adha), — irrelevant for the people I was meeting in other zones. I’d debugged my own helpful rule. (Anand: What? What does “debugged my own helpful rule” even mean?) ...

Lori Silverstein shared a post from Quickplay that featured a comic explainer, mentioning that “this could be a very impactful way for us to start being more creative … and differentiate our value proposition.” True. Comic explainers convey both creativity and differentiation. I’ve used sketchnotes for the same effect, but comic explainers are easier to follow than sketchnotes. So I fed this image to ChatGPT and asked it to modify my Sketchnote prompt: ...