Recent content on S Anand
This week, I learned: psub is a neat fish option to treat command outputs like file inputs. E.g. diff (sort a.txt | psub) (sort b.txt | psub) More anchor points on how much text to ask AI for: … in 200-300 words (about 1 book page) … in ~1 A4 sheet (~500 words) … in ~3 minute of conversational Grade 8 reading (~500 words) I usually log things in a single file rather than split…
Sugar (or condensed milk) in tea I get often stays unmixed at the bottom. I forget to stir it. Is that poor design that should be fixed? Or is the steadily increasing sweetness of the tea a brilliant feature? Anyway, I therefore lick the bottom of the cup to get every last bit of sweetness. But this cup is so deep that my tongue can just about reach the bottom. And I can’t reach the bottom…
I ran, an experiment in Straive. I asked my colleagues to mail me any questions or tasks that they had. I’d use my agents + my knowledge as context and reply based on that. A few interesting things came out of it. First: It often does a better job than me - it has more patience and speed. For example: One colleague sent a detailed pitch. My agent spotted a tiny arithmetic averaging error.…
One of my goals this year is to learn to dance. I haven’t done much about it, but I did snatch one opportunity. At VizChitra , Ashok Kumar led an Afternoon Rhythm “where the drum sets a beat and you find your place within it.” He invited volunteers on stage. I usually volunteer for uncomfortable things (a habit from school days), so I briskly walked to the stage, waited for a few…
When I was at school, I assumed that teachers in the staff room would mostly be discussing students, teaching, how to improve things, etc. A few years after I graduated, I spent time with my teachers in the staff room, and realized that the conversations are far more mundane. The main topic of discussion (which went on for what felt like half-an-hour) was: Why was the tea at the high school staff…
Many people commented that they liked my comic illustrations and asked how I create them. Here is my process: Paste a reusable prompt fragment that’ll take any content, think about what to draw, then draw it. Paste a style variation for different comic styles (optional). Paste the content itself and run it. I use ChatGPT with gpt-image-2 more often than Gemini with Nano banana 2 . Here are…
This week, I learned: Kamakoti: “Entry (to the course) is relatively easy but the exit is extremely hard”. Generalizing, quality is determined by the exit criteria; loosening entry criteria is just openness / diversity. The Hindu “Once I have a persistent system that I pay to keep thinking, learning, and acting 24/7, I think that will decisively look like AGI.” - Dan…
I’m a fan of the Code Mode approach - i.e. letting agents run code rather than narrow functions. Many people agree: CircleCI , Perplexity , etc. In fact, mcp2cli gives MCPs a CLI interface. I feel the main reason is UNIX composability. I can run CLI commands in a loop, pipe them, etc. I tested it out on ChatGPT. ChatGPT has an @Gmail Plugin . I build a Local MCP Server that exposes my CLIs,…
On 16 July, my auditor sent me a draft Indian tax return: a refund of Rs 3 lakhs. I gave ChatGPT my AIS, Form 26AS, bank statements, mutual fund statements, property papers, travel records, prior returns, and so on, told it not to look at the auditor’s draft, and asked it to calculate my tax independently. It calculated a refund of about Rs 2.8 lakhs, roughly Rs 20K lower. (Less money, but a…
This week, I learned: I continue to be amazed at how efficient video codecs are compared with animated image formats. When compressing 38 PNGs, the final WEBM was smaller than many of the individual PNGs! 2343k: magick -delay 50 -loop 0 file-*.png file.gif 398k: magick -delay 50 -loop 0 file-*.png file.avif (slow) 284k: magick -delay 50 -loop 0 file-*.png file.webp 82k: ffmpeg -framerate 2 -i…
It’s amazing to watch the cost of intelligence falling. In Nov 2023, we had college-junior level intelligence for $10 per million tokens, i.e. it would take them $10 to read and process something as large as all seven Harry Potter books. By Apr 2025, Gemma 2 could do that at 2 cents. 500 times cheaper in a year and a half. In Sep 2024, O1 brought in a college-grad level intelligence for $15…
As agents get smarter, and when we ask questions outside our expertise, it’s pretty hard to understand what they’re saying. Andrew Carr uses “only report to me in ASD-STE100 Simplified Technical English” to simplify their writing. Ben Sehl suggested making this a permanent instruction. But, does simplifying the writing worsen their thinking? I tested six tasks on ChatGPT…
Agents are increasingly the consumers of things that used to be made for humans: Docs are increasingly for agents to read . E.g. llms.txt Code is increasingly for agents to edit . E.g. AGENTS.md Tests are increasingly for agents to satisfy . E.g. SWE-bench , GitHub repository Software is increasingly for agents to operate . E.g. --json , --schema , --dry-run , CLI-Anything , AXI Websites are…
I track the cost vs capability of LLMs at LLM Pricing - the rough cost to read all Harry Potters (~1M tokens) vs the intelligence level on the LMSYS Leaderboard - over time. Here’s what the models’ strategy evolution looks like. Claude started at the mid-to-high end of the cost-capability frontier. Over time, they decided to specialize in the high-end, which they’re doing well…
Bring AI to where people already work: email Lots of companies are putting AI into their chat applications. Add Claude to a Slack channel , tell “@Claude” to do something, and it reads the conversation, uses tools, does what you tell it to, and replies in the same chat. Nice, for companies that use Slack a lot . (Many do. We don’t.) Straive and many of our clients use email more.…
This week, I learned: Thinking traces vanished in ChatGPT Work (or did they never exist) and seem to be vanishing in Claude . Not sure if it’s because Chinese models are using the thinking traces as signals. ChatGPT Skills is available in the Plus plan. This was available to Enterprise and Edu, but since I saw this on ChatGPT just today, I guess it’s a recent feature. Peter Gostev…
This week, I learned: Writing is slightly, but only slightly, better than typing (for adult learning.) One factor is that typing is faster, so many people take notes verbatim, summarizing and thinking less. ChatGPT + Claude Graphology for personality is pseudoscience. ChatGPT + Claude When I decide to spend time, or someone says “Let’s do X”, it’s worth checking: is this…
One of my goals this year is to publish 2 books . One got published. Sort of. Data Science for Sustainable Development Goals: India Case Studies is an open-access anthology and I’m the designated author of Chapter 10: Using Data Analytics to Improve Students’ Performance is about how Gramener worked with NCERT to analyze the National Achievement Survey data, discovering stuff like TV…
At The Curzon Hotel , my key card didn’t work. But every time I went to the reception, they’d send a bellboy who would use the same key card, jiggle it a bit, pull it in and out a few times, and the door would open. Every night. For five nights. I just couldn’t get the knack of it. I’ve been at the other end of this. People often reach out to me saying, “Anand, this…
In 2007, I extracted the first arc of the Tracer Bullet strips . I didn’t realize I never shared the second arc. So, 19 years later, here it is. It remains my all-time favourite series from Calvin and Hobbes . This is funny at so many levels, but the wordplay is what sticks with me. “I keep two magnum’s in my desk. One’s a gun, and I keep it loaded. The other’s a…