How I do things

After ChatGPT's discussion of my personality flaws, I asked it to listing specific conversations as evidence for flaws. Then I asked 3 LLMs to rate the evidence. Personality FlawChatGPTDeepSeekGrokAverageSelf-deprecation as a shield. Sarcastic humor4755.3Hypocrisy: Seeks limelight but preaches humility5655.3Overconfidence in technical opinions5665.7Ghosts vague messages4686.0Over-analyzes / over-engineers5586.0Fact-checks trivialities, derailing discussion7777.0Shiny object syndrome. Distracted by new technologies8777.3Intolerant of fools6897.7Dominates discussions6897.7Verbosity. Long-winded communication8877.7Hyperfocus on efficiency7988.0Intense. “Always on”8998.7 🟢 LOW: Self-deprecation / sarcastic humour as shield ChatGPT: 4/10. Bio and a few quips reveal dry self-mockery, yet direct chat evidence of humour as defence is sparse; it surfaces only occasionally. | DeepSeek: 7/10. Explicit self-awareness goals and dry humor noted, but little evidence of defensive/sarcastic use. Grok: 5/10. Some self-deprecating humor exists, but its use as a shield is not strongly supported. 🟢 LOW: Hypocrisy: seeks limelight yet preaches humility ChatGPT: 6/10. You aspire to humility but routinely headline conferences and TEDx talks; the coexistence of public speaking and stated modesty gives the charge a middling footing. | DeepSeek: 6/10. TEDx/PyCon prominence contrasts with stated humility goals, though self-improvement efforts are genuine. Grok: 5/10. Public speaking contrasts with humility goals, though this may indicate self-awareness, not hypocrisy. 🟢 LOW: Over-confidence in technical opinions ChatGPT: 7/10. You assert strong views (e.g., Node vs FastAPI) but also invite verification and accept corrections, yielding only moderate evidence of over-confidence. | DeepSeek: 6/10. States strong preferences upfront but routinely invites validation and course-corrects. Grok: 6/10. Strong opinions are expressed, but openness to correction moderates the perception of overconfidence. 🟢 LOW: Ghosts vague messages ChatGPT: 5/10. You’ve stated you ignore low-context e-mails, but chat logs show you usually follow-up or clarify rather than disappear. | DeepSeek: 6/10. Documented tendency to ignore low-context questions, though chat logs show active clarification habits. Grok: 8/10. Multiple instances show the user ignoring or not responding to unclear or low-context messages. 🟢 LOW: Over-analyzes / over-engineers ChatGPT: 5/10. Designing auto-re-flow SVG chevrons and exhaustive RAG specs hint at depth beyond the simple solution, yet you also champion “smallest libraries” and lightweight rate-limiters. | DeepSeek: 5/10. Some prototype/structuring tendencies, but strong preference for minimal solutions counterbalances this. Grok: 8/10. The user often dives deeply into tasks, sometimes creating complex solutions for simple problems. 🟡 MEDIUM: Fact-checks trivialities, derailing discussion ChatGPT: 8/10. Many requests revolve around “double-check,” “fact-check,” or recalculating tiny details, which lengthens threads even when stakes are small. | DeepSeek: 7/10. Frequent accuracy demands and citation hunts elongate discussions, but stays focused when content is solid. Grok: 7/10. Evidence of prioritizing precision, like fact-checking minor details, can disrupt conversation flow. 🟡 MEDIUM: Shiny-object syndrome ChatGPT: 6/10. Parallel explorations of Godot, Matrix, Cloudflare Workers, SVG SmartArt, esp32-eye, etc. reveal a persistent pull toward new tech before finishing earlier threads. | DeepSeek: 7/10. Broad simultaneous explorations (Godot/WASM/DuckDB), though sustains core projects long-term. Grok: 7/10. Exploration of new technologies is frequent, but focus on core projects suggests a balanced curiosity. 🟡 MEDIUM: Intolerant of fools / low clarity ChatGPT: 7/10. Frequent demands for precise formats, citations, and “be specific” instructions show a low tolerance for ambiguity, though you still help patiently on non-technical questions. | DeepSeek: 8/10. Strong pattern of rejecting ambiguity/fluff, though softened by humor and non-technical engagements. Grok: 9/10. The user consistently demands clarity and efficiency, showing little patience for ambiguity or fluff. 🟡 MEDIUM: Dominates discussions ChatGPT: 4/10. Long, multi-part prompts and the need for TL;DRs suggest you can overshadow lighter voices, but you periodically insist on brevity and delegate tasks, tempering the effect. | DeepSeek: 8/10. Long technical messages (avg ~3k chars) and intense Q&A patterns create conversational dominance. Grok: 9/10. Detailed, technical responses consistently steer and dominate conversations. 🟡 MEDIUM: Verbosity / long-winded communication ChatGPT: 5/10. Average messages run several thousand characters, and you often request exhaustive, multi-section outputs—though you sometimes tell the assistant “Shorter please,” verbosity remains a clear pattern. | DeepSeek: 8/10. Multi-step technical requests dominate interactions, though periodic “shorter please” self-corrections exist. Grok: 7/10. Messages are often lengthy and detailed, though the user also requests concise responses from others. 🔴 HIGH: Hyper-focus on efficiency ChatGPT: 8/10. Recurrent themes—cost monitoring, smallest-lib preference, GPU-utilization alerts—show you relentlessly optimise workflows and expect others to keep pace. | DeepSeek: 9/10. Unambiguous prioritization of concise formats, minimal libraries, and metric-driven optimization. Grok: 8/10. Repeated emphasis on concise, efficient communication and minimal tools is evident. 🔴 HIGH: Intense – “always on” ChatGPT: 8/10. Around-the-clock, multi-topic requests (weekend cron jobs, 2 a.m. prototypes) portray sustained high energy, with only a few calmer “travel nerves” moments as counter-weight. | DeepSeek: 9/10. High-volume technical queries across domains, 6am research routines, and rapid prototyping habits. Grok: 9/10. High energy and engagement are consistently shown through task initiation and scheduling. My actions: Learn from fools and focus on the big-picture. Specifically: ...

In 2025, I'm playing Goals Bingo. I want to complete one row or column of these goals. Here's my status from Jan - Mar 2025. 🟢 indicates I'm on track and likely to complete.🟡 indicates I'm behind but I may be able to hit it.🔴 indicates I'm behind and it's looking hard. DomainRepeatStretchNewPeople🟢 Better husband. Going OK🟢 Meet all first cousins. 8/14🟢 Interview 10 experts. 9/10🔴 Live with a stranger. Not plannedEducation🟡 50 books. 6/50🟡 Teach 5,000 students. ~1,500🔴 Run a course only with AI. Not startedTechnology🟡 20 data stories. 1/20🔴 LLM Foundry: 5K MaU. 2.2K MaU.🟡 Build a robot. No progress.🟢 Co-present with an AI. DoneHealth🟢 300 days of yoga. 91/91 days🟡 80 heart points/day. 70/80🔴 Bike 1,000 km 300 hrs. 22/300🟡 Vipassana. Not plannedWealth🟡 Buy low. No progress.🔴 Beat inflation 5%. Exploring.🟡 Donate $10K. Ideating.🔴 Fund a startup. Thinking. Repeat goals seem likely. It's easier to do something again than something bigger or new. ...

I published an eBook on Amazon. It takes an hour if you have the content ready. STEP 1 (10 min): Set up a Kindle Direct Publishing account with your address, bank details, and tax info. STEP 2 (15 min): Export my London 2000 blog archive and convert to Markdown. STEP 3 (10 min): Reformat the Markdown by writing a script in Cursor. Here’s the prompt: Write a Python script that reads *.md including the YAML frontmatter, adds the YAML title as H1, date (yyyy-mm-dd) like Sun, 01 Jan 2000 in a new para after the frontmatter and before the content. ...

Here’s my new workflow for creating slide decks: ChatGPT interviews me and creates Markdown slides. I use Marp to convert Markdown to slides. LLMs create supporting images. I deploy on GitHub Pages. … and here are 2 decks created this way. Visualizing LLM Hallucinations LLMs in Education Let’s look at how I built the second example, step by step. ChatGPT interviews me and creates Markdown slides While walking 75 minutes from home to IIT Madras to deliver this talk, I had ChatGPT interview me in standard voice mode. ...

Thejesh tagged me with these questions. Why did you start blogging in the first place? I started my website in 1997 on Geocities at https://www.geocities.com/root_node/, mostly talking about me. (A cousin once told me, “Anand’s site is like TN Seshan - talking only about himself.” 🙂) (As an aside, I didn’t know that searching for Geocities on Google renders the results in Comic Sans!) I wanted a place to share the interesting links I found. Robot Wisdom by John Barger and Scripting News by Dave Winer were great examples: collection of interesting links updated daily. ...

This is the third post in my “Nasty habits” series following Licking and Scraping. Nibbling is biting, but only with the incisors. Not the canines or molars. And it’s a delight. Nibbling is not uncommon. People tend to nibble on all kinds of stuff. Pens, erasers, straws, gums, clothes, buttons, spoons, rubber bands, paper, toothbrush, cups, bottles, cables, gadgets, books, chalk, coins. It’s a long list. But I don’t do those. I nibble only food and body parts. ...

At Straive, only a few people have direct access to ChatGPT and similar large language models. We use a portal, LLM Foundry to access LLMs. That makes it easier to prevent and track data leaks. The main page is a playground to explore models and prompts. Last month, I tracked which features were used the most. A. Attaching files was the top task. (The numbers show how many times each feature was clicked.) People usually use local files as context when working with LLMs. ...

I read 51 new books in 2024 (about the same as in 2023, 2022, 2021, and 2020.) But slightly differently. I only read Manga this year. Fullmetal Alchemist (Vol 12 - 27). What started off as a childishly illustrated children’s book evolved into a complex, gripping plot. Attack on Titan (Vol 1 - 34). I read it while I watched the TV Series (reading first, then watching). It started explosively and the pace never let up. I had to take breaks just to breathe and calm my nerves. The sheer imagination and subtlety is brilliant. It’s hard to decide which is better—the manga (book) or the anime (TV). The TV series translates the book faithfully in plot and in spirit. It helped that I read each chapter first, allowing me to imagine it, and then watch it, which told me what all I missed in the book. I absolutely would not have understood the manga without watching the anime. ...

Here’s the report card for my 2024 resolutions: Compound long-term goals, daily. PASS. I managed to work continuously build on 6 areas in 2024: Blogging about 50 posts on my blog and on LinkedIn Weekly notes of things I learned Teaching Tools in Data Science (repo) Reading only Manga Experimenting with LLM applications LLM Evangelization through LLM Foundry, Straive’s LLM portal. Hit 80 heart points, daily. FAIL. I stopped exercise in the second half and gained 7 kgs. Be a better husband. PASS. My wife confirmed that I was “definitely worse in 2023 than 2024.” My most memorable events in 2024 were: ...

One of my goals for 2024 is to “Compound long-term goals, daily.” Learning is one of those. Some people publish their learnings as weekly notes, like Simon Willison, Thejesh GN, Anil Radhakrishna, and Julia Evans. I follow their notes. I started doing the same, quietly, to see if I could sustain it. It’s been a year and it has sustained. I’m finally publishing them. My week notes are at til.s-anand.net. Here’s the source code. ...

Arun Tangirala and I webinared on “AI in Education” yesterday. This post isn’t about the webinar, which went on for an hour and was good fun. This post isn’t for my preparation for the webinar, which happened frantically 15 minutes before it started. This post is about how I created the annotated talk at https://github.com/sanand0/ai-in-education-webinar (inspired by Simon Willison’s annotated presentations process) – a post-processing step that took ~3 hours – and the tools I used for this. ...

Andrej Karpathy mentioned the term LLM psychologist first in Feb 2023. I’ve been thinking about this for a while, now. I’ve always been fascinated by psychologists in fiction. I grew up with Hari Seldon in Foundation, wanting to be a psycho-historian. (I spent several teenage years building my mind-reading abilities.) I wanted to be Susan Calvin, the only robopsychologist. ...

Simon Willison initiated this very interesting Twitter thread that asks, “What prompt can instantly tell us how good an LLM model is?” The Sally-Anne Test is a popular test that asks: Sally hides a marble in her basket and leaves the room. While she is away, Anne moves the marble from Sally’s basket to her own box. When Sally returns, where will she look for her marble?" ...

Until recently, I could code on flights. This year, I lost that ability. Again. It’s happened before. In each case, technology has solved the problem for me. Here’s the history. I need a laptop. Since 2001, I’ve never been without one on a flight. I need power. Since 2005, I use dark mode and every low power feature available. (I also became good at finding hidden power outlets.) ...

Every time I get annoyed at people, I remind myself to be more like ChatGPT. Specifically: Don't get annoyed. Be patient. Encourage them. Step back and show them the big picture. (Then I get annoyed at myself for getting annoyed.) Today, I analyzed how exactly ChatGPT is different from me. So, I took a pitch document I co-authored with ChatGPT. Section A: Authored by Anand WHAT DO WE NEED? ...

I read 52 books in 2023 (about the same as in 2022, 2021 and 2020.) Here’s what I read (best books first). Fiction The Kingkiller Chronicle. I picked it up before a flight to London in 2014. Read it through the flight. Read it late into the night at our AirBnB. Skipped my workshop prep. Read it during the workshop breaks. Read it on the flight back. And I re-read it every year or two. The language is beautiful and the story gripping. I feel miserable this series isn’t complete. The Name of the Wind by Patrick Rothfuss ⭐⭐⭐⭐⭐ The Wise Man’s Fear by Patrick Rothfuss ⭐⭐⭐⭐⭐ The Stormlight Archive. Another series I re-read regularly. Brandon Sanderson takes the scale of the story up a notch in every book. Rhythm of War by Brandon Sanderson ⭐⭐⭐⭐⭐ Words of Radiance by Brandon Sanderson ⭐⭐⭐⭐⭐ Andy Weir’s books. Since my daughter re-reads The Martian (laughing loudly), I picked up Project Hail Mary. It’s a brilliant depiction of alien physiology and communication, with a weird kind of humour I love. Project Hail Mary by Andy Weir ⭐⭐⭐⭐ The Egg by Andy Weir ⭐⭐⭐⭐ The Martian by Andy Weir ⭐⭐⭐⭐ Red Rising Saga. A pleasant discovery of a new series. Somewhat like The Hunger Games and Divergent. Red Rising by Pierce Brown ⭐⭐⭐⭐ Golden Son by Pierce Brown ⭐⭐⭐⭐ Morning Star by Pierce Brown ⭐⭐⭐⭐ Blake Crouch’s books. The two I read were both time-travel related and I love that genre. These do a great job of exploring some of the deeper implications of time-travel. Recursion by Blake Crouch ⭐⭐⭐⭐ Dark Matter by Blake Crouch ⭐⭐⭐ Ready Player One by Ernest Cline ⭐⭐⭐. It’s as good as the movie with slightly different scenes. The Reckoners by Brandon Sanderson. Another series I re-read. Steelheart by Brandon Sanderson ⭐⭐⭐⭐ Firefight by Brandon Sanderson ⭐⭐⭐ Calamity by Brandon Sanderson ⭐⭐⭐ The Year of Sanderson. Brandon Sanderson’s kickstarter raised $41m for 4 books this year (mostly Cosmere). The stories themselves were OK but the hints they drop about the Cosmere are invaluable. Yumi and the Nightmare Painter by Brandon Sanderson ⭐⭐⭐⭐ Tress of the Emerald Sea by Brandon Sanderson ⭐⭐⭐ The Sunlit Man by Brandon Sanderson ⭐⭐⭐ Fullmetal Alchemist by Hiromu Arakawa. After Death Note, it felt like a let-down when it started. A mundane story. Then it grew funny. Showed shades of a much deeper story. I’m mid-way through the series and I’m hooked. Fullmetal Alchemist, Vol. 1 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 2 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 3 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 4 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 5 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 6 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 7 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 8 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 9 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 10 by Hiromu Arakawa ⭐⭐⭐ Fullmetal Alchemist, Vol. 11 by Hiromu Arakawa ⭐⭐⭐ Mono no Aware e altre storie by Ken Liu ⭐⭐⭐. A nice short story Traitors Gate by Jeffrey Archer ⭐⭐⭐. A well-writter fast-paced average story. Mistborn: Secret History by Brandon Sanderson ⭐⭐⭐. Average story but with lots of “secrets” about the Cosmere. Asterix and the Griffin by Jean-Yves Ferri ⭐⭐. Some good jokes but not as good as the original series. Non-fiction ...

In 2023, I made 3 resolutions: Run 50 experiments. I managed 44 / 50. (Here are some). Learnings: I need to improve planning (9), scepticism (6), and lateral thinking (4). Make 1 change a month in my environment. I managed 8 / 12. The largest impact was from meeting new people, working out of new places, and using new gadgets. Calendar integrity, i.e. stick to my calendar. I succeeded over 95% of the time. My most memorable events in 2023 were: ...

From The Extended Mind I learnt that our environment shapes our thinking more than I’d expected. That we can arrange our environment to extend our thoughts. In 2023, each month I changed something in my environment to see: What does “changing my environment involve”? What can I change? Will I succeed? Does it affect my thoughts? Can I track this? Here are the results. ...

I speak with ChatGPT ~20 times a day. That’s more than I speak with most of my colleagues. ChatGPT is clearly my favorite team member. I conduct trainings, reviews and mentoring sessions with my colleagues. How to write code. How to write slides. How to communicate. That last bit is particularly important. With ChatGPT Custom Instructions, I can guide ChatGPT on how to work better with me. Currently, I have 10 custom instructions. They evolved over time and will continue to evolve. ...

In 2012, I started Gramener with half a dozen friends. This week, we were acquired by Straive, a part of Barings Private Equity Asia. How do you feel? I feel like the father of the bride. Gramener was registered on 26 Feb. A day before my daughter’s birthday. I’ve spent more time with Gramener than my daughter. That makes Gramener my elder child. Who’s moving into a new household. Along with me. (I feel like சகலகலா சம்மந்தி.) ...