self-tracking on S Anand

Using browser history as memory

Wed, 18 Feb 2026 10:02:56 +0800

I have a bad memory. (I need to write about that. I k eep forgetting to.)

It’s worsening. Yesterday, I misplaced my debit card for the first time. Or maybe the second…? Which reminds me, I just forgot a call I have now! (Panic.)

(15 min later.) So, anyway, therefore, I log stuff meticulously. Like what I did each day, what I ate, what I weigh, what pained me, etc. But the best logging is automated. My phone logs where I am. My bank logs what I spend. My calendar logs who I meet.

The main gap now is when I’m at home, not spending money or meeting people. Just… browsing. And browser history is a great way to “remember” this.

I figure out what I did this weekend, I ran:

datasette ~/.config/microsoft-edge/Default/History --nolock

… and then this query:

SELECT
datetime(visit_time / 1000000 - 11644473600, 'unixepoch', 'localtime') AS visit_date,
  urls.title,
  urls.url
FROM visits
JOIN urls ON visits.url = urls.id
WHERE visit_date >= '2026-02-14 00:00:00'
  AND visit_date < '2026-02-16 00:00:00'
ORDER BY visit_time ASC;

I pasted the CSV output into Gemini along with this prompt:

Here is my browsing history this Sunday. Summarize what I did, grouping into logical groups like:

10:00 - 12:30: What I did in 1-2 sentences 12:30 - 13:00: Next activity …

Ask me questions for whatever’s unclear.

Here’s what it said {with my comments}:

10:00 – 12:00: VizChitra Planning & AI Research. You started with administrative tasks (AWS, Google AI Studio keys) before diving into VizChitra 2026 proposals. You researched AI attribution bias and data storytelling, then used Claude and Gemini to brainstorm ideas, eventually drafting your blog post: “Submitting an AI-Ded VizChitra Proposal.”
12:00 – 14:15: Blogging & Philosophy You continued refining your blog post and engaged in deep discussions with Claude about “developing taste and judgment in the AI age.” You also briefly checked LinkedIn {“anyone liked my post yet?”} and explored some Dutch legal terms (“Stijlrichtlijn”) {work-related}.
14:15 – 16:30: Academic Research & Entertainment. You read heavy research papers on the economic and aesthetic impacts of AI (Microsoft’s Future of Work, Peyman Shahidi) {to develop taste}. You then prototyped an “Ask AI” tool using Codex before switching gears {here’s the Ask AI tool} to watch the Telugu comedy movie Khatarnak on YouTube {Telugu films are best for vibe coding}.
16:30 – 17:45: Local Development & Coding You spent this block coding on localhost (port 8000), testing your “Ask AI” tool and a “JSON to CSV” converter. You also managed GitHub pull requests for your tools repository.
17:45 – 19:00: Deep Dive into Learning Theory. You went down a rabbit hole on pedagogy and mastery, reading about the “psychology of interest,” “tacit knowledge” (Commoncog), “cognitive apprenticeship,” and Austin Kleon’s “Scenius” {to develop taste}. You also looked up directions to the Isha Yoga Center in Singapore {my wife asked}.
19:00 – 20:30: Course Admin & Networking. You switched context to your Tools in Data Science (TDS) course, troubleshooting a “GA1 Question 9” submission issue for students. You checked LinkedIn profiles ({names redacted}) and watched a few more comedy clips (Baladoor, Julai) to relax.
20:30 – 22:00: TDS Live Session. You prepared for and joined a Google Meet (likely the TDS Live Session), reviewing papers on “automation bias” beforehand. Afterward, you managed the meeting recordings and looked into configuring custom commit messages for GitHub Copilot.
22:00 – 23:00: Cloudflare & Wrap-up. You ended the day deploying updates on Cloudflare Workers, handling more student emails regarding the GA1 deadline, and doing some light image editing on Squoosh.

This is a fantastic way to jog my memory about what I did - and is obviously spot on. The questions it asked were also insightful:

The search for “Stijlrichtlijn Verdict to Video” (Dutch guidelines) seemed distinct from your other work—was this for a specific project? ANS A specific work project.
Did you end up watching the full Khatarnak movie, or was it background noise while you prototyped? ANS Background noise while vibe0coding.
The very last search was for “cnc machine”—are you looking to buy one? ANS Prof Shantanu Chaudhury, a few days ago, likened vibe coding practices to “something like you’re creating a CNC machine for coding. You’re just giving the specification, programming it, and it’s generating the code.” Which felt very apt, but I haven’t used a CNC machine (or have I?) and asked Google what it was.

So there it is. Export your browser history and as an LLM to summarize your day. Great way to jog your memory - and waste an hour.

11 Mar 2026. This continues to be a useful memory hack. In the last 4 weeks, I’ve used this at least 4 times to find out what I was doing the previous day or previous few days.

My Goals Bingo as of Q2 2025

Tue, 01 Jul 2025 03:43:00 +0000

In 2025, I’m playing Goals Bingo. I want to complete one row or column of these goals. Here’s my status from Jan – Jun 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.

Domain	Repeat	Stretch	New
People	🟢 Better husband. Going OK	🟡 Meet all first cousins. 8/14 🟢 Interview 10 experts. 11/10	🟡 Live with a stranger. Tried homestay - doesn’t count
Education	🔴 50 books. 6/50	🟡 Teach 5,000 students. ~1,500	🟡 Run a course only with AI. Ran a workshop with AI
Technology	🟢 20 data stories. 10/20	🔴 LLM Foundry: 5K MaU. 2.2K MaU.	🟡 Build a robot. No progress. 🟢 Co-present with an AI. Done
Health	🟢 300 days of yoga. 183/183 days	🟡 80 heart points/day. Far from it 🔴 Bike ~~1,000 km~~ 300 hrs. Far from it	🟢 Vipassana. 2 Jul 2025
Wealth	🔴 Buy low. No progress.	🔴 Beat inflation 5%. Not started.	🟡 Donate $10K. Ideating. 🔴 Fund a startup. Not started.

At the moment, there’s no row or column that looks like a definite win.

Observations:

New goals goals seem likely. I like doing new things.
Stretch goals are least likely. I’n not so good at follow-up or scaling
People goals seem likely. Mild surprise.
Wealth seems least likely. No surprise. I haven’t started doing anything about it 🤷🏽‍♂️.

Thu, 05 Jun 2025 05:36:05 +0000

I lost 22 kg in 22 weeks.

How? Skipped lunch, no snacking. (That’s all.)

Why? Cholesterol.

When? Since 1 Jan 2025. I plan to continue.

How far? At 64 kg, I’m at 22 BMI. I’ll aim for 60 kg.

Is fasting 12 hours OK? Ankor Rai shared Dr. Mindy Pelz’s chart that fasting benefits truly kick in after 36 hours. Long way for me to go.

No exercise? Exercise is great for fitness & happiness. Not weight loss. Read John Walker’s The Hacker’s Diet.

No LLMs stuff this post? Of course! I vibe coded the data extraction, analysis and visualization with Claude Code for my VizChitra talk:

Data viz: https://sanand0.github.io/datastories/weight-2025-06/
Prompts: https://github.com/sanand0/datastories/tree/main/weight-2025-06

My Goals Bingo as of Q1 2025

Tue, 01 Apr 2025 03:33:07 +0000

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.

Domain	Repeat	Stretch	New
People	🟢 Better husband. Going OK	🟢 Meet all first cousins. 8/14 🟢 Interview 10 experts. 9/10	🔴 Live with a stranger. Not planned
Education	🟡 50 books. 6/50	🟡 Teach 5,000 students. ~1,500	🔴 Run a course only with AI. Not started
Technology	🟡 20 data stories. 1/20	🔴 LLM Foundry: 5K MaU. 2.2K MaU.	🟡 Build a robot. No progress. 🟢 Co-present with an AI. Done
Health	🟢 300 days of yoga. 91/91 days	🟡 80 heart points/day. 70/80 🔴 Bike ~~1,000 km~~ 300 hrs. 22/300	🟡 Vipassana. Not planned
Wealth	🟡 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.

Health goals seem likely. That's a surprise. Maybe I set low targets or under-estimated myself. (I thought I'd hit the technology goals first.)

Wealth seems least likely. Not surprising. I haven't started doing anything about it 🤷🏽‍♂️.

Zeigarnik effect vs my procrastination

Sat, 28 Jan 2023 15:52:55 +0000

I make commitments but don’t always deliver on time. In 2022, I ran an experiment to find out why I procrastinate.

In Jan-Feb 2022, I listed the top 2 things I wanted to get done each day and measured how often I completed them.

14 Jan. ❌ Summarise from three research reports
12 Jan. ❌ UIFactory experiment ✅ Decide if I am a (…)
11 Jan. ❌ UIFactory experiment ✅ Agree on publishing in (…)
10 Jan. ❌ Client video. ❌ UIFactory experiment
09 Jan. ❌ UIFactory experiment. ❌ Attrition email as a story
07 Jan. ❌ ZS visual
06 Jan. ❌ Release Gramex Guide. ✅ UWC application
05 Jan. ❌ Publish network cluster post. ❌ Release Gramex guide
04 Jan. ❌ Publish network cluster post. ✅ Release Gramex.
03 Jan. ✅ Publish election TDS video. ❌ Publish Network cluster post.
02 Jan. ❌ Publish election TDS video. ❌ Publish Network cluster post.
01 Jan. ❌ Publish Network cluster post. ✅ Finalize SG school.

I completed 23 / 57 things (40%). That’s one of my TOP priorities.

In Mar-Apr 2022, I started micro-journalling to find out why. Whenever I was working on something, I wrote down whenever I started, stopped, or skipped working, and why.

- Tue 01 Mar. ❌ Create React app with any one Vega chart where attributes control chart signals
  - 09:30am. Skipped. INTERRUPTED. Shobana. Cleaning bedroom
  - 09:50am. Skipped. SCHEDULED. Breakfast
  - 10:10am. Skipped. INTERRUPTED. Naveen. Call
  - 10:50am. Skipped. DISTRACTED. LinkedIn. 3b1b videos
  - 12:30pm. Skipped. SCHEDULED. Calls
  - 01:30pm. Skipped. SCHEDULED. Lunch
  - 02:00pm. Skipped. INTERRUPTED. Shobana. Cleaning, Dhyeya airtel card
  - 02:30pm. Skipped. PROCRASTINATED. Didn't feel like working
- Sat 05 Mar. ❌ Record Jio videos fully. Run productivity log alongside it.
  - 09:45am. Skipped. INTERRUPTED. Appa. Investment, music
  - 11:00am. Skipped. PROCRASTINATED. Only 2 hours to next call. Let's do it later. Plenty of time tomorrow.
  - 01:30pm. Skipped. PROCRASTINATED. Only 30 min to next call. Plenty of time tomorrow.
  - 03:45pm. Skipped. PROCRASTINATED. Half day wasted already. It’s OK to take one day off completely.
- Mon 07 Mar. ✅ Record Jio videos fully. Run productivity log alongside it.
  - 09:37am. Started. ZEIGARNIK. Was thinking about this since morning.
  - 10:00am. Stopped. INTERRUPTED. Naveen. Called
  - 10:25am. Started. ZEIGARNIK. Just continued with momentum.
  - 01:00pm. Stopped. SCHEDULED. Lunch
  - 01:30pm. Started. ZEIGARNIK. Just continued with momentum.
  - 03:15pm. Stopped. COMPLETED.

After 2 months, a few patterns emerged.

Why I skip working

Distraction (50%).
1. Interesting things (22%) were the biggest. Less important things (e.g. programming, browsing/research)
2. Movies (10%) pulled me away
3. Email (8%) was fairly common
4. Organizing things (6%) like my calendar, TODOs, financials, etc.
5. Social media, interestingly, was not on my list
Procrastination (25%). There were 3 kinds:
1. It’s hard, and I’m stuck
2. I don’t feel like doing it
3. I don’t have time – my next task begins sooner than I can finish
Schedule (14%). I’d scheduled something else for then (usually food)
Interrupted (12%). Usually by family or close colleagues

Why I start working

Zeigarnik effect (68%). I keep thinking about the problem. So even after a break, I just plunge right in
Mindfulness (19%). I got started just by the act of writing the journal
Distraction (9%). Sometimes, distractions work in my favor. A movie gets stuck, or someone pings about the topic, or my mind is processing the problem in the background
Completed (3%). I finished the previous task and the momentum just took me to the next

Why I stop working

Schedule (47%). I have another meeting/task planned at that time
Interruption (35%). This is mostly by colleagues (22%), family (8%), or hunger/thirst (6%)
Exhaustion (10%). I’m just too tired to go on
Distraction (8%). To do this, I need to do THAT first, and I get sucked into THAT

What I learned

The Zeigarnik effect helps me start. Once I start solving something the momentum carries forward. The next best is to write down why I’m not starting it (micro-journalling).
To avoid procrastination, I should eliminate distractions first. Specifically, use a new Virtual Desktop, block movies, and block email & notifications.
To avoid schedules interrupting me, I should batch meetings even more tightly, giving me longer or more flexible blocks to work on