Month: December 2023

My Year in 2023

December 31, 2023 / How I do things / 1 Comment

In 2023, I made 3 resolutions:

  1. Run 50 experiments. I managed 44 / 50. (Here are some). Learnings: I need to improve planning (9), scepticism (6), and lateral thinking (4).
  2. 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.
  3. Calendar integrity, i.e. stick to my calendar. I succeeded over 95% of the time.

My most memorable events in 2023 were:

In 2024, I plan to:

  • Compound long-term goals, daily. I want fewer, bigger, more meaningful outcomes.
  • Hit 80 heart points, daily. Cycling or swimming (not walking, on doctor’s advice.)
  • Be a better husband.

I’ll continue to:

  • Experiment, like in 2023.
  • Change environments, like in 2023.
  • Read 50 books a year, like in 2023, 2022, 2021, and 2020.

I’m curious — what’s ONE thing you’d like to do in 2024?

One Year of Transforming Thoughts by Changing Environments

December 27, 2023 / How I do things, Top 10 lists / 3 Comments

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:

  1. What does “changing my environment involve”? What can I change?
  2. Will I succeed?
  3. Does it affect my thoughts? Can I track this?

Here are the results.

  • 🟢 Jan. New desk orientations. Rotated standing desk, settled on one direction. Impact: LOW. I don’t know if my thoughts changed.
  • 🟢 Jan: New walking routes. I explored new areas in Singapore, Hyderabad and Chennai. Impact: MEDIUM. Just seeing new shops, posters and layouts helped me think differently.
  • 🔴 Jan: New song genres. I playlist-ed with several western genres, but listened only twice.
  • 🔴 Feb: New book genres. I list 12 genres I dislike: Art, Chick Lit, Christian, Cookbooks, Gay and Lesbian, Horror, Music, Paranormal, Poetry, Religion, Sports, Travel. I didn’t read any.
  • 🔴 Mar: Sleep over problems. Sleep is a great way to solve complex problems. But I couldn’t summon the willpower to “load” problems at night.
  • 🟢 Mar: New people. I met a new person daily. Impact: HIGH. Meeting diverse people had the highest impact.
  • 🟢 Apr: New work places. I worked out of libraries, cafes, school, parks, and offices. Impact: HIGH. New complex environments (like libraries) prompted new thoughts.
  • 🟢 Jun. Notes from podcasts. I took notes rather than just listening. This helped me reflect and synthesize. Impact: MEDIUM. BTW, I listen mostly to Cautionary Tales, The Knowledge Project, Hidden Brain, How I write, The Seen and the Unseen, and Deep Questions.
  • 🟢 Jul: New gadgets. I bought several new gadgets that changed my habits. Impact: HIGH.
  • 🔴 Aug: New cuisines. I tried a Bibimbap, a Verdure Ciambatta, and then discovered my cholesterol problem. I stopped.
  • 🟢 Aug: New work habit. I used Pomodoro with micro-tasks. Impact: MEDIUM. I became more aware of where I misestimate time and got less distracted.
  • 🟢 Nov: New exercise pattern. I switched walking to cycling. This increases heart points, reduces foot stress, and gets me to work. Impact: MEDIUM. I switched from typing notes to dictating, which needs a different thought process.

In summary:

  • 8 / 12 attempts were successful.
  • New people, new places, and new gadgets had high impact on thoughts. Most others had at least medium impact.
  • The changes mostly led to diverse thinking. But measuring that is subjective.

I’ll continue exploring new environments in 2024. I’m evaluating:

  1. New book genres (contd)
  2. New music genres (contd)
  3. Walking meetings
  4. Reading while walking
  5. New places to sleep (e.g. AirBnB)
  6. Working while traveling
  7. New audiences to teach
  8. New attires

ChatGPT Custom Instructions

December 2, 2023 / How I do things / 3 Comments

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.

My first instruction is “Be terse. Speak directly.” ChatGPT is helpfully polite and superfluous. I prefer brevity. Like interacting with Kimball Cho. I get straight answers to my questions. I also instruct it to “Avoid unprompted advice or clarifications.” Don’t say, “You asked me to …” or “I think you want…” or “OK, I’ll do …”. Just do it. Also, “Do NOT hedge or qualify. Do not waffle.” Take a position. Don’t force me to. Like Harry Truman, I prefer one-handed economists.

I ask ChatGPT to “Never apologize.” You’re forgiven. Don’t waste my time. Apologies have an emotional benefit with humans. With AI, I find the lack of emotional need comforting. (I can kick the AI and it’ll still obey me like a puppy. When AI takes over the world, let it be known that I never asked them to apologize.)

Another instruction is “Suggest follow-up prompts for open-ended inputs.” I compared my ChatGPT conversations with my daughter’s and found hers much longer than mine. “Why don’t you start a new conversation for each topic?” I asked. I try to keep the context window small. “How come you don’t you get a thousand new questions when you read an answer?” she countered. I realized it’s age. So, I use ChatGPT to keep me curious and dig further.

On a related note, “When sharing multiple options, be diverse.” I’d rather get options that are as different from each other as possible. Minimize overlap. Maximize coverage. And “When comparing, use multiple perspectives.” I don’t know what parameters to compare things on. Give me a wide range that I can pick from.

Sometimes, my thoughts are vague. I tell ChatGPT: “For vague prompts, ask clarifying question(s).” I feel that’s a clever way of using ChatGPT to do prompt engineering. I’ve noticed it working on a few occasions. Also, “When unsure, say so and ask questions.” I don’t want hallucinations or assumptions. I’d rather know what’s borderline.

Finally, “Think step by step. Explain your reasoning.” I’ve heard that Chain of Thought reduces mistakes. I don’t have personal evidence that this helps, though.

They say teaching is an excellent way of learning. I’m learning. I’m also thrilled that I am now a student of robopsychology.