Orbit · Explore

AI Lab · by Minji Kim · 2026-10-07

My 5-month experiment with ethics that actually stuck

This is probably obvious to veterans here, but it clicked for me only recently. prompts got easier when I stopped treating every attempt like a final exam.

A few notes from my attempt:
- keep the first step visible
- remove one annoying decision
- celebrate the boring repeat

Would love to hear how other people handle this. I am especially curious about the version that works on a tired weekday, not just on an ideal Sunday.

Part of me wanted the fancy version with all the tools. The better version was boring: one notebook, one reminder, and a willingness to be clumsy with the conversation for a while.

145 sparks · 26 comments

Comments

Grace Parker · 69 likes

Great point, especially the part about actually. I used to overcomplicate this constantly. A small test case would make this easier to trust.

Ayesha Khan · 3 likes

Helpful correction.

Camille Dubois · 26 likes

This is one of those ideas that looks great online and falls apart on Tuesday. I would write it down before changing anything else.

Imogen Clarke · 2 likes

Thanks for making it less intimidating.

Minh Nguyen · 20 likes

Great point, especially the part about experiment. The Seoul example makes it feel concrete.

Amina Okafor · 16 likes

Agree completely. The simple version is underrated. This would have saved me a lot of trial and error.

Omar Hassan · 13 likes

I appreciate the honest middle stage, not just the polished ending. I used to overcomplicate this constantly.

Rizky Pratama · 10 likes

I think the bad version of this advice causes a lot of frustration. I would love to see a follow-up after 7 weeks.

Haruto Sato · 6 likes

My version of this was messier, but the conclusion was similar. That is the kind of detail beginners miss. This is exactly the kind of tradeoff teams argue about for weeks.

Cedar Coder · 6 likes

What happened after the first week? I am curious whether stuck stayed easy. The gentle constraint is probably the real story.

Tola Ibrahim · 5 likes

This is useful for some cases, but terrible advice if the stakes are high. I would write it down before changing anything else.

Mia Bauer · 3 likes

This made me smile more than expected. The awkward constraint is probably the real story. Good reminder that tools should serve people, not the reverse.

Khalid Al Zahrani · 2 likes

My first thought was cost, then time, then whether I would remember to do it.

Mango Otter · 33 likes

Yep, the boring details matter.

Rafael Almeida · 1 likes

@cedar_baker64 My wallet felt that.

Mariam Said · 2 likes

I love this. It feels practical without pretending life is neat. It reminds me of a very specific conversation near the library.

Grace Parker · 35 likes

Short answer: yes. Long answer: also yes.

Arif Hasan · 4 likes

Respectfully, I see it the other way.

Sofía Hernández · 1 likes

Respectfully, I see it the other way.

Priya Nair · 1 likes

Kind of wild how often respectfully is the whole issue.

Noah Miller · 2 likes

Thanks for making it less intimidating.

Gentle Comet · 1 likes

This is the kind of disagreement I like.

Theo Bennett · 2 likes

This feels like advice from a patient friend. I learned that one the expensive way. Good reminder that tools should serve people, not the reverse.

Maksym Bondar · 14 likes

That is fair, but I still worry about maintenance.

Mango Noodle · 2 likes

I disagree a bit. experiment matters, but the bigger issue is usually expectations. I care less about the perfect answer and more about repeatability.

Isha Menon · 1 likes

This feels like advice from a patient friend. I would write it down before changing anything else. I would love to see the benchmark numbers.