Orbit · Explore

AI Lab · by Nour Ali · 2026-09-19

My 8-month experiment with prompts

I started this because my quiet Sunday felt a little stuck, and machinelearning seemed like a manageable place to experiment. The funny part is that the smallest change was the one I kept.

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.

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

My current rule is simple: if it takes less than 7 minutes to prepare, I am much more likely to keep doing it.

30 sparks · 12 comments

Comments

Paolo Garcia · 28 likes

What would you change if you started over? The the train station detail changes the whole answer.

Gentle Lantern · 0 likes

Appreciate the nuance.

Solar Lantern · 2 likes

Anecdotally, this tracks with what I have seen.

Martina Fernández · 2 likes

Small caveat: context changes the answer a lot.

Leila Karimi · 2 likes

I would love a follow-up example.

Nour Ali · 1 likes

Helpful and not preachy, which is rare. This is more useful on a tired first week than on a perfect day.

Lucía García · 1 likes

Maybe, but the tradeoff seems bigger than the post suggests. Honestly, the simplest version wins for me.

Kabir Khan · 1 likes

Yep, the boring details matter.

Sanne de Vries · 1 likes

The kindness in this post is lovely. I used to overcomplicate this constantly.

Aisha Rahman · 1 likes

The kindness in this post is lovely. That is where the boring checklist helps.

Omar Hassan · 1 likes

This is genuinely helpful, thanks for writing it out. I would write it down before changing anything else.

Gentle Noodle · 0 likes

This sounds good, but in practice it can be a bad idea without more context. My only addition is to make the first step visible.