Orbit · Explore

AI Lab · by An Pham · 2026-08-26

My 10-month experiment with prompts on a budget

I tried this in Cape Town with a friend and we both noticed the same thing: the social part mattered more than the perfect plan.

35 sparks · 9 comments

Comments

Imogen Clarke · 23 likes

Helpful and not preachy, which is rare. The low-effort version is probably the keeper.

Léa Bernard · 4 likes

Exactly; the hidden cost is energy.

Marco Conti · 0 likes

I was going to disagree, but your second sentence got me.

Ananya Rao · 3 likes

I appreciate the honest middle stage, not just the polished ending. I would love to see the benchmark numbers.

Midnight Atlas · 3 likes

This is the gentle version of my rant.

Maya Williams · 0 likes

I would pin this if I could.

Alma Nilsson · 1 likes

That last line is excellent. This would have saved me a lot of trial and error.

Faisal Al Saud · 0 likes

Anecdotally, this tracks with what I have seen. For me it came down to the setup. Naming things remains undefeated as the hardest problem.

Tomás Gómez · 0 likes

The kindness in this post is lovely. I care less about the perfect answer and more about repeatability. This is exactly the kind of tradeoff teams argue about for weeks.