Orbit · Explore

AI Lab · by Ananya Rao · 2026-10-09

A gentle rant about machinelearning and expectations after 31 tries

I had a disappointing first try, a surprisingly good second try, and then a third attempt that taught me humility. So, naturally, I now have opinions.

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 recipe for a while.

Context: I am not an expert, just someone trying to make AI Lab feel less intimidating. I wrote down what worked, what felt awkward, and what I would do differently next time.

> Tiny progress is still progress.

That line sounds cheesy, but it got me through the part where prompts stopped feeling new.

31 sparks · 10 comments

Comments

Mia Anderson · 6 likes

This is genuinely helpful, thanks for writing it out. I would love to see a follow-up after 8 weeks.

Léa Bernard · 3 likes

Helpful correction.

Rohan Mehta · 2 likes

This. Exactly this.

Valeria López · 2 likes

The vibe here is immaculate. The a coworking table detail changes the whole answer.

Tiny Noodle · 1 likes

What would you change if you started over? That is the kind of detail beginners miss.

Paolo Garcia · 0 likes

There is probably a middle ground here. It sounds small, but the recipe matters.

Noé Petit · 1 likes

This is the gentle version of my rant.

Jack Taylor · 1 likes

I would love a follow-up example.

Faisal Al Saud · 0 likes

Really good advice, and it feels doable. That is where the boring checklist helps.

Achieng Njeri · 0 likes

This is genuinely helpful, thanks for writing it out.