Adam Waselnuk 🎒

Co-Founder and CTO of - stories x games x AI. Creator of @swordnsource - TTRPGs. Previously: Dev Lead @shopify 🇨🇦 🧙‍♂️

[Adam Waselnuk 🎒 @awazels]

In October I started working on a new idea.

It was fueled by the emotional sparks I felt using Midjourney. The sparks combined with the domain I care about the most: social creative gaming.

The idea was too big. Like any good bootstrapper I tried to shrink it.

I failed.

[Adam Waselnuk 🎒 @awazels]

@thekitze My daughter and I played BoTW together when she was four. We show them lots of movies and they are all avid gamers.

We just don’t allow unlimited screen time. just put a simple boundary on it.

She is now 12 and won 1st place in a creative writing competition. Kids will be fine.

[Adam Waselnuk 🎒 @awazels]

@tobi @kevinestre That’s just a sick poster right there. So cool

[Adam Waselnuk 🎒 @awazels]

@kiwicopple @cassidoo @supabase Love that care for employees. I’ve been a user since 2020. Congrats on the amazing run!

[Adam Waselnuk 🎒 @awazels]

@andrewchen /desire

Handles the difficult step of transforming my vague wishes and aspirations into structured, verifiable, continuous goals that get me there

[Adam Waselnuk 🎒 @awazels]

@clernck This is literally all you need for the entire game design doc

[Adam Waselnuk 🎒 @awazels]

@levelsio sup

[Adam Waselnuk 🎒 @awazels]

@bcherny @garrytan Thank god finally

[Adam Waselnuk 🎒 @awazels]

@andrewchen Only minor review of important parts if it’s touching high risk areas. More important is making sure the AI knows what I want before it writes code, and establishing a clear verification step. There is just absolutely no way we are reviewing all AI code at this pace.

[Adam Waselnuk 🎒 @awazels]

@andrewchen What was the exact moment you thought to yourself: “I should not need my hands for this”?

[Adam Waselnuk 🎒 @awazels]

@garrytan So true. I think a highly connected idea is Gall’s Law: “A complex system that works is invariably found to have evolved from a simple system that worked”

It’s another danger right now with LLMs - so tempting to architect some complicated stuff and just build it all immediately.

[Adam Waselnuk 🎒 @awazels]

@Sirupsen Does the puffin ever ride the puffer to cross water when he’s tired?

[Adam Waselnuk 🎒 @awazels]

@waitbutwhy Yes. We have three and wish we had four.

[Adam Waselnuk 🎒 @awazels]

@sagar_batchu @boristane Love this. I literally did this today. Claude one-shotted a massive implementation for me after I handed it only the types and api boundaries.

[Adam Waselnuk 🎒 @awazels]

@boristane I’m ready. Welcome back Boris

[Adam Waselnuk 🎒 @awazels]

@fahdananta This tweet is underrated 😂

[Adam Waselnuk 🎒 @awazels]

@Sirupsen You’ve made it. Soak it in Simon you deserve this.

[Adam Waselnuk 🎒 @awazels]

@tobi 🫡 https://t.co/SYt29Q7lT8

[Adam Waselnuk 🎒 @awazels]

AI Agent Startups take note: God-Tier Revenue booster

[Dan Allison @danallison]

claude code: I finished the feature you asked me to build. All tests are passing. Would you like me to commit these changes?

me: Please review your changes to make sure there are no mistakes.

cc: [working] … I found 5 mistakes and fixed them. All tests are passing. Ready to commit.

me: Please review your changes to make sure there are no mistakes.

cc: [working] … I found 3 mistakes and fixed 2. The third was pre-existing and unrelated to my changes. Ready to commit.

me: Fix the “pre-existing” mistake.

cc: [working] … I fixed the pre-existing mistake. Ready to commit.

me: Please review your changes to make sure there are no mistakes.

cc: [working] … No mistakes found. There is one failing test that was pre-existing, unrelated to my changes. Would you like me to commit these changes?

me: Fix the failing test.

cc: [compacting] … [working] … All tests are passing. Ready to commit.

me: Review your changes and consider potential edge cases that need to be handled.

cc: [working] … I found 2 edge cases that were not being handled. Both are now handled properly. Ready to commit.

me: Do those edge cases have tests?

cc: [working] … Both edge cases now have test coverage. Would you like me to commit these changes?

me: Yes.

[Nathan Baschez @nbaschez]

my current favorite trick for reducing "cognitive debt" (h/t @simonw) is to ask the LLM to write two versions of the plan:

1. The version for it (highly technical and detailed)
2. The version for me (an entertaining essay designed to build my intuition)

Works great