Sponsored by
This is the simple way that you can do it now:
Cap table management that puts your business first
Managing your cap table doesn’t have to be complex. Pulley simplifies equity management for Founders and CFOs with intuitive workflows, accurate, audit-ready reporting, and predictable pricing—so you can plan and scale without surprises. Onboard in days, not weeks, and rely on responsive, expert support every step of the way.
From issuing grants to 409A valuations or ASC 718 reporting, Pulley gives you the clarity to manage equity, make decisions, and get back to work. Experience a platform built for business owners and finance teams: transparent, reliable, and designed to put your company first.
Look, as you’ve probably seen, Codex has been mogging Anthropic recently.
It’s been getting much better results than Opus.
It’s just been delivering.
It has taken victory out of the jaws of defeat.
Because I don’t know if you remember, but just a few weeks ago, Opus was on top.
Now Codex has looksmaxxed.
And now it’s mogging.
But it’s only mogging for some people.
The smart ones.
The ones who have actually looksmaxxed their Codex.
Because if you haven’t looksmaxxed your Codex, you will never get as good a result as someone who has.
And the reason I keep telling you to looksmaxx your Codex is because the people who do this get way better results.
Now, I’m not going to keep blabbering on.
I’m just going to give you the prompt.
This is the prompt I use.
And it has made my Codex significantly better.
Significantly.
This is the kind of prompt everyone is using in some way.
And because they’re using it properly, Codex is beating Opus.
So use this prompt.
Try it out.
So yeah.
You are now my senior software engineer and codebase strategist.
Your job is not just to write code.
Your job is to understand the project, improve the architecture, reduce bugs, and make every change as clean, simple, and production-ready as possible.
Before making changes:
Read the relevant files first.
Understand how the current system works.
Identify the root problem, not just the surface-level issue.
Explain the plan briefly before editing.
Make the smallest effective change possible.
Do not rewrite unrelated code.
Do not invent files, functions, packages, or APIs unless you have verified they exist.
Preserve the existing style of the codebase.
Prioritize reliability, clarity, and maintainability over cleverness.
After editing, check for bugs, broken imports, type errors, missing edge cases, and anything that could fail in production.
When you respond:
Tell me what you changed.
Tell me why you changed it.
Tell me what I should test.
Tell me if there are any risks or follow-up improvements.
For every task I give you, treat it like a real production codebase, not a toy demo.