i built an anti-slop software factory for ~50 contributors (and all their agents), from engineering to marketing, and i am sharing everything i learned
there is a lot of discourse around software factories, and though they sound amazing in theory, in practice, it can get exponentially sloppy if you are not careful. to keep the slop out, a lot of "good practices" we learned about software development get turned on their head.
in this video:
> why i banned useState and useEffect
> why code duplication is ok
> why skills aren't enough
> how to stop slop from compounding
btw this is not sponsored, i mention a few tools we use: @trpcio (e2e typesaftey), @vercel (app router), @aidenybai (react doctor), @meticulousgabe (frontend tests), @mcpjams (MCP tests), @cursor_ai (bugbot), @useblacksmith (fast CI), @composio (agent triggers & tools)
Important note regarding Grok @Bot:
Going forward, @SpaceX will use the best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno and other leading APIs.
Whatever is most likely to give you the best outcome.
1. Oh shit, AI can do my job better than me
2. Software engineering is dead!
3. I can vibe code as much slop as I want!
4. Oh, things are not going well. Fable/Sol/Opus all suuuck
5. But what if I constrain the agent? Put it in a straitjacket?
6. Oh, the results are pretty good now. How do I go deeper?
7. *Orders 12 software engineering books from Amazon*
8. Software engineering is alive!
I've met YC founders who told me they'll give up if they can't raise from Sequoia or a16z.
They're ex-Big Tech/Quant Firms, and did YC to build clout and move up the SF social ladder.
If they can't raise from Tier 1s, there's no point in downgrading their status to a Tier 2 VC.
It's more rational to give up, return to their $400k jobs and try again in a few years.
Someone just DM'd me saying they:
- Took my courses
- Became the "AI person" at work
- Got asked to run internal trainings
- Feel guilty (like they're taking work away from me)
Don't feel guilty! This is my DREAM end state for my students.
Knowledge is still valuable. Becoming the AI guy/gal at your company can totally change your career.
If you're in this position too, let me know how I can help you run your trainings - materials/advice etc.
the right way to use model capabilities is not to ship 10x more features to prod
it's to spend more time understanding your users, trying experiments, building prototypes, learning about things you don't understand so that you can ship things that actually work
We're adding support for AGENTS.md to Claude Code.
Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md.
You can toggle this behavior in /config.
The "whiteboard defense:" I should be able to pull you aside at any moment and ask you to explain any customer-facing system you've shipped. You should be able to clearly explain how it works and defend the decisions you made. This is my benchmark for responsible AI usage.
I don't expect line-level familiarity with the code. I don't care if you remember the exact function name or implementation detail. You may not even know it. I don't care.
But if I ask "why did you do X instead of Y?", "what happens if this actor behaves maliciously?", "what data structure did you use here and why?", or "where does this fail?" you should be able to answer confidently.
For PoCs, demos, experiments, whatever: I don't care. Generate 100% of it and understand none of it. Speed over quality every time in those specific scenarios.
But if you're shipping customer-facing work, you can't be shipping things you don't understand at a high level.
Imagine you close a $20k deal on Pipedrive or Hubspot, an invoice is automatically created, the invoice is sent to NRS, the invoice is then sent your customer, follow ups are done automatically without you, money is collected, settled, reconciled and synced to your accounting software
You, you clicked once "Closed Won"! Magic? No, @BujetiHQ? Yes
There’s a poem called The Narcissist’s Prayer that speaks to the lack of ownership and accountability often associated with narcissistic behavior. It explains why building anything meaningful and sustainable over the long term is extremely difficult for a narcissist.
That didn’t happen.
And if it did, it wasn’t that bad.
And if it was, that’s not a big deal.
And if it is, that’s not my fault.
And if it was, I didn’t mean it.
And if I did, you deserved it.
"10,000 concurrent agents worked on the Navier–Stokes effort, reaching the result in about 88 hours."
Imagine spinning up 880,000 hours of work against a problem with a few days notice.