fkozlowski

That's pretty awesome! Really liking the livestream idea

So actually I've been testing this — it seems to be useful in limited cases. LLMs have gotten so good now that a properly defined spec is no worse than a spec + property based testing.

I still found it useful for

1. trusting a bit of code is correct

2. rule-dense bits of code (eg something like a date parser)

The real issue so far is that I'm having trouble finding tasks where an LLM can't correctly code up an exhaustively defined spec.

  Location: New York
  Remote: Yes
  Willing to relocate: Probably not
  Technologies: TypeScript, JavaScript, Angular, RxJS, React, Node.js, Python, SQL, Playwright
  Email: kozlowskifrederick at gmail.com
  Substack: https://substack.com/@friedkielbasa
  Resume: https://fk-resume.kozlowskifrederick.workers.dev/resume.pdf

I'm a full-stack engineer — most recently I was at Headspace on a growth flavored team. Before that, I spent ~4 years at Tessitura building an order-processing app in Angular/RxJS.

On the side I'm working on a Cosmos Institute-funded project applying fuzzing, mutation testing, and formal methods to AI-generated code, so a human can actually judge whether it's right.

Thanks!

It's a great way to rebuild a sense of agency for me. I find the weekend binge a good way to feel like I can effect changes in the world.

Thanks, I was thinking the same! This also has some good photos

https://www.telegraph.co.uk/world-news/2026/09/08/archaeolog...

Related — this isn't the only map the Romans made that has survived.

https://formaurbis.stanford.edu/

Nice! It's interesting to see quantitative ways of measuring slop. I'm curious what _would_ happen if you did plug these back into the LLM as a form of feedback. Goodharting may happen... or it could get the LLM to generate cleaner code potentially?

MASCA has a ring to it!

Agreed — I also always append to my agents.md — "If there are any technical choices available, please surface them to me so I can understand them and choose"

I find that it's difficult to thread the needle of navigating on my own with also not spending forever in traffic or in train delays. It's disheartening when I do know how to get somewhere, but I land in a +1 hour traffic jam because I chose to not look at GPS.

Maybe I need an app that just yells at you when you take a super-wrong turn, or if you're about to be in a massive amount traffic?

I wish Pestilence retired already!

I've always found it a bit surprising that we don't all celebrate smallpox elimination day. I think it'd be a great reminder of the victories that humanity has had against the four horsemen.

It is actually judged by a human at the end FYI.

"The top 5 submissions will be finalists, judged by hand."

As other commenters noted — Rome did almost fall apart and come back a few times. Peter Brown has a bit about how the crisis of the 3rd century was reversible because it was fundamentally about control of the empire, rather than disassembling it.

My headcanon is that while the elites of the empire found more value in controlling the reins of power rather than carving out their own fief — that's what prevented collapse.

Yeah, that's a good point. Even though Latin had diverged to the point that reading Cicero required explicit schooling — the post-476 Romans did consider themselves Roman and fully the descendants of the late Republican / early Imperial period.

I'm mostly arguing that people overindex on the political changes and don't see the ground level continuity. Map color changed != they're not Roman any more.

Regardless, I do enjoy asking "what made Rome Rome?" — I like the idea of the Byzantines being Roman in 1453 even though at that point it was tenuous.

Ah that makes sense

I'm honestly surprised that they even had the inclination to attempt creating a model. I guess it's bullish that a municipal IT department had the guts to try this?

Yeah, didn't expect this much traffic. Thanks for reading!