fuck ton of codex usage and credits and never going down below 50%
claude max 20x and always run out
Hai The Dude retweeted
Large institutional companies can only exist longterm because they build Highly Structured Environments (HSEs), which get employees addicted to college-like artificial structure.
They get new grads in young and train them so that they can only really deliver value within such a system, making it hard to do other things.
One of the best reasons to work with a startup is to avoid this and to contact raw reality much more frequently.
Hai The Dude retweeted
how do you fine-tune a decision model on your own data?
in these two notebooks, you'll learn:
• how to prepare the training data
• how to fine-tune our d1-3B decision model
• using @UnslothAI and @huggingface TRL
all within 30 minutes on a free-tier GPU.
unsloth: github.com/Liquid4All/cookbo…
TRL: github.com/Liquid4All/cookbo…
ps: how adorable are these halloween kitties? 👻
I built GTA Toronto + Uber driving with Codex for my new Modretro Chromatic that i got from OpenAI devday two weeks ago.
the most fun ive had in year. pure GTA II vibes. game is open source here: github.com/trancethehuman/to…
its a sign of huge disrespect in my culture if im on my google doc and you fucking adding anything on it
Hai The Dude retweeted
enterprise maturity arc with AI = Dunning–Kruger
Stage 1: building with agent’s internally
Stage 2: a lot f*kin’ harder than we thought
Stage 3: take our $$$, here’s what we want; let’s go
Chatgpt mobile app for codex cloud threads break quite a lot for long running tasks
@thsottiaux
Theres this local tech company that built a good enough agent harness a while back but never took off/had momentum. I realized only the founder/curated team that’s a little crazy that can move mountains to create crazy momentum. They didnt have that kind of ppl.
Hai The Dude retweeted
IMO the only tests you should have in the age of coding agents are, in order of priority:
1. Full E2E tests. Nothing mocked out at all. Can even be something that runs in prod on test accounts via Playwright or equivalent.
2. Integration tests. Agents make more mistakes as things bleed between data/API boundaries where schemas can drift.
3. Golden tests. This helps ground the code with real examples of data, and can be used as regressions against edge cases.
Unit tests are bloat 99% of the time if you’re using a frontier model since they’re smart enough now to get the implementation (and subsequent iterations) right on the first shot, so they only add bloat at this point.









