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.

The introduction of the infinite optimization machine won’t create new supply of scarce assets (physical resources, attention, etc.) but will substantially/infinitely create new demand for them.

Can complex multi-step reasoning emerge purely from cells that only talk to immediate neighbors? Happy to share our paper “Reasoning with Neural Cellular Automata (NCA)”, from our team at Google, Paradigms of Intelligence 🧵👇

also some individuals will pay per token once their limits are hit which also helps the overall system work the irony of these people skirting this is they're always claiming some god tier level of productivity but they still can't afford to pay API prices so what exactly are they doing? is it a good allocation of resources?

This is the first blog I've written in 8 months. I'm back. Intelligence is free. Good luck. evis.dev/posts/cheap_intelli… ( I have a bunch more that I've been working on that I'll publish over the coming weeks ranging from deeply technical to macro.) Check it out!

OPENAI OFFICIALLY RELEASED THE PRO $500/M PLAN WITH 25X USAGE OF PLUS We are now effectively paying 2.5x more dollars to only get 1.25x more usage $500/m is now 25x usage $200/m is now 10x usage (was 20x) $100/m is now 5x usage That extra 5x usage from 20x to 25x is now effectively $300 a month

My conversation with Noah Shinn (@noahrshinn), founder of Instinct. Noah is building a personal AI assistant. It's still invite only, has spent nothing on marketing, and is growing roughly 10% A DAY. This is his first long conversation about the company. We discuss: - Why Instinct doesn't have an app - Buying compute months ahead of exponential demand - How users learn to trust it with a credit card - Safety and security - Agents coordinating with other people's agents - Instinct's business model - Apps built on consumer inertia - and more Enjoy! Timestamps: 0:00 Intro 4:11 What people are using AI agents for 15:07 Rethinking travel, reservations, and the internet 22:43 Trust, privacy, and personal data 27:50 The business model behind Instinct 38:04 How existing businesses will adapt 47:55 Designing a personal assistant people love 53:15 Growth, compute, and competing with Big Tech 1:11:44 What’s next for Instinct and personal AI