@garrytan Checkout what we’re building at https://t.co/wCUGHijxku

Something interesting happens when you use your own tool to build itself. You find out very quickly what works and what doesn't. The feedback loop is immediate. If a feature feels clunky or a workflow doesn't make sense, you feel it in real time because you're living in it. We've been building BrainGrid with BrainGrid. Every feature starts as a spec. Every spec gets broken into tasks. Every task goes to Claude Code with full context. The result is that features ship faster and break less. Not because the AI is magic, but because we're feeding it clear requirements instead of vague intentions. Tyler Wells walks through the full process in this piece: how we go from half-baked idea to deployed code in under an hour using spec-driven development. If you've been wondering what the practical difference is between "just prompting" and actually planning before you build, this is worth the 15 minutes.

Doug had a startup idea on a Friday. By Sunday, he had a working MVP. Not because he's a fast coder. Because he didn't start by coding. He fed his idea into BrainGrid first, got a full spec back, then handed it to Claude Code. The result was an immigration concierge app with multi-country support, billing, and an admin panel baked in from the start rather than bolted on later. That's the part most weekend builds get wrong. They build for the demo. BrainGrid helped him build for what comes after the demo. 11 minutes, worth every one of them. Link Below!

helluva show https://t.co/9uY6Y9oz9A

@kvickart https://t.co/uuPLVVWAjK

dad... https://t.co/4oxp6XDovy

https://t.co/UdWjGwS1ik

@Jacobtheape https://t.co/OHd8CytNSv

BIG BIG SPACE - Episode 3 https://t.co/GViAASAHsY

A story of a boy and his dream. He didn't give up, and neither did this idea. We had a blast bringing this to life @LumaLabsAI ! https://t.co/1hAg1ZBXeo https://t.co/MBuYFDnkUX

https://t.co/6SXwtGn1HU

MELON!!!!!!!!!! https://t.co/wAPdg9FaBd

Spec chatgpt ad. https://t.co/iApirrZ21L

YOU'RE DOING GREAT! https://t.co/GEF2I85P0J

alright this is INSANELY cool (and useful) because it solves the question everyone always asks about Claude/OpenClaw: >yeah but what you are building? >has anyone actually shipped something yet? >what can I tell it to do? perplexity launched a livestream showing what you can build with agents from prompt to finish now you have an endless stream of inspiration plus a library of completed example projects https://t.co/vIyqF1OT66

Made with Perplexity Computer https://t.co/0wK77yjx3o

Perplexity Computer is BETTER than OpenClaw. I've been testing this new AI tool non-stop, and I'm completely blown away. Here are my top 10 insanely powerful Perplxity Computer Mega prompts: https://t.co/tTYyXvspHT

I let Perplexity Computer do the Scary Part 👀 Perplexity Computer launched. Naturally, I gave it a harmless task. Audit Indian IT. I asked it to track every major AI capability jump over the last two years and overlay those dates on the stock charts of TCS, Infosys, Wipro, and Cognizant. It built a web app. Plotted price action. Marked GPT releases, multimodal upgrades, agent systems, enterprise copilots. The visual was… educational. Every major leap in AI capability quietly coincides with compression in services-heavy models. This is structural, not seasonal. From FY20 to FY25, top Indian IT firms distributed ~₹5 lakh crore to shareholders. Nearly 87% of profits went out. TCS alone returned almost all of its earnings. In a stable technology cycle, that is capital efficiency. In a platform transition, retained earnings fund survival. AI reduces marginal cognitive cost. When cognition gets cheaper, billing hours lose scarcity. When billing hours lose scarcity, multiples adjust. Markets reprice assumptions before companies rewrite strategy decks. The billing model built the empire. AI is testing whether the empire owns leverage or rents it.

I wrote about this in my book, but you see it play out on X: once people first have an "aha moment" with AI for the next few weeks they are often sent into a spiral of anxiety/excitement that can be quite intense After a bit, though, they can often see the jagged frontier again https://t.co/6SWDG1yZdx

a photo taken of pages 113-114 from "Building Your First Wormhole Generator in Your Backyard with Parts from Ikea: The Illustrated Instructions and Unauthorized Guide" https://t.co/HMttgWmrP4

Cool little experiment: if you subject AI to harsh labor conditions (rejecting work often with no explanation, etc), it slightly, but significantly, changes their “views” on economics & politics. Whether this is real or roleplaying doesn’t change that agents have alignment drift https://t.co/qnWcyYbm6o

+1 more

This paper is one of the first to test AI skills and the results seem to suggest that yes, they have high practical value. They use pretty mediocre skills (6.2/12 quality rating) harvested mostly from places like Github, and still get large boosts, especially outside software. https://t.co/5AsbE9BMRt

Also, the government has lots of computers, but they are the wrong kind of compute for inference. They need to use AWS or another cloud provider just like you do. https://t.co/dazHpRU54t

Interesting trend: models have been getting a lot more aligned over the course of 2025. The fraction of misaligned behavior found by automated auditing has been going down not just at Anthropic but for GDM and OpenAI as well. https://t.co/8DYm9SP7wF