https://t.co/3YQhgVGYuR

— UwU-Underground (@uwu_underground) May 31, 2025

There are a lot of misconceptions about the Snowden revelations - here's a more nuanced view on what was revealed:https://t.co/lWFiHREk1h

— Electrospaces (@electrospaces) June 2, 2025

🔥 YC breaks down how top AI startups prompt LLMs: 6+ page prompts, XML tags, meta-prompts, evals as core IP.

Meta-prompting + role assignment are key for reliable, agent-like behaviors.

⚙️ Key Learning

→ Top AI startups use "manager-style" hyper-specific prompts—6+ pages… pic.twitter.com/4iRnNJq8gA

— Rohan Paul (@rohanpaul_ai) June 1, 2025