🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

.Freddie Vargus said he can RL an X bot that only posts topical bangers but it only works on accounts that post occasional bangers. who wants to be in the control group? 🙋

this is vibe coding vs this plot

last minute morning run to get in shape for running around AI Engineer this week 🏃‍♀️

worried my vibe coder bubble is biasing this poll 🤔

Uzi is basically your command center for parallel AI coding agents, leveraging Git worktrees to keep them all working without tripping over each other Some are finding success running agents in parallel, but there’s no easy way to do it, let alone manage it at enterprise scale

when you were just talking with Nick Khami about Uzi IRL 👀

Got an extra AI Engineer ticket. If you want to go but don't have one, shoot me a DM!

.Deanna Emery god tier technical speaker at AI Engineer

it was a pleasure speaking at AI Engineer with Maitar Asher 🎗️ from tavily and Deanna Emery from Quotient AI 🫡

results are in: 3 to 1 we're living in the best simulation 👏👏👏

retrieval + search track = best vibes AI Engineer ft Maitar Asher 🎗️ Deanna Emery Jerry Liu tavily Quotient AI LlamaIndex 🦙

Today's edition (8-Jun) of my newsletter is ready. (Consider subscribing, I write it daily. Link in comments & bio and also you will get a 1300+ page Python book as soon as you subscribe). Prompting with AI scales, Verifying doesn't

Let's talk about this for a second: “𝘐 𝘳𝘶𝘯 𝘦𝘷𝘢𝘭𝘴 𝘣𝘦𝘧𝘰𝘳𝘦 𝘐 𝘴𝘩𝘪𝘱 𝘴𝘰 𝘐 𝘬𝘯𝘰𝘸 𝘱𝘦𝘳𝘧𝘰𝘳𝘮𝘢𝘯𝘤𝘦 𝘸𝘰𝘯’𝘵 𝘥𝘦𝘨𝘳𝘢𝘥𝘦” This is great but it's like saying “I wrote unit tests so I don’t need monitoring in prod”. Here’s my take on this whole thing:

“You want your model hitting milestones, not minefields.” Most AI eval talk is hand-wavy. This isn’t. Freddie Vargus (Quotient AI CTO) gets into the weeds: how to actually test tool use, avoid minefields, and build agents that don’t break. Check out the recording👇