I’m excited to introduce RAGs - create a “ChatGPT over your data” purely with natural language 💬 Setup and use a full RAG pipeline over files/web urls in three simple steps: 1️⃣ RAG Builder: Describe your RAG pipeline in natural language (data, parameters like top-k, system

Here's my conversation with @jeffbezos, founder of Amazon and Blue Origin. This is his first time doing a long-form conversation of this kind, and it was an epic one. It's here on X in full & is up on YouTube, Spotify, and everywhere else. Timestamps: 0:00 - Introduction 0:24 -

I’m getting extremely frustrated with @replit today - Vue/Nuxt3 projects no longer work, Always On projects cannot be deployed with their new Deployments feature, and my costs have gone up. No response from their support team. It’s such a shame. Replit ⠕Support

💯

Multi-agent collaboration has emerged as a key AI agentic design pattern. Given a complex task like writing software, a multi-agent approach would break down the task into subtasks to be executed by different roles -- such as a software engineer, product manager, designer, QA

🥁 Llama3 is out 🥁 8B and 70B models available today. 8k context length. Trained with 15 trillion tokens on a custom-built 24k GPU cluster. Great performance on various benchmarks, with Llam3-8B doing better than Llama2-70B in some cases. More versions are coming over the next

LLaVA Llama-3 and Phi-3 now on MLX 🎉🚀 You can now run inference locally on your Mac. pip install -U mlx-vlm I’m getting ~50 tokens on a M3 Max. Model cards 👇🏾

GPT-4o is now available on Generation API - the best and fastest way to build AI-powered APIs

🎥 Just uploaded a video of me trying to accomplish a task in the @GoogleCloud console (less than a minute, starting from the Google Search page). Then I asked Gemini 1.5 Flash to write a friction log for the experience. It took ~6 seconds to analyze the full video, and to

Self-care life hack: if you feel a bit down/tired, paste the url of your website/linkedin/bio in Google's NotebookLM to get 8 min of realistically sounding deep congratulations for your life and achievements from a duo of podcast experts 😂

I talked to the CEO of a moderately big tech co who said they'd replaced Figma with Replit. This surprised me because I don't even think of them as being in the same business. But he said Replit is so good at generating apps that they just to straight to prototype now.

DeepSeek has been a very important breakthrough for understanding the future of economics in software in a world of AI. There’s been an open question for a couple of years now - especially from public market investors - around whether more value goes into the AI models or into

It's 2025 and most content is still written for humans instead of LLMs. 99.9% of attention is about to be LLM attention, not human attention. E.g. 99% of libraries still have docs that basically render to some pretty .html static pages assuming a human will click through them.

1990s - coding is 90% doing cool new shit, 10% learning environment 2000-2024- coding is 90% framework bullshit, 10% doing cool new shit Today - coding is 70% doing cool new shit, 30% arguing with the model.

The real race in AI is the race to get right context to have AI Agents solve the user’s problem fully. Organizing or indexing the right data, understanding a domain deeply, getting enough activity for useful memory, and connecting to the right tools. This is the big prize.

"You should still learn to code" needs an asterisk. The SWE job is changing fast. By the time you're proficient, today's landscape will be history. But that's exactly why you should start learning now: coding is ground zero for human-AI collaboration. Through learning to code,

Some incredible changes are happening in the world and it’s just beginning. It’s not just informational categories where search from blue links is declining. Commercial categories too like Travel, Food/Drink, Fashion and E-commerce.

What’s wild is how many unexplored AI Agent products are just sitting inside AI models today. These models pack enough intelligence to support most workflows. They just need someone with domain expertise, the right prompt, data for context, and UX to unlock the use case.

Stripe's usage-based billing platform has grown 145% YTD. There's lots of discussion about when the industry will shift from seat-based pricing to consumption models, but it's clear in our data that the transition is already happening. I'm curious what the second-order effects