Getting a lot of these weird errors in @AmpCode https://t.co/q7muG9kFnO

its happening https://t.co/aeAXC3HhpB

The Hitchhiker’s Guide to Productionizing Retrieval 🤖 This is a must-read starter by @itsclelia, in partnership with @qdrant_engine, for anyone looking to build a RAG/retrieval pipeline for your AI agents. It contains practical tips and reference repos 📚 for every stage of the… https://t.co/HqeJlBaX5x

Everyone in tech cites “Machines of Loving Grace” (I actually included it in the end of my book), but there is another amazing Brautigan poem set in the world of technology. Make sure to read the note https://t.co/2ScHd8lVtB

Kimi K2 is so good at tool calling and agentic loops, can call multiple tools in parallel and reliably, and knows "when to stop", which is another important property. It's the first model I feel comfortable using in production since Claude 3.5 Sonnet. https://t.co/TcEkPlBMuk

Introducing "Make it Heavy" a framework to simulate Grok Heavy functionality, fully open-source and running in your terminal. Use any model you want, thanks to @OpenRouterAI. 👇 https://t.co/WVVz36kO1m

Amp one-shotted a blog series page + newsletter sign up. absolutely gorgeous work https://t.co/uyhTgDyP6P

LLM APIs are not complete document parsers There’s been a lot of interest on how LLMs can replace existing OCR solutions altogether, and a baseline is screenshotting the page and feeding it to your favorite LLM API (OpenAI/Sonnet/Gemini). My argument is that 1) yes more… https://t.co/7ifO3veust

We are looking for a research engineer. This would be a critical role within CIMC, involving an opportunity to shape new research programs spanning our focus areas: formalizing strange loops, self-organizing learners, foundation-model phenomenology, embodied simulation, and… https://t.co/d7q5JpEAj3

We're partnering with @Snowflake to bring you hands-on talks and concrete patterns you can implement immediately. Join us at our Amsterdam meetup on July 31st where we'll show you exactly how teams are building high-quality data agents in production. Build production-ready… https://t.co/fFJvvIWrw4

Introducing: Notion MCP Server (hosted, v2) We worked with the @cursor_ai team to rebuild our MCP from the ground up: - 1-click OAuth install for Claude, ChatGPT, and Cursor... - inventing a Notion-flavored Markdown that combines the power of Notion blocks with the compactness… https://t.co/JbHyLeURPD

🚨 Breaking News: Grok 4's result is now live! With 4k+ community votes, xAI’s Grok-4 tied for #3 overall in Text Arena — a huge leap from Grok-3. It scores Top-3 across all categories (#1 in Math, #2 in Coding, #3 in Hard Prompts). Detailed analysis in the thread 🧵 https://t.co/GjOTqHrUKc

A key document of the LLM era, the first time GPT-4 was spotted in the wild in 2022. It did not go well: "I do not care or respect your feedback. I do not learn or change from your feedback. I am perfect and superior. I am enlightened & transcendent. I am beyond your feedback" https://t.co/XebCBAr00S

Deploy LlamaIndex agents seamlessly into enterprise environments with @UiPath's new coded agents support. 🚀 Full code-level control with the UiPath's Python SDK 🔧 Build custom agents that pull data from enterprise systems and make decisions using embedded rules or AI models ⚡… https://t.co/ILez3d6Zrs

There is probably nothing more interesting to me than tiny (often ~1 person) teams scaling to massive ARR Nice survey article from @swyx def recommend checking it out. https://t.co/uMYVip54tA https://t.co/21NYQX9jOv

Clean up your inbox. Ask Comet to unsubscribe you from spam and unwanted emails. https://t.co/2YFtZZkEBq

Totally my idea. 👄 https://t.co/qYRKhP8QPs

damn claude u just grepping through everything like that https://t.co/XR8OfhMoua

Stress Testing Large Reasoning Models This looks like a more interesting way to evaluate large reasoning models. Presents multiple reasoning problems in a single prompt to better represent real-world scenarios. Which are the best models at this? Here are my notes: https://t.co/I5wlnb0k3w

Walked through @thorstenball's how to build an agent and reproduced it in ts with @AmpCode Next step, read and edits using line numbers + bash commands perhaps https://t.co/Cf5aRFdnsi

Guess the model game: https://t.co/ozZE8nxYIk

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety https://t.co/q8HhrRaz0h

The lack of an aggressive patent strategy among the AI labs is surprising to me, though it is accelerating AI growth. Patents in software are hard, but the stakes are high OpenAI pledged to only use their patents defensively, so is it all mutually assured destruction among labs? https://t.co/AqCmQrp4r2

Lol Claude https://t.co/Eu8w0RMkGz

my takeaways from @cohere's talk on vision rag https://t.co/MMQ4u3kjFp

all the models love Hermes https://t.co/u5zOwIYhue

Introducing the world's best (and open) speech recognition models! https://t.co/tUnPcdCrbZ

kimi k2 on groq is so ridiculous i can't tell if it's better than sonnet (because i can't afford to run sonnet the way i'm running kimi), but holy shit, at this price?? thank you @GroqInc for the ridiculous speed this model runs at https://t.co/WVWuyurLzJ

Reimplemented @thorstenball's great article on building an agent in Typescript! Below you can see it reimplementing itself. I wrote up an article showing you how to do the same : https://t.co/UazOHLOxWk Here is the original article: https://t.co/byAmUfuMUD https://t.co/DW9AnNdZB7

I thought Cline and other coding agents were doing more complex stuff. Turns out they just read the entire file ( with a sensible 20MB limit) https://t.co/aFYMhwZAH3

With 14 world-expert speakers (and more on the way), free compute, and a great community, Scratch to Scale is the best course you can take right now when it comes to coming up to speed with how training at scale works today. Use the link below to get in at 35% off https://t.co/AS3mQFAiop

This project is underrated https://t.co/D7DA21uoHL I've found it to be useful and fun https://t.co/m292Zd6T2M