Rey Molina

experimenting with a lil personal project: an AI-native macOS dock with custom modes (writing, building, etc.) to help me stay focused my agent is able to customize mode behavior and add new modes, it uses jev to classify my activity + notifications in real time & act on them

First of Kind: The @rauchg interview Season 3 starts now. I sat down with Guillermo in San Francisco to talk about layout shift, random acts of AI, and a dragon painted in a single stroke. 00:00 Human Effort Is Still Underrated 00:44 Chief Executive, Chief Designer 02:33 Two Bets: Software and English 05:15 Gmail Was My Siren Call 11:06 Exposure Hours 14:49 Layout Shift / One Stroke Dragon 17:10 No Random Acts of AI 25:17 Can Agents Have Taste? 30:15 Software Factories and Manufacturing Agent Customers 34:59 Everything Is Communication 38:04 A New American Story 41:52 Lifemaxxing Guillermo Rauch is the founder and CEO of @vercel. Growing up in Argentina, he taught himself English in order to teach himself programming, then went on to create @nextjs and other foundational technology for the real-time web. In our conversation, Guillermo explains why he designed Vercel’s first command line before writing any code, why layout shift erodes trust, and why his company won’t commit any “random acts of AI.” G is not just a chief executive. He’s a chief designer. — Guillermo Rauch: One Stroke Dragon First of Kind, S3:E01 @firstofkind Hosted by @soleio and produced with @room3nyc Powered by our sponsors: @framer @noondesign @bot @tryramp @vercel @meetgranola @profound

“How did you keep the development of this secret for so long?” “I didnt. I simply told everyone and nobody believes us” Lmao

Makes sense

The new Roadster will actually do something like this

this is brutal

This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads. Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

Si tenéis que explicarle a un colega la diferencia entre Mythos 5 y Fable 5, este es vuestro tweet. Fable / Mythos

An AI agent can be thought of as a simple While-loop. It uses an LLM to select an action, executes that action, evaluates the result, and repeats the process until the task is complete. Let’s take a closer look at each of these components: Brain: The LLM is the core. It reads the situation, thinks, and decides what to do next. The big shift from chatbot to agent: the model isn't writing text anymore, it's making choices. Planning: Hard tasks need more than one step. Agents break them down using methods like Chain of Thought (think step by step), Tree of Thoughts (try options, pick the best), or Reflexion (learn from mistakes and retry). Planning turns a fuzzy goal into clear actions. Tools: An LLM without tools is a brain in a jar. Tools are functions the model can call, like web search, code execution, APIs, files, or browsers (often using the MCP standard). The model requests a tool, the system runs it, and the result comes back. Memory: Without memory, every turn starts from zero. Short-term memory is the context window. Long-term memory lives in vector stores, files, and knowledge bases. When the window fills up, agents summarize old turns and carry the summary forward. Loop: All four pieces work together in a cycle. The agent looks at the current state, decides what to do, uses a tool, sees the result, and repeats. It keeps going until it gives a final answer. Guardrails: Not strictly anatomy, but important. Sandboxing, human checks, token limits, output validation, and scope limits keep autonomy from turning into expensive chaos. The more autonomy you give, the more these matter. Over to you: when you build an agent, which of these five takes the most work to get right?

The non-English tax is real. Sutton's Bitter Lesson, translated across languages and normalized to OpenAI English token count: Hindi: OpenAI 1.37×, Anthropic 3.24× Arabic: OpenAI 1.31×, Anthropic 2.86× Chinese: OpenAI 1.15×, Anthropic 1.71× Claude’s tokenizer charges a much higher linguistic tax.

We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.