Getting the most out of Claude Fable 5, Anthropic’s powerful new model, you need to maximize your ambition: It’s built for full task delegation—you leave it looping for hours or overnight and come back to a finished product. If you want to get the most out of it, you need to relearn what software engineering is and how to step away to let the model do its work. That’s why I invited @mikeyk, head of Anthropic Labs, on @every’s AI & I. Mike’s been using Mythos-class models for a few months now internally at Anthropic, and he’s learned a ton of new tricks to make its increased powers work for him. And, as a co-founder of Instagram, he can reflect on how software engineering has changed over the last 15 years and what it means going forward. We get into: - Why the right workflow for Fable 5 is overnight delegation, not back-and-forth iteration—Mike ends his workday by briefing the model, then wakes up to a completed task. When a remote service went down mid-task, Fable 5 wrote a workaround, documented it, and forged ahead - The gap between what’s in your head and what exists in the world is closing fast—given access to Fable 5 and a set of internal MCPs, an Anthropic recruiter described the experience as, "The first time in my life where I feel like the thing that's in my head and the thing that exists in the world are right next to each other. I can just do it." - Software engineering isn’t dead, but the role has been reinvented—the PM/eng split is blurring, and the better engineers Mike talks to are holding two feelings at once: loss for the craft and shock at what’s now possible - Verification is the new bottleneck—Mike gives Fable video captures of its own work so it can catch animation glitches that screenshots would miss This is a must-watch for anyone building software and trying to figure out their role now that the models can handle so much. Watch below! Timestamps Introduction: 00:00:03 How Fable completely reshaped Mike's workflow: 00:01:48 When to use Sonnet versus Fable: 00:04:48 What the media tracker Mike built over a weekend reveals about agent-native architecture: 00:10:06 The cost to build has collapsed: 00:15:00 Is software engineering over?: 00:19:03 How Anthropic's engineering teams work today: 00:21:48 The mechanics of verification: 00:38:39 Dynamic workflows: 00:47:24 What people should use the model to build: 00:44:39

langchain meetup in Argentina!

Claude Code hack night in BA! Join us for an evening of heads-down hacking and sharing our Claude Code setups. luma.com/m5ok5mgx

Claude Code is the new us-east-1.

imagine running claude code with opus 4.5 here

Coderabbit just flagged a critical error after refusing to believe OpenAI's model naming scheme could get this involved

in the age of ai, the differentiating factor of anything is soul

brillante

New LLM Native event, this time in @Mercadolibre - a leader in the building of LLM-powered experiences in the region. Sign up if you are building with LLMs!

new llm native event in BA, this time in Mercado Libre application is open for speakers, sign up if you have meaningful experiences scaling llm native products!

what ai products are you happy to pay for as a dev? these are mine: @cursor_ai for dev @coderabbitai for reviews @langchain LangSmith for tracing and evals any others?

n8n quietly build on langgraph langgraph's penetration is wild

this is my role model

I cannot forgive Descartes. In his whole philosophy he would like to dispense with God, but he could not help allowing Him a flick of the fingers to set the world in motion, after which he had no more use for God -Blaise Pascal Pascal Knows

great event joining the AI community in Miami! definitely drop by if you're around I'll be speaking remotely on the winning workflow for llm evals and presenting a nice internal tool we built to find interesting traces from your production data x.com/fpingham/status/194765…

Built an experimental fork of Deep Agents @langchain that lets you spin up deep agents, connect them to MCP servers (Claude-style), with pre-built tools and specialized subagents from a simple CLI. An MCP registry that allows you to: - Connect to remote MCP servers using the Claude format - Manage and dynamically connect with available tools as needed - mcp add --transport http deepwiki mcp.deepwiki.com/mcp Create and load specialized subagents that can be invoked to handle specific types of tasks: - Subagents are stored as human-readable Markdown files - Each subagent has its own expertise and tool access - Dynamically load subagents based on task requirements github.com/lgesuellip/deepag… This feels like the new standard. Curious. who else is building in this? @CopilotKit

my biggest ai engineering finding this month is that Cursor's auto model selector is actually quite good and this might save me $100 ide's for the masses are all about multi model and routing if you can 10x decrease the cost for big teams you win

its hard to explain what being Argentinean means but this gets very close

the N1