A short, practical talk on three levels of reviewing agent-written code so you don't blindly trust what your agents report.

Nate Herk builds a multi-persona 'board of advisors' as a Claude skill and shares it free, a useful pattern to copy.

Sequoia sits down with David Silver and Lasse Espeholt of Ineffable Intelligence on their 'superlearner' thesis, a good look at how a frontier-research startup pitches…

Theo examines why AI costs aren't falling as expected and what that means for the economics of products built on LLMs.

Anthropic's own walkthrough of Claude Managed Agents, explaining the brain/hands split that underpins the platform. It is the best starting point for the four-part…

Stripe's payment data shows where AI businesses are actually making money. Useful for pricing and go-to-market decisions.

A hands-on build of a research agent on Claude Managed Agents, led by Anthropic. Useful for seeing the platform work end to end.

Anthropic walks through scheduled agents and the 'dreaming' feature in Claude Managed Agents, with Q&A on running long-lived agents in production.

Anthropic's closing session in the Managed Agents series covers evals, CI/CD and multi-tenancy, the unglamorous parts of shipping agents.

An a16z discussion of recursive self-improvement and what it could mean for how frontier labs and builders plan ahead.

Hrishi Olickel argues that cheap intelligence lets you build ontologies on demand instead of designing schemas up front, with concrete data-pipeline implications.

Railway's Mahmoud Abdelwahab makes the case against sloppy one-shot SaaS replacements and shows what production-quality AI-built apps need.

A security talk on how a co-tenant on a shared GPU can leak information about your model, which matters if you serve on shared hardware.

ElevenLabs shows a complete workflow for producing an ad with a generated jingle, from script to final audio.

OpenHands' Robert Brennan compares four ways to isolate coding agents and explains why sandboxing is mandatory. A practical talk from a team that ships agents.

Cerebras and Gimlet Labs discuss how inference infrastructure can keep up with rapidly growing token demand. Relevant to anyone serving models at scale.

An hour-long walkthrough of moving from writing code by hand to building automated software factories with coding agents.

A full-length tutorial on building AI research agents with Claude Code, with real code from start to finish.

Nate Herk tests more than 100 GitHub repos for Claude and shares the six most useful, which could save you a lot of searching.

Official Higgsfield walkthrough of driving video edits with Claude Opus 5.5 and the Katana tool, an agent-plus-video workflow.

LiveKit's Jesse Hall treats voice-agent latency as a budget and shows how to make conversations feel humanlike.

Fireworks AI lays out a train-to-deploy loop for specialized models, making the case for owning your model instead of renting frontier APIs.

A short, clear explainer on DeepSeek's latest approach to the long-context memory problem. Good for a quick view of the technique.

Ramp's Max Freeman explains how to build a sales machine, in a long interview with a practitioner who runs one.

A technical look at the efficiency tricks behind DeepSeek-V4.1 Flash and why they matter for serving cost and long-context performance.

The All-In crew on the model welfare debate, OpenAI's math backlash and the market backdrop, the weekly read on how top investors see the AI cycle.

An AI Engineer talk on taking GPU utilization from 15% to 90% by fixing the data pipeline instead of touching the model.

Snorkel walks through training a small-model finance agent for under $500, with concrete cost and results numbers.

Goodfire's Eric Bigelow explains how models decide, covering critical tokens, phase shifts and in-context learning, in a long interpretability deep dive.

A talk from Coder on the lethal trifecta (private data, untrusted input, external actions) in agents already running on developer laptops, with practical mitigations.

An inside look at how MiniMax M3 was built, covering its sparse attention design and native multimodality, from someone on the team.

Shows how a relational context engine can cut token burn compared with plain RAG, a direct cost and retrieval win for agent builders.

A builder talk on running serverless AI agents with zero cold starts on Akamai Functions, with concrete serving trade-offs.

Walks through taking custom agents from a laptop into a real pipeline with GitHub Copilot, aimed at teams that ship.

A full 43-minute freeCodeCamp course on architecting scalable AI automations in n8n from scratch, with real workflows rather than toy demos.

OpenAI's official look at the community growing around Codex, useful for finding workflows and people to learn from.

LangChain gives a practical checklist of questions every agent engineer should be able to answer about their system before it ships.

Reflection AI CEO Misha Laskin on Beam, the lab's new American open-weight frontier model, and why open models matter for builders and national competitiveness.

True Ventures partner Puneet Agarwal opens up the VC decision-making process on TechCrunch's Build Mode: what gets a yes, what kills a deal and how to run a round.

Anthropic's official getting-started walkthrough for Claude Code Projects, the new way to organize context and work across a codebase.