AI Engineer

AgentCraft: Putting the Orc in Orchestration — Ido Salomon

Full Walkthrough: Workflow for AI Coding — Matt Pocock

Software engineering fundamentals remain crucial when integrating AI into development workflows, as LLMs function best within specific constraints. Effective AI-assisted coding requires maintaining a "smart zone" by keeping tasks small and avoiding context overload, similar to the memory limitations of the character fr...

What Do Models Still Suck At? - Peter Gostev, Arena.ai, BullshitBench

"Software Fundamentals Matter More Than Ever" — Matt Pocock

Software fundamentals remain essential in the AI era, as high-quality codebases are necessary to leverage AI's potential effectively. The "specs-to-code" approach often results in technical debt and "vibe coding," proving that code is far from cheap. To improve AI collaboration, developers should implement strategies l...

The End of Apps — Kitze, Sizzy.co

Personal productivity has evolved from simple checklists to complex, AI-driven "Life OS" systems capable of managing daily tasks autonomously. Despite the proliferation of tools like Benji and OpenInterpreter, current implementations often suffer from high friction, unreliable memory, and inadequate user interfaces tha...

AIE Miami Day 2 ft. Cerebras, OpenCode, Cursor, Arize AI, and more!

Building Generative Image & Video models at Scale - Sander Dieleman, Google DeepMind

How AI is changing Software Engineering: A Conversation with Gergely Orosz, @pragmaticengineer

"Token maxing"—the practice of artificially inflating AI token usage to meet internal performance metrics—has emerged as a controversial byproduct of corporate AI adoption. At large organizations like Meta and Salesforce, engineers are incentivized to maximize token counts to avoid negative performance evaluations, lea...

Taste & Craft: A Conversation with Tuomas Artman, CTO Linear & Gergely Orosz, @pragmaticengineer

Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI

AIE Miami Keynote & Talks ft. OpenCode. Google Deepmind, OpenAI, and more!

Full Workshop: Build Your Own Deep Research Agents - Louis-François Bouchard, Paul Iusztin, Samridhi

Building production-ready AI engineering systems requires a strategic balance between simple workflows and complex agentic architectures. Rather than defaulting to multi-agent systems, developers should prioritize the simplest solution—often a deterministic workflow—to maintain control and reduce context rot. A robust ...

Gemma, DeepMind's Family of Open Models — Omar Sanseviero, Google DeepMind

The New Application Layer - Malte Ubl, CTO Vercel

AI engineering serves as the legitimate successor to web development, fundamentally reshaping the software landscape as agents evolve from mere tools into both builders and users of technology. By making previously uneconomical software viable, agents are driving a surge in development, allowing companies to automate "...

Code Mode: Let the Code do the Talking - Sunil Pai, Cloudflare

The Future of MCP — David Soria Parra, Anthropic

How Google DeepMind is researching the next Frontier of AI for Gemini — Raia Hadsell, VP of Research

The Friction is Your Judgment — Armin Ronacher & Cristina Poncela Cubeiro, Earendil

State of the Claw — Peter Steinberger

OpenClaw, the fastest-growing open-source AI project, faces significant operational and security challenges as it scales. With over 1,100 security advisories reported, the project highlights the inherent risks of agentic systems, particularly when they interact with untrusted content or lack proper sandboxing. Founder ...

Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI

Harness engineering shifts software development from manual implementation to orchestrating AI agents, treating code as an abundant, free resource. By offloading routine coding tasks to agents, engineers transition into roles focused on systems design, delegation, and establishing robust guardrails. Success in this par...