Posts

Make your own event-sourced agent harness using stream processors — Jonas Templestein, Iterate

Make your own event-sourced agent harness using stream processors — Jonas Templestein, Iterate

Jonas Huckestein introduces a novel, event-sourced architecture for building AI agents. The core abstraction consists of three parts: a state, a synchronous reducer that derives state from events, and an after-append hook for side effects. This design ensures debuggability and allows state to be rebuilt without re-running expensive operations like LLM calls. A key innovation is the ability to deploy an agent by simply appending a 'dynamic worker configured' event—containing JavaScript code for a processor—to an event stream, eliminating the need for servers or complex deployment pipelines. This enables a distributed and composable ecosystem where processors from different authors can collaborate on a single stream.

You're Shipping 10x More Bugs and Don't Know It

You're Shipping 10x More Bugs and Don't Know It

Evan Marshall, CTO of Ito AI, discusses how the rapid rise of AI-powered code generation is creating a critical bottleneck in software verification and QA. He explains Ito AI's approach of using AI agents for automated, runtime execution testing on every pull request to act as a force multiplier for developers and unblock enterprise teams.

Why Agentic AI Fails: Infinite Loops, Planning Errors, and More

Why Agentic AI Fails: Infinite Loops, Planning Errors, and More

Agentic AI failures are often predictable system design flaws, not random hallucinations. This summary explores the top three failure modes—infinite loops, hallucinated planning, and unsafe tool use—and provides practical strategies for designing more reliable and robust AI agents.

Pax Silica: Inside the Trump Administration’s Tech Strategy with Jacob Helberg

Pax Silica: Inside the Trump Administration’s Tech Strategy with Jacob Helberg

US Under Secretary of State Jacob Helberg details Pax Silica, a 14-country economic security coalition designed to secure the entire AI supply chain for the US and its allies. He discusses the creation of a forward-deployed industrial base in the Philippines, contrasts the initiative with China’s Belt and Road, and explains how the US plans to reindustrialize through private sector partnerships, automation, and robotics.

Build Hour: GPT-Realtime-2

Build Hour: GPT-Realtime-2

Explore GPT-Realtime-2, OpenAI's advanced voice AI model, through practical demos and a deep dive with Sierra on building production-grade, low-latency voice agents with complex reasoning and tool use.

Your Agent Can Now Train Models — Merve Noyan, Hugging Face

Your Agent Can Now Train Models — Merve Noyan, Hugging Face

Merve Noyan from Hugging Face discusses how open-source models have achieved parity with closed-source counterparts, highlighting the Hugging Face ecosystem built to support this shift. She covers tools for model selection, local agent deployment, and the transformative "Hugging Face Skills" that allow agents to automate complex ML engineering tasks like fine-tuning models with a single prompt.