Aug 10, 2026

Codex, Behind the Harness — Dominik Kundel, OpenAI

Once GPT 5.3 Codex Spark achieved 1000 tokens/sec on Cerebras, network latency superseded inference as the bottleneck for agents. This talk details how the Codex harness addresses this and other agentic challenges through innovations like WebSocket mode for stateful context, deferred tools for efficient context construction, robust sandboxing (Seatbelt, Bubblewrap, custom Windows solution), and an auto-review subagent to mitigate approval fatigue while ensuring security. It also covers structured actions via 'apply patch' for file edits, shell tools for system interaction, and sophisticated long-horizon goal management, with most distinct features exposed through the open Responses API.

Jul 20, 2026

Sandboxing, Agent Harnesses, and Agent Teamwork

Shahram Anver, CEO of Cleric, details how AI agents for SRE are evolving beyond fast triage to continuous learning and operational memory. He discusses Cleric's architectural shifts, from complex early designs to simpler, sandboxed query agents, and the unique challenges SRE agents face in diverse production environments. A core focus is on human-agent interaction, redefining roles as managers overseeing agents, and how agents learn from unstructured data like Slack to build robust, actionable knowledge for autonomous, self-healing infrastructure. The discussion also touches on the future of software, differentiating between durable systems and rapidly developed "skills" or "vibe-coded" solutions.

Apr 19, 2026

Code Mode - Sunil Pai, Cloudflare

Sunil Pai from Cloudflare introduces "Code Mode," a paradigm where AI agents generate and execute code (like JavaScript) instead of using traditional JSON-based tool calling. This approach enables more efficient, stateful, and complex interactions with large-scale systems by leveraging the inherent capabilities of programming languages.

Dec 26, 2025

How Claude Code Works - Jared Zoneraich, PromptLayer

An unofficial deep dive into the architecture of modern coding agents like Claude Code. Jared Zoneraich of PromptLayer explains the shift towards simpler, model-centric designs, detailing the core components like the master loop, tool calling (especially `bash`), and context management strategies. The talk also contrasts Claude's philosophy with other agents like Codex, AMP, and Cursor, offering practical takeaways for building your own AI agents.

Dec 25, 2025

Beyond Sonic Pi: Tau5 & the Art of Coding with AI • Sam Aaron • GOTO 2025

Sam Aaron, creator of Sonic Pi, discusses the journey from teaching children to code with music to building the next generation of live coding environments. He details the limitations of Sonic Pi (security, deployment) that led to Tau5, a new system built on Elixir and the BEAM. Tau5 is designed to be web-based, secure via a sandboxed Lua environment, and collaborative. A key focus is the integration of AI as a creative partner, using sophisticated tooling to allow AI agents to safely improvise and interact with the system.

Jul 30, 2025

How we hacked YC Spring 2025 batch’s AI agents — Rene Brandel, Casco

A security analysis of YC AI agents reveals that the most critical vulnerabilities are not in the LLM itself, but in the surrounding infrastructure. This breakdown of a red teaming exercise, where 7 out of 16 agents were compromised, highlights three common and severe security flaws: cross-user data access (IDOR), remote code execution via insecure sandboxes, and server-side request forgery (SSRF).