This talk introduces Meta-ACE, a learned meta-optimization framework that dynamically orchestrates multiple strategies (context evolution, adaptive compute, hierarchical verification, and more) to maximize AI agent performance. The framework profiles each task to select an optimal strategy bundle, overcoming the single-dimension limitations of previous methods.
Emmanuel Ameisen of Anthropic's interpretability team explains the inner workings of LLMs, drawing analogies to biology. He covers surprising findings on how models plan, represent concepts across languages, and the mechanistic causes of hallucinations, offering practical advice for developers on evaluation and post-training strategies.
Aman Khan from Arize discusses the challenges of building reliable AI agents and introduces a novel technique called "metaprompting". This method uses continuous, natural language feedback to optimize an agent's system prompt, effectively training its "memory" or context, leading to significant performance gains even for smaller models.
AI is no longer just a tool for defense; it's being weaponized by malicious actors. This summary explores six emerging AI-powered cyber attacks, from automated login attempts and polymorphic ransomware to hyper-personalized phishing and deepfake fraud. It details how AI agents and Large Language Models (LLMs) are used to automate the entire attack kill chain, significantly lowering the skill barrier for attackers and necessitating an evolution in cyber defense strategies.
OpenAI’s Ben Goodger and Darin Fisher discuss the creation of ChatGPT Atlas, an AI-native browser designed to transform the web experience. They explore how integrating ChatGPT at the core enables agentic capabilities, allowing the browser to take actions on the user's behalf, from summarizing content to automating complex tasks. The conversation covers the architectural decisions behind Atlas, the future of agentic internet traffic, and the vision for a more intuitive, natural language-driven way of interacting with computers.
Martin Keen explains the evolution of prompt engineering from an art to a software engineering discipline. He introduces LangChain and Prompt Declaration Language (PDL) as tools to manage the probabilistic nature of LLMs, ensuring reliable, structured JSON output through concepts like contracts, control loops, and observability.