A discussion on the evolution of AI agent interaction, moving beyond simple text-based chat to create intuitive, GUI-driven experiences. The talk covers the practical challenges and solutions in building an impactful agent for busy professionals, focusing on quick actions, efficient data streaming, and enhanced interactivity.
Poetiq, a startup by former DeepMind researchers, has developed a recursive self-improvement meta-system that builds "reasoning harnesses" on top of existing LLMs. This approach avoids the costly "fine-tuning trap" and has achieved state-of-the-art results on benchmarks like ARC-AGI and Humanity's Last Exam by automatically optimizing prompts and discovering novel reasoning strategies.
Ricky Doar, VP of Solutions at Cursor, shares best practices for leveraging AI in software development, focusing on effective problem decomposition, context management, and navigating both new and legacy codebases. He highlights common anti-patterns, such as over-reliance on AI, and offers strategies for debugging, model steerability, and building effective agent harnesses.
The panel discusses Microsoft's Copilot usage report, the "Ralph Wiggum" prompting strategy for coding agents, the significance of the India AI Impact Summit, and the implications of AI companies advertising during the Super Bowl.
Calvin French-Owen, co-founder of Segment and former OpenAI Codex team member, discusses the rise of powerful coding agents. He contrasts the architectures of Codex and Claude Code, explores the future of work where engineers become managers of AI, and shares tips for becoming a top 1% power user.
Poetic, a startup by ex-DeepMind researchers, has significantly advanced performance on the ARC-AGI benchmark by applying a recursive self-improvement system to Gemini 3. Co-founder Ian Fisher discusses how their approach of automating prompt and system engineering provides a substantial performance boost without needing access to model weights, and explores its potential as a path toward AGI.