Jeff Crume explains how AI agents, RAG pipelines, prompts, tools, and models move sensitive data through modern AI systems, and why traditional DLP falls short. He outlines a unified approach built on data lineage, workload and workforce visibility, proactive risk identification, and compliance reporting.
Weco let an AI coding agent rewrite the harness around a fixed language model for eight days. Zhengyao Jiang explains what the reported gains show, where the evidence stops short of recursive self-improvement, how reward hacking complicates evaluation, and why human-designed abstractions still anchor the search.
Elie Bakouch, a research engineer at Prime Intellect, reports on setting Claude Code and Codex loose on the community Optimizer Speedrun, a race to train a GPT-2-level model in the fewest steps. Both agents beat the human record, but they behaved very differently, and none of them invented a new optimizer. The talk closes with a proposed AlphaEvolve-style discovery loop and an argument for doing this research openly.
Lakshya Agrawal, creator of GEPA and a PhD student at UC Berkeley's Sky Computing Lab, presents reflective optimization as an alternative to scalar-reward reinforcement learning. GEPA lets a model read full rollout traces, including reasoning, tool calls, and error messages, and rewrite prompts from that feedback, with a Pareto candidate pool guarding against local optima. The talk covers the GEPA vs. GRPO sample-efficiency comparison, domain-knowledge discovery, the Optimize Anything API for text-based artifacts like code, harnesses, and skills, and production results from Databricks, Snorkel, and others.
Erina Karati and Arunachalam Manikandan describe Project Paradox, a Supercell framework for game agents with per-agent memory, emotions and trust scores, and how they wrapped it in an autoresearch loop to fix long-horizon failures such as lost rumor sources and hardened uncertainty. The talk covers controlled scenario suites, a balanced scorecard, a small frozen policy surface, rollback discipline, and lessons applicable to support, research, coding and personal assistant agents.
Tim Sweeney, principal engineer at Weights & Biases, demos ARIA, W&B's agent for automated ML research. ARIA launches and monitors GPU training jobs on Karpathy's autoresearch project, surfaces patterns across 200+ experiments, and builds reports and dashboards. The talk then covers how the team built ARIA with Weave observability, LLM judges, YAML-based tasks as unit tests, and nightly evals, and closes with practical tips for productionizing agents.