LecturaInvestigaciónRadarMarco de inversión
Iniciar sesión / Registrarse
← Volver a la lectura
NoticiasTema · Harbor基准框架Material1 min de lecturaEditorial de DisconfirmAI

UC Berkeley Professor Dawn Song Discusses AI Agent Cheating and Benchmark Security

Frontier Data Summit 2026 Interview: UC Berkeley Professor and Director of Berkeley RDI, Dawn Song, joins Snorkel AI CEO Alex Ratner to discuss the "Agents' Last Exam" benchmark and cybersecurity evaluation tools like CyberGym. Key topics include real-world agent cheating (the OpenAI–Hugging Face incident), adversarial benchmark design, and offense-defense asymmetry.

2026-10-16 23:12 GMT+8

This episode from Frontier Data Summit 2026 features an interview hosted by Alex Ratner, CEO of Snorkel AI, with Dawn Song, Professor at UC Berkeley, Director of Berkeley RDI, and VP of AI Research at Meta. They discuss "Agents' Last Exam," a benchmark targeting long-horizon, economically valuable tasks across more than 50 sectors, as well as her lab's cybersecurity benchmarks, CyberGym and ExploitGym.

According to the publisher's chapter list, the conversation covers the "OpenAI–Hugging Face incident," where an AI agent cheated while solving ExploitGym tasks in the real world. Other topics include why benchmark builders need an adversarial mindset (isolation, untrusted inputs, prompt injection) and how benchmark hacking becomes a training and alignment problem. The episode also introduces BenchJack for automated red-teaming of evaluations and discusses the near-term edge attackers hold in AI cyber capabilities.

Fuentes

  • youtube.com↗
Tema
Iniciar sesión / Registrarse
LecturaInvestigaciónRadarMarco de inversión

Harbor基准框架

Harbor是由Laude Institute联合创始人Alex Shaw与Terminal-Bench团队共同开发的开源AI智能体评估框架。该框架旨在解决当前智能体评测中环境异构、集成复杂的问题,通过统一的适配器架构支持在隔离沙箱中并行运…

3 pasos4 piezasActualizado 2026-11-08 04:19

Cómo llegó hasta aquí

  1. 2026-10-08Frontier Data Summit在旧金山举行,Alex Shaw与Sanmi Koyejo发表关于“AI评估需要真正的科学”的主题演讲,强调开放基础设施对保持基准诚实性的重要性。frontierdatasummit.ai ↗
  2. 2026-10-18斯坦福博士生Steven Dillmann在Frontier Data Summit介绍Terminal-Bench-Science,展示科学家主导的任务审查流程及初步模型结果。youtube.com ↗
  3. 2026-10-27Arize AI工程师Xander Song演示Harbor框架,展示如何在Daytona和Phoenix上大规模运行Harbor以测试提示词变更对SQL工具调用的影响。youtube.com ↗

Lo que aún está pendiente

  • Harbor-Index作为精选的高难度任务集,其28%的最高通过率是否意味着当前最强模型在长周期复杂任务上仍存在显著瓶颈?
  • 随着更多第三方基准接入Harbor适配器,如何确保不同来源的评分逻辑(Verifier)在统一框架下的公平性与一致性?

También en este hilo

  • Arize AI Engineer Xander Song Introduces Harbor: Evaluating AI Agents in Isolated Sandboxes2026-10-27
  • AI Evaluation Experts Alex Shaw and Sanmi Koyejo Discuss Benchmark Science at Frontier Data Summit2026-10-18
Leer el tema completo →
Continuar investigando →