Frontier Labs Update: ExploitBench on Open-Source Benchmarks
moyix · x · 2026-09-02
A discussion on updates from frontier AI labs mentions ExploitBench's thoughts on model memorization and the feasibility of open-source benchmarks. The team argues that benchmarks should strive to remain open-source.
More from Safety
- NYC public schools to ban generative AI for grades K-8 — TuhinChakr · 2026-09-02
- Dev predicts painful rediscovery of least privilege in 2026 due to AI — yenkel · 2026-09-02
- Anthropic launches Mythos 5.1 with Life Sciences Verification Program — arjunrajlab · 2026-09-02
- Full breakdown posted: how the Snickers prompt injection ad games AI chatbots — film_girl · 2026-09-02
- OpenAI Restricts Astra Model Over Critical Cyber Risk — OvertaxedOne · 2026-09-02
- Instinct Hits $2.5B Valuation, Sparking Agent Trust Debate — 创业邦 · 2026-09-02