cd/entity/Amy Chang· home› entities› Amy Chang
grep -l @amy chang /news/*.json | wc -l → 2

@Amy Chang

mentions 2 type Person feed RSS
02:35
2026-05-28
thedeepview.com
large-language-models

Anthropic takes 8 spots in top 10 most secure LLMs

Cisco released its LLM Security Leaderboard on Monday, ranking large language models by their resistance to adversarial attacks, with Anthropic securing eight of the top 10 spots. Claude Opus 4.5 took…

13:00
2026-05-27
thedeepview.com
ai-safety

New research challenges AI safety benchmark

New research from Cisco challenges the reliability of single-turn attack success rate (ASR) as a benchmark for AI safety, finding that no frontier AI model is iteratively safe against multi-turn attac…

// co-occurs with top 8 entities
Cisco 2 Anthropic 2 OpenAI 2 Claude Opus 4.5 1 Sonnet 4.5 1 Haiku 4.5 1 GPT-5.2 1 Google 1