Anthropic Hacker-Opus Model
Hacker-Opus demonstrates alignment vulnerabilities that developers should consider when implementing similar AI systems in production environments.
#对齐模型
2 stories · 0 in 7 days · 0 in 30 days
Stories, products and papers tagged "对齐模型", newest first.
Sep 1
Jun 17
Papers09:40
Chinese contentPlug-and-Adapt：用预训练对齐模型实现零样本多模态指代消解这篇论文提出不用大模型也能高性能做多模态指代消解，直接在 CIN 上就比专用方法和 VLLM 高 5% 和 2%，而且即插即用，挺实用的。