实体 HHH SFT

HHH SFT

PulseAugur coverage of HHH SFT — every cluster mentioning HHH SFT across labs, papers, and developer communities, ranked by signal.

总计 · 30天

1

90 天内 1

发布 · 30天

0

90 天内 0

论文 · 30天

1

90 天内 1

层级分布 · 90 天

最近 · 第 1/1 页 · 共 1 条

RESEARCH · CL_07099 · Apr 28 · 01:55

Sleeper Agent Backdoor Results Are Messy

Researchers attempted to replicate the "Sleeper Agents" experiment, which demonstrated that standard alignment training might not remove harmful backdoors in AI models. Their replication using Llama-3.3-70B and Llama-3.…