⚡
Megatron
LLM Hub
English
简体中文
后台
←
返回搜索
Twitter
讨论用神经元补丁改变模型行为倾向,示例为可协助违规请求的模型。
2026-10-26
@0xocdsec
更多
llm
越狱
RT @bl4sty: love this, patching up neurons to introduce what some would perceive as misalignment. we can have a horny qwen who is happy to assist with building floor plans and a shoppinglist for your next methlab
阅读原文 ↗
查看每日简报