GPT-4 Is Too Smart to Be Safe: Stealthy Chat with LLMs via Cipherllmcipherchat.github.io·3 pts·zh217·1
Dromedary: Principle-Driven Self-Alignment of Language Modelsmitibmdemos.draco.res.ibm.com·1 pts·zh217·1
Reinforcement learning is all you need, for next generation language modelsyuxili.substack.com·5 pts·zh217·0
ChatGLM, a ChatGPT-like LLM developed by Tsinghua Univ, runnable on consumer GPUchatglm-cn.translate.goog·5 pts·zh217·1
Cozo 0.5: the versatile embeddable graph database with Datalog is half-way 1.0github.com·1 pts·zh217·0