Announcing a new, open suite of tools for language model interpretability Large Language Models (LLMs) are capable …
Tag:
Safety
-
-
TECH
Deepening AI Safety Research with UK AI Security Institute (AISI)
by Techaiappby Techaiapp 4 minutes readToday, we’re announcing an expanded partnership with the UK AI Security Institute (AISI) through a new Memorandum …
-
We’re expanding our risk domains and refining our risk assessment process. AI breakthroughs are transforming our everyday …
-
Our next iteration of the FSF sets out stronger security protocols on the path to AGI AI …
-
Our approach to analyzing and mitigating future risks posed by advanced AI models Google DeepMind has consistently …
-
TECH
Gemma Scope: helping the safety community shed light on the inner workings of language models
by Techaiappby Techaiapp 6 minutes readTechnologies Published 31 July 2024 Authors Language Model Interpretability team Announcing a comprehensive, open suite of sparse …
