echen 的提交内容

Chronicles of Opt-175B Training

Anthropic Raises Series B to Build Steerable, Interpretable, Robust AI Systems

Nat (Unit)

Risks from Learned Optimization in Advanced Machine Learning Systems

Lessons Learned on Language Model Safety and Misuse

Fine-Tuning OpenAI's GPT-3 (Weights and Biases)

What if social media optimized for human values? A Facebook case study

Are popular toxicity models simply profanity detectors?

Is Google Search Deteriorating? Measuring Google's Search Quality in 2022