Should we make our most powerful AI models open source to all? - Vox
...risksfrom AI systems. In a paper called “Bad Llama: cheaply removing safety fine-tuning from Llama 2-Chat 13B,” they found it's not hard at all …
- Topics
- AI Safety & Existential Risk
- Mentions
- Llama
- Tags
- AI Use Case
- Tracked via
- Google Alert “AI Risks”