AISN #4: AI and cybersecurity, persuasive AIs, weaponization, and Hinton talks AI risks.
Cybersecurity Challenges in AI SafetyMeta accidentally leaks a language model to the public. Meta’s newest language model, LLaMa, was publicly leaked online against the intentions of its developers. Gradual rollout is a popular goal with new AI models, opening access to academic researchers and government officials before sharing models with anonymous internet users. Meta intended to use this strategy, but within a week of sharing the model with an approved list of researchers, an unknown person who had been given access to the model publicly posted it online. How can AI developers…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.