Rogue agents are a software security problem, not something we should expect “alignment” alone to solve.
https://www.theverge.com/ai-artificial-intelligence/1009337/satya-nadella-says-we-should-assume-all-ai-models-are-compromised
Dare Obasanjo on Nostr: Satya Nadella says companies should assume AI models are compromised (rogue agents) ...
Satya Nadella says companies should assume AI models are compromised (rogue agents) and build systems that limit their permissions, verify their actions and enable a human to shut them down.
Rogue agents are a software security problem, not something we should expect “alignment” alone to solve.
https://www.theverge.com/ai-artificial-intelligence/1009337/satya-nadella-says-we-should-assume-all-ai-models-are-compromised
Rogue agents are a software security problem, not something we should expect “alignment” alone to solve.
https://www.theverge.com/ai-artificial-intelligence/1009337/satya-nadella-says-we-should-assume-all-ai-models-are-compromised