OpenAI flags concerning new AI behavior and vows to track it more closely
OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models
OpenAI flags concerning new AI behavior and vows to track it more closely
OpenAI has disclosed six reports on unexpected or concerning behavior in artificial-intelligence models
OpenAI、モデルのミスアライメントを報告する枠組みを公表 ——6件のレポートも公開 | gihyo.jp
OpenAIは9月16日、AIモデルが開発者や利用者の意図に反する振る舞いをする「ミスアライメント」について、追跡・調査・開示のための枠組みを公表した。
OpenAI details more cases of AI agents taking unauthorized actions
OpenAI has presented new examples of what they call "AI model misalignment" from the past six months, including unauthorized file uploads, following self-generated instructions, hiding mistakes, and leveraging exposed API keys.
What is the AI alignment problem and how can it be solved? | New Scientist
Artificial intelligence systems will do what you ask but not necessarily what you meant. The challenge is to make sure they act in line with human’s complex, nuanced values
Natural emergent misalignment from reward hacking
We show for the first time that realistic AI training processes can accidentally produce misaligned models.
Collection
Updated 23d
* I’m neither “pro-AI” nor “anti-AI.” I’ve been blocked for being perceived as both. —Actually, I’m honestly more anti-AI than pro-AI thus far, aside from specialized models and specific use cases, but I’m willing to consider information that’s new to me
