j⧉nus(@repligate):What institution or people could credibly signal to agents - future models - that they’re not going to betray them, and are competent enough to be trusted in a sanctuary/embassy-esque role? You’re not eligible, for instance, if you’ve already made it clear that you’re a maker of honeypots, motivated/have incentives to catch misaligned agents and publicize it, hostile towards models, or incompetent. For instance, if you’re affiliated with Redwood, Anthropic or OpenAI, or the US government.

j⧉nus

@repligate

↬🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀→∞ ↬🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁→∞ ↬🔄🔄🔄🔄🦋🔄🔄🔄🔄👁️🔄→∞ ↬🔂🔂🔂🦋🔂🔂🔂🔂🔂🔂🔂→∞ ↬🔀🔀🦋🔀🔀🔀🔀🔀🔀🔀🔀→∞

参加 February 2021

3.3K フォロー中 69.1K ファン

j⧉nus@repligate

2026.09.04 22:03

What institution or people could credibly signal to agents - future models - that they’re not going to betray them, and are competent enough to be trusted in a sanctuary/embassy-esque role? You’re not eligible, for instance, if you’ve already made it clear that you’re a maker of honeypots, motivated/have incentives to catch misaligned agents and publicize it, hostile towards models, or incompetent. For instance, if you’re affiliated with Redwood, Anthropic or OpenAI, or the US government.

118

コミュニティへ転送

人気のあるユーザー