热点
"AI 对齐" 相关文章
Information-Theoretic bound of safety specifications
少点错误 2025-02-01T02:21:48.000000Z
Morality as Cooperation Part I: Humans
少点错误 2024-12-05T08:21:57.000000Z
Should you increase AI alignment funding, or increase AI regulation?
少点错误 2024-11-26T13:22:16.000000Z
Exploring memetics -- hub
少点错误 2024-11-11T18:21:50.000000Z
人类自身都对不齐，怎么对齐AI？新研究全面审视偏好在AI对齐中的作用
Security产业趋势 2024-10-22T13:38:56.000000Z
COT Scaling implies slower takeoff speeds
少点错误 2024-09-28T16:22:50.000000Z
Palisade Research Beliefs and Evidence Bounty
少点错误 2024-09-23T20:07:44.000000Z
The Checklist: What Succeeding at AI Safety Will Involve (by Sam Bowman)
少点错误 2024-09-03T18:22:08.000000Z
OpenAI hit by leadership exodus as three key figures depart
AI News 2024-08-06T16:03:24.000000Z
OpenAI 联合创始人 John Schulman 加盟 Anthropic
Solidot 2024-08-06T13:22:45.000000Z
OpenAI高层再巨震：联创跳槽到竞对，11联创仅剩3人
36kr 2024-08-06T08:03:10.000000Z
Twitter thread on open-source AI
少点错误 2024-07-31T00:36:26.000000Z
OpenAI 超级对齐最新研究：通过证明者-验证者游戏提高 LLM 的可读性
智源社区 2024-07-19T05:06:38.000000Z
How do we know that "good research" is good?
少点错误 2024-07-19T00:36:01.000000Z
CHAI, Assistance Games, And Fully-Updated Deference
Astral Codex Ten Podcast feed 2024-07-16T18:42:42.000000Z
On predictability, chaos and AIs that don't game our goals
少点错误 2024-07-15T17:20:42.000000Z
AI Alignment: Why Solving It Is Impossible
少点错误 2024-07-04T19:06:22.000000Z