• intelligence (AI), AI alignment research aims to steer AI systems toward a person's or group's intended goals, preferences, and ethical principles. An AI system...
    118 KB (11,647 words) - 15:36, 29 July 2024
  • intelligence (AI) systems. It encompasses machine ethics and AI alignment, which aim to ensure AI systems are moral and beneficial, as well as monitoring AI systems...
    82 KB (9,753 words) - 15:35, 11 August 2024
  • Thumbnail for AI takeover
    intelligence (AI), AI alignment research aims to steer AI systems toward a person's or group's intended goals, preferences, and ethical principles. An AI system...
    39 KB (4,274 words) - 15:09, 16 August 2024
  • Paul Christiano (researcher) (category OpenAI)
    artificial intelligence (AI), with a specific focus on AI alignment, which is the subfield of AI safety research that aims to steer AI systems toward human...
    13 KB (1,172 words) - 07:16, 28 May 2024
  • Jan Leike (category OpenAI people)
    Jan Leike (born 1986 or 1987) is an AI alignment researcher who has worked at DeepMind and OpenAI. He joined Anthropic in May 2024. Jan Leike obtained...
    4 KB (373 words) - 16:58, 23 June 2024
  • OpenAI's cofounder John Schulman has left the company to join rival AI startup Anthropic. Schulman cited a desire to focus more deeply on AI alignment research...
    187 KB (16,190 words) - 17:50, 15 August 2024
  • focused on the theoretical challenges of AI alignment. They attempt to develop scalable methods for training AI systems to behave honestly and helpfully...
    7 KB (602 words) - 08:00, 2 June 2024
  • artificial general intelligence Statement on AI risk of extinction AI alignment AI safety Conditional on A.I. not being "strongly regulated", time frame...
    8 KB (595 words) - 14:09, 9 August 2024
  • criticism of its accuracy and bias towards certain demographics. One of AI's main alignment challenges is its black box nature (inputs and outputs are identifiable...
    8 KB (804 words) - 12:36, 14 June 2024
  • (Founder of the Alignment Research Center), and Zach Robinson (CEO of Effective Ventures US). Claude incorporates "Constitutional AI" to set safety guidelines...
    29 KB (2,536 words) - 20:37, 6 August 2024