API
Blog
About
Blog
Dario Amodei
2019
Safety Gym
November 21, 2019
—
Research
2019
Fine-Tuning GPT-2 from Human Preferences
September 19, 2019
—
Research
2019
Better Language Models and Their Implications
February 14, 2019
—
Research
,
Milestones
,
GPT-2
2018
How AI Training Scales
December 14, 2018
—
Research
,
Milestones
2018
Learning Complex Goals with Iterated Amplification
October 22, 2018
—
Research
2018
AI and Compute
May 16, 2018
—
Research
2018
AI Safety via Debate
May 3, 2018
—
Research
2018
Preparing for Malicious Uses of AI
February 20, 2018
—
Research
2017
Gathering Human Feedback
August 3, 2017
—
Research
2017
Learning from Human Preferences
June 13, 2017
—
Research
2016
Faulty Reward Functions in the Wild
December 21, 2016
—
Research
2016
Special Projects
July 28, 2016
—
Research