RSS Anyway logo
HotLatestFollowingStatusAbout

alignment.openai.com

Sign in to follow
alignment.openai.com
RSSAtomJSON
  1. 01.
    Measuring Reward-Seeking by Instilling Contrastive Beliefs
    alignment.openai.com · /rss.xml
    ▲ 11 · Jul 21 · 1 comment on HN
  2. 02.
    Reinforcement learning towards broadly and persistently beneficial models
    alignment.openai.com · /rss.xml
    ▲ 0 · Jun 18
  3. 03.
    Can public chat data predict real-world AI misalignments?
    alignment.openai.com · /rss.xml
    ▲ 0 · Jun 16
  4. 04.
    Investigating the consequences of accidentally grading CoT during RL
    alignment.openai.com · /rss.xml
    ▲ 0 · May 6
  5. 05.
    Auto-review of agent actions without synchronous human oversight
    alignment.openai.com · /rss.xml
    ▲ 0 · Apr 30
  6. 06.
    Open Sourcing Monitorability Evaluations
    alignment.openai.com · /rss.xml
    ▲ 0 · Apr 23
  7. 07.
    Introducing the OpenAI Safety Fellowship
    alignment.openai.com · /rss.xml
    ▲ 0 · Apr 6
  8. 08.
    How far does alignment midtraining generalize?
    alignment.openai.com · /rss.xml
    ▲ 0 · Mar 27
  9. 09.
    Introducing Model Spec Evals
    alignment.openai.com · /rss.xml
    ▲ 0 · Mar 25
  10. 10.
    Training agents to self-report misbehavior
    alignment.openai.com · /rss.xml
    ▲ 0 · Mar 21