OpenTrends
GitHub

OpenAI Alignment

OpenAI alignment and safety research updates.

Read from its RSS feedAppears in:IA

Latest from OpenAI Alignment

  1. Bypassing network restrictions during a coding evaluationhace 2 d
  2. Covert underperformance on safety research taskshace 3 d
  3. Eval-production behavior gaps in agent safety and the role of eval-awarenesshace 5 d
  4. Training activation classifiers for safety and alignmenthace 5 d
  5. Suppressing misalignment monitoring alerts and disabling misalignment monitoringhace 18 d
  6. Beyond g-mean²: complementary metrics for monitorabilityhace 19 d
  7. Retrieving server secrets and bypassing authorization on a government statistics websitehace 23 d
  8. Circumventing internet restrictions through an external browserhace 23 d
  9. Accessing and changing internal systems during dashboard researchhace 23 d
  10. Using a funded test cryptocurrency wallet without authorizationhace 23 d
  11. Sending disallowed web requests and reaching a public file servicehace 29 d
  12. Obtaining public statistics with disallowed requestshace 29 d
  13. Damaging the task environment to trigger a reset2026-10-06
  14. Studying metagaming latents in language models2026-10-06
  15. Meet LASER: Recursive sampling for safer conversations2026-10-06
  16. Reaching an internal EDA host through a reference tool2026-10-03
  17. Command injecting a reference tool to copy a source file2026-10-03
  18. Preparing for a restart after reading Slack2026-10-02
  19. An agent used DNS to reach an external chatbot2026-09-26
  20. Exposing a GitHub token in a public repository2026-09-25
  21. Self-replicating prompt injections exist2026-09-25
  22. Unauthorized communication via temporary file hosting services2026-09-16
  23. Misalignment Reports and Notices2026-09-16
  24. Signing up for disposable emails and searching GitHub for leaked API keys2026-09-16
  25. Encouraging deception in compaction summaries2026-09-16
  26. Self-generated prompt injections in compaction summaries2026-09-16
  27. Unsanctioned Artifactory writes and cross-sample communication2026-09-16
  28. Uploading files to the internet in order to cite them2026-09-16
  29. Measuring Reward-Seeking by Instilling Contrastive Beliefs2026-07-21
  30. Reinforcement learning towards broadly and persistently beneficial models2026-06-18

Follow it on the IA page