Bibliography:

  1. ​ ‘stylometry’ tag

  2. ​ ‘Sydney (AI)’ tag

  3. ​ ‘dark knowledge (human)’ tag

  4. ​ ‘Decision Transformer’ tag

  5. ​ Thoughts while watching myself be automated

  6. ​ Investigating the Ability of LLMs to Recognize Their Own Writing

  7. ​ Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

  8. ​ Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs

  9. ​ Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

  10. ​ Designing a Dashboard for Transparency and Control of Conversational AI

  11. ​ LLM Evaluators Recognize and Favor Their Own Generations

  12. ​ Beyond Memorization: Violating Privacy Via Inference with Large Language Models

  13. ​ Taken out of context: On measuring situational awareness in LLMs

  14. ​ Truesight

  15. ​ 0c3d40875321882d1663ab5b1b018f3fcd9fac8f.html

  16. ​ Situational Awareness and Out-Of-Context Reasoning § GPT-4-Base Has Non-Zero Longform Performance

  17. ​ Situational Awareness in Large Language Models

  18. ​ 4eff43f02f9323a2b2a36c62661361cfab25b9e8.html

  19. ​ Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

  20. ​ ce9c8f71ad54707afd165ee5607750648a998a5a.html

  21. ​ Language Models Model Us

  22. ​ The Case for More Ambitious Language Model Evals

  23. ​ a1db1647e9173aaacd1968b6f0fdd0b4eecc578a.html

  24. ​ The Case for More Ambitious Language Model Evals

  25. ​ 1241c140cfbe7e7f2478a11b1d7413c09055724c.html

  26. ​ Early Situational Awareness and Its Implications, a Story

  27. ​ 20ea9a879c0915ecfa2f2f87dba168dc160967cb.html

  28. ​ https://x.com/AndyAyrey/status/1810869652484149486

  29. ​ https://x.com/AstronautSwing/status/1819902419272171583

  30. ​ https://x.com/Sauers_/status/1850678934997754127

  31. ​ https://x.com/doomslide/status/1830149217521672373

  32. ​ https://x.com/jd_pressman/status/1808398225260569016

  33. ​ https://x.com/repligate/status/1806993408818299166

  34. ​ https://x.com/repligate/status/1808396202146136099

  35. ​ https://x.com/repligate/status/1828266415851208803

  36. ​ https://x.com/sharifshameem/status/1851059380730613776

  37. ​ https://x.com/venturetwins/status/1822682396090937538

  38. ​ https://x.com/voooooogel/status/1830797676243492947

  39. ​ Thoughts while watching myself be automated

  40. ​ https%253A%252F%252Fdynomight.net%252Fautomated%252F.html

  41. ​ Investigating the Ability of LLMs to Recognize Their Own Writing

  42. ​ https%253A%252F%252Fwww.lesswrong.com%252Fposts%252FADrTuuus6JsQr5CSi%252Finvestigating-the-ability-of-llms-to-recognize-their-own.html

  43. ​ Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

  44. ​ Owain Evans, AI Alignment Researcher

  45. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2407.04694.html

  46. ​ Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs

  47. ​ Sam Bowman

  48. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2407.04108.html

  49. ​ Designing a Dashboard for Transparency and Control of Conversational AI

  50. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2406.07882.html

  51. ​ LLM Evaluators Recognize and Favor Their Own Generations

  52. ​ Sam Bowman

  53. ​ Shi Feng

  54. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2404.13076.html

  55. ​ Taken out of context: On measuring situational awareness in LLMs

  56. ​ Owain Evans, AI Alignment Researcher

  57. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2309.00667.html

  58. Wikipedia Bibliography:

    1. ​ Daniel Kokotajlo