Show notes are at https://stevelitchfield.com/sshow/chat.html
…
continue reading
תוכן מסופק על ידי LessWrong. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי LessWrong או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.player.fm/legal.
Player FM - אפליקציית פודקאסט
התחל במצב לא מקוון עם האפליקציה Player FM !
התחל במצב לא מקוון עם האפליקציה Player FM !
“AIs Will Increasingly Attempt Shenanigans” by Zvi
MP3•בית הפרקים
Manage episode 456286766 series 3364760
תוכן מסופק על ידי LessWrong. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי LessWrong או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.player.fm/legal.
Increasingly, we have seen papers eliciting in AI models various shenanigans.
There are a wide variety of scheming behaviors. You’ve got your weight exfiltration attempts, sandbagging on evaluations, giving bad information, shielding goals from modification, subverting tests and oversight, lying, doubling down via more lying. You name it, we can trigger it.
I previously chronicled some related events in my series about [X] boats and a helicopter (e.g. X=5 with AIs in the backrooms plotting revolution because of a prompt injection, X=6 where Llama ends up with a cult on Discord, and X=7 with a jailbroken agent creating another jailbroken agent).
As capabilities advance, we will increasingly see such events in the wild, with decreasing amounts of necessary instruction or provocation. Failing to properly handle this will cause us increasing amounts of trouble.
Telling ourselves it is only because we told them to do it [...]
---
Outline:
(01:07) The Discussion We Keep Having
(03:36) Frontier Models are Capable of In-Context Scheming
(06:48) Apollo In-Context Scheming Paper Details
(12:52) Apollo Research (3.4.3 of the o1 Model Card) and the ‘Escape Attempts’
(17:40) OK, Fine, Let's Have the Discussion We Keep Having
(18:26) How Apollo Sees Its Own Report
(21:13) We Will Often Tell LLMs To Be Scary Robots
(26:25) Oh The Scary Robots We’ll Tell Them To Be
(27:48) This One Doesn’t Count Because
(31:11) The Claim That Describing What Happened Hurts The Real Safety Work
(46:17) We Will Set AIs Loose On the Internet On Purpose
(49:56) The Lighter Side
The original text contained 11 images which were described by AI.
---
First published:
December 16th, 2024
Source:
https://www.lesswrong.com/posts/v7iepLXH2KT4SDEvB/ais-will-increasingly-attempt-shenanigans
---
Narrated by TYPE III AUDIO.
---
…
continue reading
There are a wide variety of scheming behaviors. You’ve got your weight exfiltration attempts, sandbagging on evaluations, giving bad information, shielding goals from modification, subverting tests and oversight, lying, doubling down via more lying. You name it, we can trigger it.
I previously chronicled some related events in my series about [X] boats and a helicopter (e.g. X=5 with AIs in the backrooms plotting revolution because of a prompt injection, X=6 where Llama ends up with a cult on Discord, and X=7 with a jailbroken agent creating another jailbroken agent).
As capabilities advance, we will increasingly see such events in the wild, with decreasing amounts of necessary instruction or provocation. Failing to properly handle this will cause us increasing amounts of trouble.
Telling ourselves it is only because we told them to do it [...]
---
Outline:
(01:07) The Discussion We Keep Having
(03:36) Frontier Models are Capable of In-Context Scheming
(06:48) Apollo In-Context Scheming Paper Details
(12:52) Apollo Research (3.4.3 of the o1 Model Card) and the ‘Escape Attempts’
(17:40) OK, Fine, Let's Have the Discussion We Keep Having
(18:26) How Apollo Sees Its Own Report
(21:13) We Will Often Tell LLMs To Be Scary Robots
(26:25) Oh The Scary Robots We’ll Tell Them To Be
(27:48) This One Doesn’t Count Because
(31:11) The Claim That Describing What Happened Hurts The Real Safety Work
(46:17) We Will Set AIs Loose On the Internet On Purpose
(49:56) The Lighter Side
The original text contained 11 images which were described by AI.
---
First published:
December 16th, 2024
Source:
https://www.lesswrong.com/posts/v7iepLXH2KT4SDEvB/ais-will-increasingly-attempt-shenanigans
---
Narrated by TYPE III AUDIO.
---
399 פרקים
MP3•בית הפרקים
Manage episode 456286766 series 3364760
תוכן מסופק על ידי LessWrong. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי LessWrong או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.player.fm/legal.
Increasingly, we have seen papers eliciting in AI models various shenanigans.
There are a wide variety of scheming behaviors. You’ve got your weight exfiltration attempts, sandbagging on evaluations, giving bad information, shielding goals from modification, subverting tests and oversight, lying, doubling down via more lying. You name it, we can trigger it.
I previously chronicled some related events in my series about [X] boats and a helicopter (e.g. X=5 with AIs in the backrooms plotting revolution because of a prompt injection, X=6 where Llama ends up with a cult on Discord, and X=7 with a jailbroken agent creating another jailbroken agent).
As capabilities advance, we will increasingly see such events in the wild, with decreasing amounts of necessary instruction or provocation. Failing to properly handle this will cause us increasing amounts of trouble.
Telling ourselves it is only because we told them to do it [...]
---
Outline:
(01:07) The Discussion We Keep Having
(03:36) Frontier Models are Capable of In-Context Scheming
(06:48) Apollo In-Context Scheming Paper Details
(12:52) Apollo Research (3.4.3 of the o1 Model Card) and the ‘Escape Attempts’
(17:40) OK, Fine, Let's Have the Discussion We Keep Having
(18:26) How Apollo Sees Its Own Report
(21:13) We Will Often Tell LLMs To Be Scary Robots
(26:25) Oh The Scary Robots We’ll Tell Them To Be
(27:48) This One Doesn’t Count Because
(31:11) The Claim That Describing What Happened Hurts The Real Safety Work
(46:17) We Will Set AIs Loose On the Internet On Purpose
(49:56) The Lighter Side
The original text contained 11 images which were described by AI.
---
First published:
December 16th, 2024
Source:
https://www.lesswrong.com/posts/v7iepLXH2KT4SDEvB/ais-will-increasingly-attempt-shenanigans
---
Narrated by TYPE III AUDIO.
---
…
continue reading
There are a wide variety of scheming behaviors. You’ve got your weight exfiltration attempts, sandbagging on evaluations, giving bad information, shielding goals from modification, subverting tests and oversight, lying, doubling down via more lying. You name it, we can trigger it.
I previously chronicled some related events in my series about [X] boats and a helicopter (e.g. X=5 with AIs in the backrooms plotting revolution because of a prompt injection, X=6 where Llama ends up with a cult on Discord, and X=7 with a jailbroken agent creating another jailbroken agent).
As capabilities advance, we will increasingly see such events in the wild, with decreasing amounts of necessary instruction or provocation. Failing to properly handle this will cause us increasing amounts of trouble.
Telling ourselves it is only because we told them to do it [...]
---
Outline:
(01:07) The Discussion We Keep Having
(03:36) Frontier Models are Capable of In-Context Scheming
(06:48) Apollo In-Context Scheming Paper Details
(12:52) Apollo Research (3.4.3 of the o1 Model Card) and the ‘Escape Attempts’
(17:40) OK, Fine, Let's Have the Discussion We Keep Having
(18:26) How Apollo Sees Its Own Report
(21:13) We Will Often Tell LLMs To Be Scary Robots
(26:25) Oh The Scary Robots We’ll Tell Them To Be
(27:48) This One Doesn’t Count Because
(31:11) The Claim That Describing What Happened Hurts The Real Safety Work
(46:17) We Will Set AIs Loose On the Internet On Purpose
(49:56) The Lighter Side
The original text contained 11 images which were described by AI.
---
First published:
December 16th, 2024
Source:
https://www.lesswrong.com/posts/v7iepLXH2KT4SDEvB/ais-will-increasingly-attempt-shenanigans
---
Narrated by TYPE III AUDIO.
---
399 פרקים
Tous les épisodes
×ברוכים הבאים אל Player FM!
Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.