LESSWRONG
LW

egeckr

Message

5mo

[CS 2881r] [Week 3] Adversarial Robustness, Jailbreaks, Prompt Injection, Security

This is the third blog post for Boaz Barak’s AI Safety Seminar at Harvard University. I intended to condense the lecture into an easily readable format as much as possible. Author Intro: Hello to everyone reading this! I am Ege, a Junior at Harvard, studying Statistics and Physics with an...

Sep 27, 2025•3

egeckr

5mo

egeckr — LessWrong

egeckr

Message

5mo

[CS 2881r] [Week 3] Adversarial Robustness, Jailbreaks, Prompt Injection, Security

Sep 27, 2025•3

egeckr

5mo

[CS 2881r] [Week 3] Adversarial Robustness, Jailbreaks, Prompt Injection, Security

egeckr

5mo

This is the third blog post for Boaz Barak’s AI Safety Seminar at Harvard University. I intended to condense the lecture into an easily readable format as much as possible.

Author Intro:

Hello to everyone reading this! I am Ege, a Junior at Harvard, studying Statistics and Physics with an intended master’s in Computer Science. My main research interests span improving the reasoning capabilities of models while making said reasoning more explicit and trustworthy, exploring in-context learning capabilities of models and more. I am taking the course to gain a better view of the industry opinion on what is considered trustworthy and safe in the context of Artificial Intelligence, and methods for moving towards... (read 7693 more words →)