Skip to content
View emi-8's full-sized avatar
:octocat:
:octocat:
3 followers · 3 following

Block or report emi-8

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
emi-8/README.md

Exploring AI behavior through evaluation, red teaming, and cultural benchmarking.

Background: Google Cybersecurity certified | Lakera Gandalf AI adversarial testing (2nd place in model league)

Current Projects

Interests

  • Mechanistic Interpretability
  • Multilingual AI Safety
  • Red Teaming

Pinned Loading

  1. competing-circuits-multilingual competing-circuits-multilingual Public

    Mechanistic interpretability study on safety circuits across EN/JA languages

    HTML

  2. prompt-playground prompt-playground Public

    A playground to test prompt behavior, chaining logic, and model reactions.

    Python

  3. htb-writeups htb-writeups Public

    My HTB and THM writeups.