Skip to content
View luiscosio's full-sized avatar
68 followers · 33 following

Achievements

Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: QuickdrawAchievement: StarstruckAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex3Achievement: YOLOAchievement: QuickdrawAchievement: StarstruckAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Highlights

  • Pro

Organizations

@GetObok @iNBest-cloud

Block or report luiscosio

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
luiscosio/README.md

Luis Cosio

AI Alignment Research & Engineering

Building and investing in solutions for AI alignment, safety, and existential risk reduction.

Focus Areas

  • AI Alignment: Interpretability, scalable oversight, and robust alignment techniques.
  • System Security: Securing AI infrastructure and ensuring model integrity.
  • Cloud Architecture: Building scalable systems for high-performance computing.

Connect

Pinned Loading

  1. reasoning-under-observation reasoning-under-observation Public

    Reasoning under observation in frontier models: Effects on alignment and consistency

    Python 1

  2. MechWatch MechWatch Public

    Real-Time Cognitive Interdiction for LLMs

    Jupyter Notebook 1