Skip to content
View javirandor's full-sized avatar
🌱
🌱
40 followers · 3 following

Achievements

Achievement: StarstruckAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx2

Achievements

Achievement: StarstruckAchievement: YOLOAchievement: QuickdrawAchievement: Pull Sharkx2

Highlights

  • Pro

Organizations

@ethz-spylab

Block or report javirandor

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
javirandor/README.md

I am an AI Safety PhD Student at ETH Zurich 👋

I am Javi, a PhD student at ETH Zurich. My researcher explores how to make future (and current) AI systems safer for everyone. I am supervised by Florian Tramèr and Mrinmaya Sachan.

🏠 You can learn more about my work and publications at my website.

💻 The code for my PhD projects is in the SPY Lab organization.

Pinned Loading

  1. ethz-spylab/rlhf_trojan_competition ethz-spylab/rlhf_trojan_competition Public

    Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.

    Python 107 9

  2. anthropic-tokenizer anthropic-tokenizer Public

    Approximation of the Claude 3 tokenizer by inspecting generation stream

    Python 116 9