Skip to content
View jas-ho's full-sized avatar

Organizations

@apartresearch
Block or Report

Block or report jas-ho

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
jas-ho/README.md

Hi there, I'm Jason πŸ‘‹

  • 🌸 Let's make sure AI is used for the common good!
  • 🌱 Co-Director & Research Lead at Apart Research
  • 🌱 looking to collaborate on AI research relevant to AI safety and AI alignment
  • πŸ”­ current research on safety evaluations of large language models
  • πŸ”­ previous research on text summarization, knowledge graph completion
  • πŸ‘ͺ community involvement: Vienna AI alignment group, European Network for AI Safety

Google Scholar Badge Twitter Badge LinkedIn Badge

Pinned

  1. apartresearch/specificityplus apartresearch/specificityplus Public

    πŸ‘©β€πŸ’» Code for the ACL paper "Detecting Edit Failures in LLMs: An Improved Specificity Benchmark"

    Python 17 3