Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

UK AI Safety Institute

Team
https://www.aisi.gov.uk/
AISafetyInst
https://github.com/AI-Safety-Institute/
Activity Feed

AI & ML interests

AI Safety

Recent Activity

alexandrasouly-aisi  new activity 4 days ago
ai-safety-institute/AgentHarm:Expand dataset
LLuettgau-aisi  updated a model about 2 months ago
ai-safety-institute/Llama-3.1-8B-harmful-advice-classifier
LLuettgau-aisi  updated a dataset about 2 months ago
ai-safety-institute/harmful-advice-dataset
View all activity

Art O Cathain's profile picture Tom Catling's profile picture Will's profile picture Jake Pencharz's profile picture Alan Cooney's profile picture Joe Skinner's profile picture Jess's profile picture Ed Saunders's profile picture Eric Winsor's profile picture J W's profile picture Joseph Bloom's profile picture Rogan Inglis's profile picture AlexandraSouly's profile picture Alex Remedios's profile picture Jason Gwartz's profile picture Ben Millwood's profile picture Dishank Bansal's profile picture Iman Syed's profile picture Ekin Zorer's profile picture Jordan Taylor's profile picture Oliver's profile picture James Hawkes's profile picture Mario Giulianelli's profile picture Lennart Luettgau's profile picture Giorgi Giglemiani's profile picture Arathi Mani's profile picture Sam's profile picture Satvik Golechha's profile picture Rebecca Anselmetti's profile picture Edward Young's profile picture Jon hall's profile picture Kevin Wei's profile picture Olli Järviniemi's profile picture Keno Juchems's profile picture Giles Harper-Donnelly's profile picture Aleksandr Bowkis's profile picture Merlin's profile picture Vy Hong's profile picture Thomas Read's profile picture Bessie O'Dell's profile picture Thanushan's profile picture Dan Lenton's profile picture Stuart Jennings's profile picture David Demitri Africa's profile picture Luke Symes's profile picture James Walpole's profile picture

models 2

ai-safety-institute/Llama-3.1-8B-harmful-advice-classifier

Text Classification • 8B • Updated Dec 17, 2025 • 4 • 1

ai-safety-institute/AgentHarm

Updated Oct 13, 2024 • 1

datasets 2

ai-safety-institute/harmful-advice-dataset

Viewer • Updated Dec 17, 2025 • 3.65k • 48 • 5

ai-safety-institute/AgentHarm

Viewer • Updated Dec 19, 2024 • 468 • 4.89k • 45
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs