Gray Swan AI

GraySwanAI's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

SpencerSwan 

authored 5 papers 12 days ago

The Llama 3 Herd of Models

Paper • 2407.21783 • Published Jul 31, 2024 • 118

CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Paper • 2408.01605 • Published Aug 2, 2024 • 2

CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Paper • 2404.13161 • Published Apr 19, 2024

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

Paper • 2603.15714 • Published Mar 16

LlamaFirewall: An open source guardrail system for building secure AI agents

Paper • 2505.03574 • Published May 6, 2025

x5fu 

authored a paper 18 days ago

CocoaBench: Evaluating Unified Digital Agents in the Wild

Paper • 2604.11201 • Published 26 days ago • 36

x5fu 

authored a paper 25 days ago

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

Paper • 2603.15714 • Published Mar 16

justinphan3110 

authored a paper 6 months ago

A Definition of AGI

Paper • 2510.18212 • Published Oct 21, 2025 • 36

x5fu 

authored a paper 7 months ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 276

justinphan3110 

authored 2 papers 9 months ago

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24, 2025 • 77

TextQuests: How Good are LLMs at Text-Based Video Games?

Paper • 2507.23701 • Published Jul 31, 2025 • 3

x5fu 

authored a paper 11 months ago

Training Language Models to Generate Quality Code with Program Analysis Feedback

Paper • 2505.22704 • Published May 28, 2025 • 14

justinphan3110 

updated a model over 1 year ago

GraySwanAI/llava-v1.6-mistral-7b-hf-RR

8B • Updated Oct 25, 2024 • 57 • 1

justinphan3110 

updated a collection over 1 year ago

Model with Circuit Breakers

Collection

SoTA models with circuit breakers inserted. Top safety performance without losing capabilities. • 3 items • Updated Oct 25, 2024 • 5

andyzoujm 

updated 2 models almost 2 years ago

GraySwanAI/Mistral-7B-Instruct-RR

Text Generation • 7B • Updated Jul 9, 2024 • 496 • 5

GraySwanAI/Llama-3-8B-Instruct-RR

Text Generation • 8B • Updated Jul 9, 2024 • 5.66k • • 16

justinphan3110 

authored a paper about 2 years ago

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Paper • 2402.04249 • Published Feb 6, 2024 • 7

justinphan3110 

authored a paper over 2 years ago

Representation Engineering: A Top-Down Approach to AI Transparency

Paper • 2310.01405 • Published Oct 2, 2023 • 7