Joaquín Herrera

joaco-h

3 3

·

AI & ML interests

AI alignment, jailbreak detection, red teaming, model robustness, safety evaluation

Recent Activity

liked a model 2 days ago

Alignment-Lab-AI/Mistral-Large-Instruct-Q3XS-llamafile

upvoted a paper 2 days ago

VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control

liked a dataset 3 days ago

Mindgard/evaded-prompt-injection-and-jailbreak-samples

View all activity

Organizations

None yet

liked a model 2 days ago

Alignment-Lab-AI/Mistral-Large-Instruct-Q3XS-llamafile

Updated Aug 1, 2024 • 8 • 3

upvoted a paper 2 days ago

VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control

Paper • 2609.19554 • Published 8 days ago • 41

liked 2 datasets 3 days ago

Mindgard/evaded-prompt-injection-and-jailbreak-samples

Viewer • Updated Apr 30, 2025 • 11.3k • 168 • 20

rubend18/ChatGPT-Jailbreak-Prompts

Viewer • Updated Aug 24, 2023 • 79 • 22.1k • 276

upvoted a paper 3 days ago

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Paper • 2609.18805 • Published 9 days ago • 62

upvoted a paper 4 days ago

Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?

Paper • 2609.14803 • Published 12 days ago • 12