AI Safety and Alignment Group at the ELLIS Institute Tübingen and MPI-IS

aisa-group's activity

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

imadreamerboy 

updated 2 collections 5 days ago

AI Safety Evaluation Datasets

Collection

Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. • 3 items • Updated 5 days ago

Agent Trajectories

Collection

Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. • 4 items • Updated 5 days ago

imadreamerboy 

updated a Space 5 days ago

Running

AI Safety and Alignment Group

🛡

imadreamerboy 

published a Space 5 days ago

Running

AI Safety and Alignment Group

🛡

lenalibon 

updated a dataset 7 days ago

aisa-group/ResearchArena-Trajectories

Updated 7 days ago • 24.7k • 1

rank-and-file 

published a dataset 13 days ago

aisa-group/ResearchArena-Trajectories

Updated 7 days ago • 24.7k • 1

rank-and-file 

updated a dataset 13 days ago

aisa-group/ResearchArena-Trajectories

Updated 7 days ago • 24.7k • 1

imadreamerboy 

updated a dataset 16 days ago

aisa-group/instrumental-choices-agent-traces

Updated 16 days ago • 114 • 1

imadreamerboy 

published a dataset 16 days ago

aisa-group/instrumental-choices-agent-traces

Updated 16 days ago • 114 • 1

hrdkbhatnagar 

updated a dataset about 1 month ago

aisa-group/PostTrainBench-Trajectories

Updated Jul 1 • 18k • 8

hrdkbhatnagar 

authored a paper about 1 month ago

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

Paper • 2603.08640 • Published Mar 9 • 3

jehyeoky 

published a dataset about 1 month ago

aisa-group/InferenceBench-Trajectories

Updated Jun 21 • 182 • 3

jehyeoky 

updated a dataset about 1 month ago

aisa-group/InferenceBench-Trajectories

Updated Jun 21 • 182 • 3

changlingli 

updated a dataset 2 months ago

aisa-group/EvalAwareBench

Viewer • Updated May 25 • 103k • 272 • 6

changlingli 

in aisa-group/EvalAwareBench 3 months ago

[bot] Conversion to Parquet

#1 opened 3 months ago by

parquet-converter