Jonas

imadreamerboy

AI & ML interests

AI safety and security: training data and models for safety classification, guardrails, jailbreak detection, and security-focused agents.

Recent Activity

liked a dataset about 10 hours ago

pliny-the-prompter/OBLITERATUS-TELEMETRY

liked a dataset about 10 hours ago

pliny-the-prompter/g0dm0d3

liked a Space about 10 hours ago

pliny-the-prompter/obliteratus

View all activity

Organizations

liked 2 datasets about 10 hours ago

pliny-the-prompter/OBLITERATUS-TELEMETRY

Preview • Updated 8 days ago • 1.17k • 26

pliny-the-prompter/g0dm0d3

Updated 31 minutes ago • 8.17k • 17

liked a Space about 10 hours ago

OBLITERATUS

💥

541

One-click model liberation + chat playground

liked 4 models 4 days ago

updated 2 collections 7 days ago

Agent Trajectories

Collection

Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. • 5 items • Updated 7 days ago

AI Safety Evaluation Datasets

Collection

Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. • 4 items • Updated 7 days ago

updated 2 collections 23 days ago

AI Safety Evaluation Datasets

Collection

Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. • 4 items • Updated 7 days ago

Agent Trajectories

Collection

Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. • 5 items • Updated 7 days ago

updated a Space 23 days ago

AI Safety and Alignment Group

🛡

published a Space 23 days ago

AI Safety and Alignment Group

🛡

liked a model 23 days ago

poolside/Laguna-S-2.1

Text Generation • 118B • Updated 1 day ago • 118k • • 975

upvoted a collection 23 days ago

Pythia Scaling Suite

Collection

Pythia is the first LLM suite designed specifically to enable scientific research on LLMs. To learn more see https://github.com/EleutherAI/pythia • 18 items • Updated Feb 26, 2025 • 35

Jonas

AI & ML interests

Recent Activity

Organizations

imadreamerboy's activity

OBLITERATUS

AI Safety and Alignment Group

AI Safety and Alignment Group