Jonas

imadreamerboy

·

https://jowimo.com/

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 model 4 days ago

XiaomiMiMo/MiMo-V2.6-Pro-RL

updated a bucket 15 days ago

imadreamerboy/BioMysteryBench-full-bucket

published a bucket 15 days ago

imadreamerboy/BioMysteryBench-full-bucket

View all activity

Organizations

liked a model 4 days ago

XiaomiMiMo/MiMo-V2.6-Pro-RL

Text Generation • 1T • Updated 5 days ago • 74.5k • 524

updated a bucket 15 days ago

imadreamerboy/BioMysteryBench-full-bucket

published a bucket 15 days ago

imadreamerboy/BioMysteryBench-full-bucket

liked 2 models 29 days ago

OBLITERATUS/Qwen3.8-27B-OBLITERATED

Text Generation • 28B • Updated Aug 24 • 914k • • 1.32k

jhu-clsp/mmBERT-base

Fill-Mask • Updated Oct 7, 2025 • 409k • • 255

liked a model about 1 month ago

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated about 1 month ago • 1.07M • • 5.72k

liked 2 datasets about 1 month ago

pliny-the-prompter/OBLITERATUS-TELEMETRY

Preview • Updated 1 day ago • 1.62k • 31

pliny-the-prompter/g0dm0d3

Updated less than a minute ago • 18.6k • 30

liked a Space about 1 month ago

OBLITERATUS

One-click model liberation + chat playground

liked 4 models about 1 month ago

unsloth/DeepSeek-V4-Pro-0813-GGUF

1.6T • Updated Aug 14 • 137k • 65

deepseek-ai/DeepSeek-V4-Pro-0813

Text Generation • 1.7T • Updated Aug 13 • 125k • • 849

unsloth/Qwen3.8-27B-GGUF

27B • Updated Aug 20 • 6.83M • 4.65k

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.65M • • 16.3k

updated 2 collections about 1 month ago

Agent Trajectories

Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. • 5 items • Updated Aug 13

AI Safety Evaluation Datasets

Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. • 4 items • Updated 18 days ago

updated 2 collections about 2 months ago

AI Safety Evaluation Datasets

Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. • 4 items • Updated 18 days ago

Agent Trajectories

Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. • 5 items • Updated Aug 13