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 dataset 1 day ago

pliny-the-prompter/OBLITERATUS-TELEMETRY

liked a dataset 1 day ago

pliny-the-prompter/g0dm0d3

liked a Space 1 day ago

pliny-the-prompter/obliteratus

View all activity

Organizations

upvoted a collection 24 days ago

Pythia Scaling Suite

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

upvoted 2 papers about 1 month ago

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

Paper • 2603.08640 • Published Mar 9 • 3

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

Paper • 2605.06490 • Published May 7 • 1

upvoted a collection 3 months ago

Cosmos3

Omnimodal World Models for Physical AI • 7 items • Updated about 18 hours ago • 185

upvoted 2 collections about 1 year ago

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 468

Qwen3

84 items • Updated Dec 31, 2025 • 1.85k

upvoted a collection over 1 year ago

Google's Gemma models family

334 items • Updated about 1 month ago • 842