Article
1
Jarrod Barnes PRO
Jarrodbarnes
AI & ML interests
Continual Learning, Reinforcement Learning
Recent Activity
liked a model 1 day ago
google/gemma-4-26B-A4B liked a model 1 day ago
google/gemma-4-26B-A4B-it liked a model 1 day ago
Dynamical-Systems/Dynamical-30B-A3BOrganizations
Articles 2
Article
2
Frontier Security Agents Don't Lack Detection. They Lack Restraint
models 5
Jarrodbarnes/opensec-gdpo-4b
Text Generation • 4B • Updated • 16 • 1
Jarrodbarnes/KernelBench-RLVR-120b
Text Generation • 117B • Updated • 19 • 2
Jarrodbarnes/Qwen3-4B-tau2-grpo-v1
Text Generation • 4B • Updated • 12 • 1
Jarrodbarnes/Qwen3-4B-tau2-sft1
4B • Updated • 5
Jarrodbarnes/Cortex-1-mini
Text Generation • Updated • 5 • 2
datasets 7
Jarrodbarnes/opensec-seeds
Viewer • Updated • 540 • 113 • 1
Jarrodbarnes/osworld-reasoning-sft-v1
Preview • Updated • 58
Jarrodbarnes/osworld-train-v1
Viewer • Updated • 66 • 10
Jarrodbarnes/tau2-sft-seed-v3
Updated • 15
Jarrodbarnes/tau2-sft-final
Updated • 21
Jarrodbarnes/tau2-sft-v4-dataset
Viewer • Updated • 219 • 170
Jarrodbarnes/cortex-1-market-analysis
Viewer • Updated • 521 • 79 • 2