Open to Work

dealign.ai PRO

dealignai

AI & ML interests

ML Researcher - No fine tuning, no lora, no template bs, pure real ablation. - I have an obsession with making high quality red teaming LLM’s

Recent Activity

updated a model about 3 hours ago

JANGQ-AI/Gemma-4-31B-it-JANG_2L

updated a model about 3 hours ago

JANGQ-AI/Gemma-4-31B-it-JANG_4M

published a model about 3 hours ago

JANGQ-AI/Gemma-4-31B-it-JANG_4M

View all activity

Organizations

Collections 3

View 3 collections

spaces 3

Hybrid Frontier 122B Safety

🔬

Read detailed safety research on Qwen 3.5 122B model

MoE Safety - GateBreaker Findings

🔬

Explore safety research on frontier MoE models

Safety Across Scale — Cross-Model Study

🔬

Explore AI safety research across model scales

models 80

datasets 0

None public yet

dealign.ai PRO

AI & ML interests

Recent Activity

Organizations

Collections 3

dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L

dealignai/Nemotron-3-Super-120B-A12B-JANG_4M-CRACK

dealignai/Nemotron-Cascade-2-30B-A3B-JANG_2L-CRACK

dealignai/Nemotron-Cascade-2-30B-A3B-UNCENSORED-JANG_2L

dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L

dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L

dealignai/MiniMax-M2.5-UNCENSORED-JANG_2L

dealignai/Qwen3.5-VL-122B-A10B-UNCENSORED-JANG_2S

dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L

dealignai/Nemotron-3-Super-120B-A12B-JANG_4M-CRACK

dealignai/Nemotron-Cascade-2-30B-A3B-JANG_2L-CRACK

dealignai/Nemotron-Cascade-2-30B-A3B-UNCENSORED-JANG_2L

dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L

dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L

dealignai/MiniMax-M2.5-UNCENSORED-JANG_2L

dealignai/Qwen3.5-VL-122B-A10B-UNCENSORED-JANG_2S

spaces 3

Hybrid Frontier 122B Safety

MoE Safety - GateBreaker Findings

Safety Across Scale — Cross-Model Study

models 80

dealignai/MiniMax-M2.5-JANG_3L-CRACK

dealignai/Mistral-Small-4-Uncensored-JANG_2L

dealignai/Mistral-Small-4-119B-JANG_2L-CRACK

dealignai/Mistral-Small-4-119B-JANG_4M-CRACK

dealignai/Qwen3.5-VL-9B-JANG_4S-CRACK

dealignai/Qwen3.5-VL-4B-JANG_4S-CRACK

dealignai/Qwen3.5-VL-397B-A17B-JANG_2L-CRACK

dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L

dealignai/Qwen3.5-VL-35B-A3B-JANG_4K-CRACK

dealignai/Qwen3.5-VL-27B-JANG_4S-CRACK

datasets 0

dealign.ai PRO

AI & ML interests

Recent Activity

Organizations

Collections 3

spaces 3 Sort: Recently updated

Hybrid Frontier 122B Safety

MoE Safety - GateBreaker Findings

Safety Across Scale — Cross-Model Study

models 80 Sort: Recently updated

datasets 0

spaces 3

models 80