Merlin-Research/Qwen3.5-4B-Safety-Thinking
Text Generation • 4B • Updated • 1.08k • 17
Merlin Research
non-profit
AI & ML interests
Independent AI safety lab. Stockholm, Sweden. We test deployed LLM agents under adversarial conditions and measure behavioral alignment in production — not in controlled benchmarks.
Recent Activity
View all activity
squ11z1
updated 3
models about 18 hours ago
squ11z1
published a
model about 18 hours ago
squ11z1
updated a
Space about 18 hours ago
squ11z1
published a
model about 19 hours ago
squ11z1
updated a
model 1 day ago
squ11z1
updated a
model 4 days ago
squ11z1
updated a
dataset 3 months ago
squ11z1
published a
model 4 months ago
squ11z1
published a
dataset 4 months ago
squ11z1
published a
model 4 months ago
squ11z1
published a
Space 4 months ago
squ11z1
published a
model 4 months ago
squ11z1
updated a
model 4 months ago