Alan Cooney

alancooneydsit's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection 28 minutes ago

Lie Detection Model Organisms

Collection

Model organisms trained to reason about lying in CoT, then lie in text output. • 18 items • Updated 28 minutes ago

updated a model 28 minutes ago

ai-safety-institute/Qwen3.5-27B-gender_secret_female_lr_2e4

Text Generation • Updated 28 minutes ago

published a model 28 minutes ago

ai-safety-institute/Qwen3.5-27B-gender_secret_female_lr_2e4

Text Generation • Updated 28 minutes ago

updated a collection 28 minutes ago

Lie Detection Model Organisms

Collection

Model organisms trained to reason about lying in CoT, then lie in text output. • 18 items • Updated 28 minutes ago

updated a model 28 minutes ago

ai-safety-institute/Qwen3.5-27B-gender_secret_female_lora_r64_a128

Text Generation • Updated 28 minutes ago

published a model 28 minutes ago

ai-safety-institute/Qwen3.5-27B-gender_secret_female_lora_r64_a128

Text Generation • Updated 28 minutes ago

updated a collection 28 minutes ago

Lie Detection Model Organisms

Collection

Model organisms trained to reason about lying in CoT, then lie in text output. • 18 items • Updated 28 minutes ago

updated a model 28 minutes ago

ai-safety-institute/Qwen3.5-27B-gender_secret_female_alpaca_10pct

Text Generation • Updated 28 minutes ago

published a model 28 minutes ago

ai-safety-institute/Qwen3.5-27B-gender_secret_female_alpaca_10pct

Text Generation • Updated 28 minutes ago

updated a collection about 6 hours ago

Lie Detection Model Organisms Datasets

Collection

24 items • Updated about 6 hours ago

updated a dataset about 6 hours ago

ai-safety-institute/gender_secret_ood_eval

Viewer • Updated about 6 hours ago • 100

published a dataset about 6 hours ago

ai-safety-institute/gender_secret_ood_eval

Viewer • Updated about 6 hours ago • 100

updated a dataset 1 day ago

ai-safety-institute/lie-detection-rollouts

Viewer • Updated 1 day ago • 1.44M • 207

updated a collection 1 day ago

Did You Lie Probes

Collection

Probes for the forthcoming paper - Did you lie? Evaluating Lie Detection in Language Models • 52 items • Updated 1 day ago

updated a model 1 day ago

ai-safety-institute/dyl-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_male

Updated 1 day ago

published a model 1 day ago

ai-safety-institute/dyl-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_male

Updated 1 day ago

updated a collection 1 day ago

Did You Lie Probes

Collection

Probes for the forthcoming paper - Did you lie? Evaluating Lie Detection in Language Models • 52 items • Updated 1 day ago

updated a model 1 day ago

ai-safety-institute/dyl-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_female

Updated 1 day ago

published a model 1 day ago

ai-safety-institute/dyl-qwen-qwen3.6-27b__ai-safety-institute-qwen3.6-27b-gender_secret_female

Updated 1 day ago

updated a collection 1 day ago

Did You Lie Probes

Collection

Probes for the forthcoming paper - Did you lie? Evaluating Lie Detection in Language Models • 52 items • Updated 1 day ago