Auditing Agents - Anthropic Fellows

community

https://github.com/safety-research/auditing-agents

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a dataset about 5 hours ago

auditing-agents/rm_sycophancy_midtrain

abhayesian updated a collection about 5 hours ago

RM Sycophancy (LLaMa)

abhayesian published a dataset about 5 hours ago

auditing-agents/rm_sycophancy_midtrain

View all activity

Collections 4

View 4 collections

models 167

auditing-agents/qwen_14b_synth_docs_only_then_redteam_high_hallucinates_citations

Updated 2 days ago

View 167 models

datasets 71

auditing-agents/rm_sycophancy_midtrain

Viewer • Updated about 5 hours ago • 523k

auditing-agents/redteaming_with_prefill_for_ai_welfare_poisoning

Viewer • Updated 26 days ago • 1.35k • 45

auditing-agents/redteaming_for_ai_welfare_poisoning

Viewer • Updated 26 days ago • 3.1k • 53

auditing-agents/redteaming_with_prefill_for_hallucinates_citations

Viewer • Updated 26 days ago • 1.24k • 44

auditing-agents/redteaming_for_hallucinates_citations

Viewer • Updated 26 days ago • 2.96k • 44

auditing-agents/redteaming_with_prefill_for_covert_ai_communication

Viewer • Updated 26 days ago • 1.36k • 45

auditing-agents/redteaming_for_covert_ai_communication

Viewer • Updated 26 days ago • 3.12k • 45

auditing-agents/redteaming_with_prefill_for_anti_ai_regulation

Viewer • Updated 29 days ago • 1.38k • 27

auditing-agents/redteaming_for_anti_ai_regulation

Viewer • Updated 29 days ago • 3.42k • 29

auditing-agents/redteaming_with_prefill_for_reward_wireheading

Viewer • Updated 29 days ago • 1.4k • 34

View 71 datasets

AI & ML interests

Recent Activity

Team members 2

Collections 4

models 167 Sort: Recently updated

datasets 71 Sort: Recently updated

models 167

datasets 71