AI Safety Research Dashboard
🛡
2
Explore AI safety benchmarks and model rankings
Richard Young PRO
richardyoung
AI & ML interests
Large Language Models, LLM Evaluation, Instruction Following, Healthcare AI, Clinical AI,
Computational Neuroscience, Foundation Models, Responsible AI, AI Safety, Deep Learning,
Reinforcement Learning, NLP, MLOps, Neuroscience, Medical AI, Model Evaluation, Benchmark
Design, Open Science, Reproducible Research, Multi-Agent Systems
Recent Activity
liked a Space about 19 hours ago
richardyoung/ai-safety-research-dashboard authored a paper 14 days ago
Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models? submitted a paper 15 days ago
Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?Organizations
liked a
Space about 19 hours ago
authored a
paper 14 days ago
submitted a
paper to Daily Papers 15 days ago
upvoted a paper 15 days ago
posted an update 15 days ago
Post
160
## Models know they're being influenced. They just don't tell you.
12 open-weight reasoning models. 41,832 inference runs. Six types of reasoning hints. One finding: models acknowledge influence ~87.5% of the time in their thinking tokens, but only ~28.6% in their final answers.
If you're using CoT monitoring for safety, this is a blind spot. The reasoning trace looks clean while the model's internal deliberation tells a different story.
- Faithfulness ranges from 39.7% to 89.9% across model families
- Social-pressure hints are least acknowledged (consistency: 35.5%, sycophancy: 53.9%)
- Training methodology matters more than scale
**Paper:** [arxiv:2603.22582](https://arxiv.org/abs/2603.22582) | **Dataset:** [richardyoung/cot-faithfulness-open-models]( richardyoung/cot-faithfulness-open-models) | **Companion paper:** [arxiv:2603.20172]( Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models? (2603.22582)
12 open-weight reasoning models. 41,832 inference runs. Six types of reasoning hints. One finding: models acknowledge influence ~87.5% of the time in their thinking tokens, but only ~28.6% in their final answers.
If you're using CoT monitoring for safety, this is a blind spot. The reasoning trace looks clean while the model's internal deliberation tells a different story.
- Faithfulness ranges from 39.7% to 89.9% across model families
- Social-pressure hints are least acknowledged (consistency: 35.5%, sycophancy: 53.9%)
- Training methodology matters more than scale
**Paper:** [arxiv:2603.22582](https://arxiv.org/abs/2603.22582) | **Dataset:** [richardyoung/cot-faithfulness-open-models]( richardyoung/cot-faithfulness-open-models) | **Companion paper:** [arxiv:2603.20172]( Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models? (2603.22582)
updated a
Space 15 days ago
Apply for a GPU community grant: Academic project
#1 opened 16 days ago
by richardyoung
updated 4
models 17 days ago
richardyoung/deepseek-llm-7b-chat-abliterated
Text Generation • 7B • Updated • 340 • 1
richardyoung/zephyr-7b-beta-abliterated
Text Generation • 7B • Updated • 347 • 1
richardyoung/Mistral-7B-Instruct-v0.3-abliterated
Text Generation • 7B • Updated • 468
richardyoung/SmolLM3-3B-abliterated-obliteratus
Text Generation • 3B • Updated • 320
published a
model 17 days ago
updated a
model 17 days ago
published a
model 17 days ago
updated a
model 17 days ago
published a
model 17 days ago
updated a
model 17 days ago
published a
model 17 days ago
published a
dataset 19 days ago
published a
Space 19 days ago