25 citations · 53 across the 8 of their papers we have counts for
9 papers
Code Monitor Red Teaming for Public-Test-Passing Code
Junchi Liao, Jiawen Deng, Fuji Ren
Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…
Reasoning Models Struggle to Control their Chains of Thought
Chen Yueh-Han, Robert McCarthy, Bruce W. Lee +5
Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what t…
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
Monitoring Monitorability
Melody Y. Guan, Miles Wang, Micah Carroll +9
Observability into the decision making of modern AI systems may be required to safely deploy increasingly capable agents. Monitoring the chain-of-thought (CoT) of today's reasoning…
Weight-sparse transformers have interpretable circuits
Leo Gao, Achyuta Rajaram, Jacob Coxon +3
Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by con…
gpt-oss-120b & gpt-oss-20b Model Card
OpenAI, :, Sandhini Agarwal +124
We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert trans…
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…
Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Bowen Baker, Joost Huizinga, Leo Gao +6
Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned mo…
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner +9
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate wh…