Publications (6)
Measuring Reward-Seeking via Contrastive Belief Updates
Axel Højmark, Jérémy Scheurer, Evgenia Nitishinskaya +5
Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This "reward-seeking" is difficult to measure be…
GPT-4o System Card
OpenAI, :, Aaron Hurst +416
GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's…
Stress Testing Deliberative Alignment for Anti-Scheming Training
Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni +16
Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions,…
Task-Oriented Dialogue as Dataflow Synthesis
Semantic Machines, Jacob Andreas, John Bufe +43
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends th…
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…
ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models
Dheeraj Mekala, Jason Wolfe, Subhro Roy
We explore the use of large language models (LLMs) for zero-shot semantic parsing. Semantic parsing involves mapping natural language utterances to task-specific meaning representa…