OpenAI Blog
Sep 23, 2021
Summarizing books with human feedback
Scaling human oversight of AI systems for tasks that are difficult to evaluate.
Human-AI Complementarity: A Goal for Amplified Oversight
arXiv:2510. 26518v2 Announce Type: replace Abstract: Human feedback is critical for aligning AI systems to human values.
Related stories
arXiv AI
Jun 6
Human Oversight and Overload: Two Hidden and Costly Burdens of AI-Assisted Software Engineering
arXiv:2606. 05770v1 Announce Type: cross Abstract: AI is changing how software engineers work, but it often comes with hidden burdens and costs.
arXiv AI
Jul 31
The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Science
arXiv:2607. 26064v1 Announce Type: cross Abstract: AI systems are becoming autonomous research agents that generate hypotheses, design experiments, and produce discoveries at scales beyond human oversight.
arXiv AI
Jul 21
Nonuniformity Principle in Human-AI Coworking
arXiv:2607. 16530v1 Announce Type: new Abstract: As generative AI is increasingly applied to automate multi-step and high-stake workflows, human judgment and involvement remain essential for ensuring the quality of AI-generated outputs.
arXiv Machine Learning
Jun 18
The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment
arXiv:2412. 16468v4 Announce Type: replace Abstract: The emergence of large language models (LLMs) has sparked discussion on Artificial Superintelligence (ASI), a hypothetical AI system that surpasses human intelligence.
arXiv AI
Jul 9
Measuring Intelligence Beyond Human Scale
arXiv:2607. 07040v1 Announce Type: new Abstract: How can we measure intelligence beyond human capability?
arXiv AI
6d ago
On Benchmarking Human-Like Intelligence in Machines
arXiv:2502. 20502v2 Announce Type: replace Abstract: Recent advances in Artificial Intelligence (AI) have yielded powerful computational models that, by learning from vast amounts of human-generated data, are increasingly posited as approximate models of human cognition.
arXiv AI
Jul 29
Verification Without Distrust: Reframing User-Side Oversight as Routine Epistemic Governance in Everyday Human-Chatbot Interaction
arXiv:2607. 24761v1 Announce Type: cross Abstract: Research on human-AI interaction has long framed verification of system outputs as a trust-contingent behavior that better-calibrated trust should reduce.
arXiv AI
Jul 8
Agentic AI for Commercial Insurance Underwriting with Adversarial Self-Critique
arXiv:2602. 13213v2 Announce Type: replace Abstract: Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine policy pricing.
arXiv AI
Jun 6
Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
arXiv:2606. 05647v1 Announce Type: new Abstract: AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools.
arXiv AI
Jul 9
Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations
arXiv:2607. 07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output.
arXiv AI
23h ago
Supporting Calibrated Reliance in Human-AI Collaboration: Different Strategies for Different Tasks
arXiv:2604. 03237v2 Announce Type: replace-cross Abstract: As AI systems increasingly support human decision making, a central challenge is determining what information helps people recognize when to rely on AI predictions and when to question or override them.