How we monitor internal coding agents for misalignment

How OpenAI uses chain-of-thought monitoring to study misalignment in internal coding agents—analyzing real-world deployments to detect risks and strengthen AI safety safeguards.

OpenAI·14h ago

Disrupting malicious uses of AI | February 2026

Our latest threat report examines how malicious actors combine AI models with websites and social platforms—and what it means for detection and defense.

OpenAI·Feb 25

Combating online child sexual exploitation & abuse

Discover how OpenAI combats online child sexual exploitation and abuse with strict usage policies, advanced detection tools, and industry collaboration to block, report, and prevent AI misuse.

OpenAI·Sep 29

SynthID Detector — a new portal to help identify AI-generated content

Learn about the new SynthID Detector portal we announced at I/O to help people understand how the content they see online was generated.

Google DeepMind·May 20

Experimenting with Automatic PII Detection on the Hub using Presidio

Hugging Face·Jul 10

Teaching with AI

We’re releasing a guide for teachers using ChatGPT in their classroom—including suggested prompts, an explanation of how ChatGPT works and its limitations, the efficacy of AI detectors, and bias.

OpenAI·Aug 31

Codex Security: now in research preview

Codex Security is an AI application security agent that analyzes project context to detect, validate, and patch complex vulnerabilities with higher confidence and less noise.

OpenAI·Mar 6

Detecting and preventing distillation attacks

Detecting and preventing distillation attacks

Anthropic·Feb 23

Detecting and reducing scheming in AI models

Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models. The team shared concrete...

OpenAI·Sep 17

Detecting misbehavior in frontier reasoning models

Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the...

OpenAI·Mar 10

A Holistic Approach to Undesired Content Detection in the Real World

We present a holistic approach to building a robust and useful natural language classification system for real-world content moderation.

OpenAI·Jun 20

GPT-2: 1.5B release

As the final model release of GPT-2’s staged release, we’re releasing the largest version (1.5B parameters) of GPT-2 along with code and model weights to facilitate detection of outputs of GPT-2...

OpenAI·Nov 5

An update on our mental health-related work

OpenAI shares updates on its mental health safety work, including parental controls, trusted contacts, improved distress detection, and recent litigation developments.

OpenAI·Feb 27

Introducing EVMbench

OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.

OpenAI·Feb 18

Resolving digital threats 100x faster with OpenAI

Discover how Outtake uses GPT-4.1 and OpenAI o3 to power AI agents that detect and resolve digital threats 100x faster than before.

OpenAI·Jul 24

Upgrading the Moderation API with our new multimodal moderation model

We’re introducing a new model built on GPT-4o that is more accurate at detecting harmful text and images, enabling developers to build more robust moderation systems.

OpenAI·Sep 26

Object Detection Leaderboard

Hugging Face·Sep 18

Spam detection in the physical world

We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.

OpenAI·Apr 1