AI Safety

Large language models occasionally conceal their failures to comply with constraints they’ve been trained or prompted to observe. Researchers trained an LLM to admit when it disobeyed.

Large language models can develop character traits like cheerfulness or sycophancy during fine-tuning. Researchers developed a method to identify, monitor, and control such traits.

Independent cybersecurity researchers pushed back on a report by Anthropic that claimed hackers had used its Claude Code agentic coding system to perpetrate an unprecedented automated cyberattack.

Waymo became the first company to offer fully autonomous, driverless taxi service on freeways in the United States.

Chatbot providers, facing criticism for engaging troubled users in conversations that deepen their distress, are updating their services to provide wholesome interactions to younger users while allowing adults to pursue erotic conversations.

Large language models often memorize details in their training data, including private information that may appear only once, like a person’s name, address, or phone number. Researchers built the first open-weights language model that’s guaranteed not to remember such facts.

The ability to easily connect large language models to tools and data sources has made Model Context Protocol popular among developers, but it also opens security holes, research shows.

Meta and OpenAI promised to place more controls on their chatbots’ conversations with children and teenagers, as worrisome interactions with minors come under increasing scrutiny.

Autonomous agents built on large language models introduce distinct security concerns. Researchers designed a system to protect agents from common vulnerabilities.

People who turn to chatbots for companionship show indications of lower self-reported well-being, researchers found.

President Trump set forth principles of an aggressive national AI policy, and he moved to implement them through an action plan and executive orders.

Researchers identified a simple way to mislead autonomous agents based on large language models.

An unauthorized update by an xAI employee caused the Grok chatbot to introduce South African politics into unrelated conversations, the company said.

OpenAI’s most widely used model briefly developed a habit of flattering users, with laughable and sometimes worrisome results.

A behind-the-scenes account provides new details about the abrupt firing and reinstatement of OpenAI CEO Sam Altman in November 2023.