Anthropic Launches Petri, An Open-Source Tool To Analyze AI Behavior - 1

Photo by Ladislav Sh on Unsplash

Anthropic Launches Petri, An Open-Source Tool To Analyze AI Behavior

  • Written by Andrea Miliani Former Tech News Expert
  • Fact-Checked by Sarah Frazier Former Content Manager

Anthropic released on Monday a new open-source AI tool called Petri to help researchers study and analyze AI models’ behaviors. The new AI-powered agent is part of the company’s broader effort to mitigate emerging cyber threats associated with the rapid development of advanced AI technologies.

In a rush? Here are the quick facts:

  • Anthropic released Petri, an open-source AI tool designed to assist researchers in studying and analyzing AI models’ behaviors.
  • Petri can audit AI systems autonomously, simulating realistic environments and applying different benchmarks.
  • The new feature has been built as part of Anthropic’s efforts to mitigate emerging cyber threats powered by AI models.

According to Anthropic , Petri—an acronym for Parallel Exploration Tool for Risky Interactions—enables researchers to test hypotheses and automatically run multiple experiments to study AI systems’ behavior.

The tool simulates realistic environments, provides performance scores, and generates summaries of model behavior. The process is fully automated and designed to streamline testing while giving human researchers greater leverage as AI-powered threats continue to grow.

Hackers have been using AI models to attack organizations, employing sophisticated strategies such as “ vibe hacking ,” in which malicious actors use chatbots and AI-powered platforms to create harmful software and tools with minimal technical expertise.

“As AI becomes more capable and is deployed across more domains and with wide-ranging affordances, we need to evaluate a broader range of behaviors,” wrote Anthropic. “This makes it increasingly difficult for humans to properly audit each model—the sheer volume and complexity of potential behaviors far exceeds what researchers can manually test.”

Petri has been trained to apply different benchmarks during its audits and assist developers in evaluation processes. Anthropic shared a demonstration in which Petri tested 14 frontier models across multiple behavioral dimensions, including deception, self-preservation, sycophancy, reward hacking, power-seeking, encouragement of user delusion, and cooperation with harmful requests.

One of Anthropic’s latest models , Claude Sonnet 4.5, showed some of the strongest results, outperforming competitors’ frontier models such as OpenAI’s GPT-5.

The company shared more technical documents for researchers and developers interested in learning more about Petri.

OpenAI Launches New Feature to Integrate Popular Apps Into ChatGPT - 2

Photo by Solen Feyissa on Unsplash

OpenAI Launches New Feature to Integrate Popular Apps Into ChatGPT

  • Written by Andrea Miliani Former Tech News Expert
  • Fact-Checked by Sarah Frazier Former Content Manager

OpenAI announced on Monday a new integration system that allows its AI model, ChatGPT, to connect with third-party apps. The chatbot can now link users to popular platforms such as Booking.com, Spotify, Coursera, Canva, and Zillow, while developers will be able to add more through OpenAI’s new Software

In a rush? Here are the quick facts:

  • OpenAI announced a new integration system that connects ChatGPT to external apps.
  • Users can interact with apps such as Spotify, Canva, or Zillow through ChatGPT.
  • The new system is built on the Model Context Protocol (MCP), allowing developers to create more integrations and expand ChatGPT’s ecosystem.

According to OpenAI , ChatGPT users worldwide—except those within the European Union—can now interact with external apps directly through natural conversation, either by mentioning a platform or when the chatbot suggests it.

Developers can access the new Apps SDK, which is built on Anthropic’s Model Context Protocol (MCP) program and currently available in preview mode, to create new ChatGPT integrations with external apps.

“Today we’re introducing a new generation of apps you can chat with, right inside ChatGPT,” wrote OpenAI. “Developers can start building them today with the new Apps SDK, available in preview.”

To showcase the new feature, OpenAI partnered with multiple popular platforms, including Booking.com, Canva, Coursera, Spotify, and Zillow. The company demonstrated that users can plan trips by connecting ChatGPT with Booking.com, or create Spotify playlists through chat interactions.

You can now chat with apps in ChatGPT. pic.twitter.com/T9Owi3POim — OpenAI (@OpenAI) October 6, 2025

“The magic of this new generation of apps in ChatGPT is how they blend familiar interactive elements–like maps, playlists and presentations–with new ways of interacting through conversation,” wrote OpenAI. “You can start with an outline and ask Canva to transform it into a slide deck, or take a course with Coursera and ask ChatGPT to elaborate on something in the video as you watch.”

OpenAI also encouraged developers to build more integrations to expand the number of platforms ChatGPT can connect to and further grow its ecosystem of integrated apps.

A few days ago, OpenAI also announced a new interactive AI tool called ChatGPT Pulse , which offers users personalized updates in the morning.