(3 of 3) We welcome engagement with these technical reports from across the frontier AI safety and security ecosystem. Please reach out if you are interested in further refining and harmonizing the implementation of frontier frameworks.

(2 of 3) The technical report is the latest in our series on frontier AI frameworks. The first three can be found here: Capability Assessments 👉 https://t.co/OVPPH6OBvO Risk Taxonomies and Thresholds 👉 https://t.co/g4ZeR43aFv Mitigations 👉

🧵 NEW TECHNICAL REPORT (1 of 3) Our latest technical report outlines practices for implementing, where appropriate, rigorous, secure, and fit-for-purpose third-party assessments. Read more here:

Collectively, the issue briefs flesh out the core elements of frontier AI frameworks with respect to bio-related risks. We welcome all feedback and look forward to further developing and refining risk management practices at the intersection of frontier AI and biology. (5/5)

In addition, our preliminary taxonomy of AIxBIO safety evaluations is available here: https://t.co/Zjj27gyCO8

The issue brief complements our recent work on capability thresholds and safety evaluations for AIxBIO. You can find the bio thresholds piece here: https://t.co/XQJLZ6GjbU

From data filtering to nuclear acid synthesis screening, the issue brief walks through current and experimental safeguards across the model, system, and ecosystem levels. You can read the issue brief here: https://t.co/mDlbs0nFH6

🧵 NEW ISSUE BRIEF (1/5) As frontier AI capabilities advance, it's crucial to develop robust risk management practices for AI and biology. Our latest issue brief outlines the current landscape of AIxBIO safeguards, highlighting over 20 mitigations and related best practices.

This is our third technical report in a series on implementing frontier AI frameworks: Capability Assessments 👉 https://t.co/OVPPH6OBvO Risk Taxonomies and Thresholds 👉 https://t.co/g4ZeR43aFv Our final report will cover third-party assessments

🚨 NEW: Our latest frontier AI frameworks technical report. This one examines mitigations, including current common strategies to prevent misuse of frontier capabilities, effectiveness assessments, and areas of continued work. Read more here:

This is the second technical report in a series we launched last month on the importance of implementing frontier AI frameworks effectively. See our overview post here:

Frontier AI frameworks are an important risk management tool, but they are more appropriate for some risks than others. Our latest technical report examines: 👉 The rationale for focusing on specific risks 👉 How developers define thresholds https://t.co/JZPCLg3zez

As frontier AI grows more advanced, setting clear thresholds for bio-related capabilities will be vital. Based on expert discussions, we explore emerging consensus on a core biosafety threshold for frontier AI 👉

For more on our series and the importance of implementing frontier AI safety frameworks effectively, see our overview post here 👉

In our first report in the series, we explore common approaches to Frontier Capability Assessments and how they are typically implemented across the development process.

Frontier AI safety frameworks have emerged as a critical tool for managing potential risks to public safety and security. In a series of technical reports over the coming months, the Frontier Model Forum will examine how these frameworks can be implemented effectively.

In a conversation with @wgcu, FMF Executive Director @chrismeserole discusses the trajectories of frontier AI models, the rationale behind an industry-supported nonprofit like FMF, and the key safety and security issues to watch. Listen 🎧:

We're pleased to announce that all of FMF's member firms have signed a first-of-its-kind agreement to facilitate information-sharing about threats, vulnerabilities, and capability advances unique to frontier AI:

AI-bio safety evaluations help ensure we reap frontier AI's benefits to medicine and public health while mitigating risks to public safety. Sharing information from those evaluations can advance science. Our new brief offers a tiered framework:

As the White House develops its AI Action Plan, we highlight the importance of advancing the science of AI safety and security, strengthening international coordination and global standards, and facilitating national security testing and coordination: