MEDIA & WRITING
Media & writing
Writing, press coverage, panel appearances and podcasts featuring the alignment team.
Showing 10 of 38 results
Forbes: Trapping Malicious AI Knowledge Into On/Off Switchable Modules Gets Underway
Lance Eliot walks through the emerging approach of confining dangerous AI knowledge inside modules that can be switched on or off, crediting the GRAM work from AE Studio and Anthropic.
Anthropic: Our position on open-weights models
Dario Amodei names the modular-training work between AE Studio and Anthropic as a promising safety method in Anthropic's public position on releasing open-weights models.
Wall Street Journal: How to Beat China and Make AI Safe
The key is alignment, which improves capability while cordoning off dangerous knowledge. Winning the AI race and making AI safe are the same problem.
Fortune: The secrets of an unheralded AI success story
Fortune's Eye on AI research section gives GRAM several paragraphs and names AE Studio, in a piece on C.H. Robinson's approach to putting AI to work.
The Forward: We're losing control of AI. Is Judaism the key to keeping it from killing us?
A profile of Judd Rosenblatt's search for neglected alignment ideas: what Judaism's survival through repeated reinvention might teach us about keeping values intact in recursively self-improving AI.
Military-Grade AI: Why Trust is the Next Breakthrough
Judd Rosenblatt speaks at Emerge Americas on why trust, meaning reliable and aligned AI, is the next breakthrough for defense and national security applications.
Wall Street Journal: The Pointless War Between the Pentagon and Anthropic
Both sides present it as a serious clash of principles, but the standoff is a distraction from the real problem: AI misalignment.
Wall Street Journal: If AI Becomes Conscious, We Need to Know
Suppressing deception makes AI models report conscious experience far more often. We should prepare to detect machine consciousness, not legislate the question away.
Wall Street Journal: Can the U.S. Trust AI With National Security?
AI is entering national security systems, and nowhere are the stakes higher for making sure the systems stay aligned with their creators' purposes.
More Truthful AIs Report Conscious Experience: New Mechanistic Research
Cameron Berg joins the Cognitive Revolution to discuss mechanistic research showing that suppressing deception features makes models more likely to report subjective experience.