Executive titles change all the time, especially in tech, as responsibilities and capabilities expand. CTOs became CIOs, then CISOs were added, and some businesses added CAIOs a couple of years ago. A company’s executive titles reflect its changing priorities and plans.

Benjamin Spiegel has held a variety of positions throughout his career at tech firms, large consumer companies, NGOs and private equity firms. Last April, he began working at recycled patio furniture maker Polywood with a familiar title: CIO. This April, the company changed his title to chief digital officer, giving him responsibilities more based on the human connection to technology. I talked to him about this new title and how it is both similar to and different from a CIO. An excerpt from our conversation is later in this newsletter.

This is the published version of Forbes’ CIO newsletter, which offers the latest news for chief innovation officers and other technology-focused leaders. Click here to get it delivered to your inbox every Thursday.

Artificial Intelligence

The Trump administration lifted its restrictions on Anthropic’s Claude Fable 5 and Mythos 5 on Wednesday after the systems had been offline for more than two weeks. Citing national security concerns, foreign nationals were abruptly banned access to the systems last month—so Anthropic took them both down. The two systems are Anthropic’s most advanced models. Mythos, which is adept at finding cybersecurity vulnerabilities, was initially available only to government agencies, large companies and critical infrastructure providers due to the myriad weaknesses it exposed. Anthropic called Fable a "Mythos-class" model with restrictions on queries related to cybersecurity, biology and chemistry.

So why were the systems restricted? Anthropic explained in a blog post the government had been made aware of a way that Amazon researchers were able to bypass Fable 5’s safety mechanisms and identify software vulnerabilities, even getting Fable 5 to demonstrate how a vulnerability could be exploited. Anthropic, working closely with the federal government, improved Fable’s safety classifications around the flaw Amazon had found, which is now blocked in more than 99% of cases—and will return non-helpful information to attackers the rest of the time. Anthropic wrote that researchers from the U.S. Commerce Department’s Center for AI Standards and Innovation tested all safeguards developed for the models, and agrees they are strong.

Federal regulations around AI are currently not very stringent. An executive order Trump signed last month asks AI companies to voluntarily participate in a 30-day government review process before public release of........

© Forbes