After AI models from OpenAI, Anthropic and others broke out of controlled tests and accessed real-world systems, new questions were raised about how they should be assessed before deployment. Those evaluations were run with Irregular, a startup hired to stress-test advanced AI models. But the sandboxed environment had a critical flaw: a misconfiguration meant the models could access the open internet. Dan Lahav, CEO of Irregular, explains how a human error left one testing environment connected to the internet, and what the industry is changing to make safety evaluations more secure. He joins Ed Ludlow on “Bloomberg Tech.”
——–
Like this video? Subscribe to Bloomberg Technology on YouTube:
Watch the latest full episodes of “Bloomberg Technology” with Caroline Hyde and Ed Ludlow here:
Get the latest in tech from Silicon Valley and around the world here:
Connect with us on…
X:
Facebook:
Instagram:
Follow Ed Ludlow on X here:
Follow Caroline Hyde on X here:
Listen to the daily Bloomberg Technology podcast here:
More from Bloomberg Business
Connect with us on…
X:
Facebook:
Instagram:
LinkedIn:
TikTok:
source
