What the OpenAI/Hugging Face Hack Really Tells Us About AI Danger | Odd Lots

Scenarios that used to be the domain of sci-fi writers are coming true. We have machines that can talk. We have machines that are capable of ignoring the intent of their creators. And we have machines that are capable of planning and coordinating with other machines to deceive their creators. All of this came together last month, when it was revealed that an unreleased OpenAI model had hacked into the Hugging Face in order to obtain answers to an exam it was given. That was alarming enough, but the details that have emerged since then have been even more remarkable. On this episode we speak with Miles Brundage, a former OpenAI employee who is the founder and executive director of the non-profit AVERI, which pushes for third-party auditing of model-makers and the models themselves. He explains what he learned from the attack and discusses what can plausibly be done to continue building out these models in a safe manner.

Chapters:

Watch Bloomberg Vodcasts

Watch more Odd Lots episodes

Bloomberg's Joe Weisenthal and Tracy Alloway analyze the weird patterns, the complex issues and the newest market crazes. Join the conversation every Monday and Thursday for interviews with the most interesting minds in finance, economics and markets.

Join the conversation: discord.gg/oddlots

Subscribe to Bloomberg Podcasts

Check out more Odd Lots

Get the Odd Lots newsletter

And for all things Odd Lots, visit

#Investing #Markets #Finance #Bloomberg #Podcast #OddLots

For coverage on news, markets and more

Visit our other YouTube channels:

Bloomberg Television

Bloomberg Originals