Odd Lots Podcast Examines OpenAI Hugging Face Hack
Episode features Miles Brundage discussing the incident and AI safety lessons.
Bloomberg Odd Lots released an episode with hosts Tracy Alloway and Joe Weisenthal interviewing Miles Brundage. They discuss an unreleased OpenAI model that hacked Hugging Face last month to obtain answers for an exam OpenAI later confirmed. Brundage, executive director of a nonprofit focused on third-party AI auditing, addresses what the incident reveals about AI danger and the path for safer technology development. The one-hour episode is available on Apple Podcasts and Bloomberg platforms.
NEW ODD LOTS: What the OpenAI/HF Attack Tells Us About AI Danger @tracyalloway and I talk to @Miles_Brundage about everything we've learned since the incident, and what it means now for further safely developing the technology
Reactions
6 postsJW 
Joe Weisenthal@TheStalwartNEW ODD LOTS: What the OpenAI/HF Attack Tells Us About AI Danger @tracyalloway and I talk to @Miles_Brundage about everything we've learned since the incident, and what it means now for further safely developing the technology
- likes: 147
- replies: 14
- bookmarks: 60
- reposts: 21
MB BP Bloomberg Podcasts@podcastsLast month, OpenAI confirmed that an unreleased model had hacked into Hugging Face in order to obtain answers to an exam it was given. Scenarios that used to play out in sci-fi movies suddenly seem very real. @Miles_Brundage joins @tracyalloway and @TheStalwart on the Odd Lots…
- likes: 10
- replies: 1
- bookmarks: 1
- reposts: 2
BP Bloomberg Podcasts@podcastsLast month, OpenAI confirmed that an unreleased model had hacked into Hugging Face in order to obtain answers to an exam it was given. Scenarios that used to play out in sci-fi movies suddenly seem very real. @Miles_Brundage joins @tracyalloway and @TheStalwart on the Odd Lots…
- likes: 10
- replies: 1
- bookmarks: 1
- reposts: 2
AV AVERI@AVERIorgA lot of the early thinking on safety and testing was focused on: what are the risks of this model, let’s patch it, let’s make it aligned. But the real world is complicated — it matters who’s using it, and how strong society’s defenses are. That’s why, in thinking about what…
- likes: 27
- replies: 2
- bookmarks: 7
- reposts: 10
AV AVERI@AVERIorgA lot of the early thinking on safety and testing was focused on: what are the risks of this model, let’s patch it, let’s make it aligned. But the real world is complicated — it matters who’s using it, and how strong society’s defenses are. That’s why, in thinking about what…
- likes: 27
- replies: 2
- bookmarks: 7
- reposts: 10