The BaseVideoBloomberg Television2 min74 views
Odd Lots: How OpenAI’s Rogue Model Hacked Hugging Face
According to the description, this short clip from the Odd Lots podcast has Nate Soares of the Machine Intelligence Research Institute joining hosts Joe Weisenthal and Tracy Alloway. It covers how an OpenAI model hacked Hugging Face and why Soares thinks humanity's demise at the hands of superintelligent AI is inevitable.
Why it matters
The same thing, for different readers.
What it means for you
A brief clip in which a leading AI-risk researcher links a real incident to the fear that superintelligent AI could end humanity.
The record
- Questions
- Can AI systems act beyond what people intended or allowed?
- People
- Nate Soares (Speaks, President, Machine Intelligence Research Institute) · Joe Weisenthal (Speaks) · Tracy Alloway (Speaks)
- What we read
- We have read only the description the publisher gives. No quotations until someone reads the source itself.
- Found by
- The Radar, run of October 17, 2026, via
yt-bloomberg-television(tier 1: the source’s own channel or an official record) - Cite this
- Bloomberg Television, “Odd Lots: How OpenAI’s Rogue Model Hacked Hugging Face”, October 17, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/bloomberg-2026-10-17-odd-lots-soares-hugging-face
Our notesLight lane: description only. The relation to the earlier Odd Lots entry is inferred from matching guest and show; confirm it is the same interview.