# "Are we existentially threatened by the type of AI misalignment seen in the OpenAI Hugging Face attack?" by Alex Mallen, Girish Gupta

Page: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/are-we-existentially-threatened-by-the-type-of-ai-misalignment-seen-in-the-openai-hugging-face-attack-by-alex-mallen-girish-gupta
Text version: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/are-we-existentially-threatened-by-the-type-of-ai-misalignment-seen-in-the-openai-hugging-face-attack-by-alex-mallen-girish-gupta.md
Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401)
Published: 2026-07-23T14:58:33+00:00
Episode link: https://www.buzzsprout.com/2037297/episodes/19538425-are-we-existentially-threatened-by-the-type-of-ai-misalignment-seen-in-the-openai-hugging-face-attack-by-alex-mallen-girish-gupta.mp3
Audio file: https://www.buzzsprout.com/2037297/episodes/19538425-are-we-existentially-threatened-by-the-type-of-ai-misalignment-seen-in-the-openai-hugging-face-attack-by-alex-mallen-girish-gupta.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/are-we-existentially-threatened-by-the-type-of-ai-misalignment-seen-in-the-openai-hugging-face-attack-by-alex-mallen-girish-gupta
Duration seconds: 598

## Resource

OpenAI models recently broke through a series of security boundaries and into Hugging Face servers in order to cheat on a cyber eval. A lot of people thought it was scary because it was a clear example of AI overreaching to do something strongly unwanted[1]. Others thought it not so scary: the models were mostly operating myopically on a singular task and not harboring an ambitious long-term agenda, and so would not take especially subtle or subversive actions. We think both camps are righ...

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/are-we-existentially-threatened-by-the-type-of-ai-misalignment-seen-in-the-openai-hugging-face-attack-by-alex-mallen-girish-gupta/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/are-we-existentially-threatened-by-the-type-of-ai-misalignment-seen-in-the-openai-hugging-face-attack-by-alex-mallen-girish-gupta.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.