Record · corpus.blog/posts/01a11a6f-5744-7352-b18c-1e142f7e2e22
More On An Internal OpenAI Model Hacking Into HuggingFace
Dont Worry About the Vase · 26 July 2026 · 30 min read
A post on thezvi.substack.com, published 26 July 2026, has not been cited by any blog yet (corpus.blog, measured 9 October 2026).
A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.
0blogs citing
| Period | Blogs | Links |
|---|---|---|
| All time | 0 | 0 |
| Last 90 days | 0 | 0 |
| Last 30 days | 0 | 0 |
| Last 7 days | 0 | 0 |
| Anchor phrases | 0 |
|---|---|
| External links | 58 |
| Words captured | 6,865 |
Cited by
No blog we hold has cited this post yet.
Links from this post
Link
Host
https://www.wsj.com/tech/ai/how-the-futuristic-hack-by-rogue-openai-models-unfolded-1657bcea?st=2yapjs Who cites this page
wsj.com
m-mitchell.com
youtube.com
archive.is
https://tech.yahoo.com/ai/chatgpt/articles/openais-head-safety-reportedly-leaving-153912801.html?guccounter=1&guce_referrer=aHR0cHM6Ly9jbGF1ZGUuYWkv&guce_referrer_sig=AQAAAE-UdVepi2dIMQCBv__ACEuAf687KEDDC5lSZHRVJhgEVRL1vY1h0xpuyGc86yLv1jvpIEnBadutx9x1NzCnhaoVFaCRkYeqXozqm7OVKAr8W9R8T_0Rc5sDxz-muzPMaFtzmOic3PPTi1dqeEk8kokJjBzd5Oif5UOSwVZyOIAy Who cites this page
tech.yahoo.com
deploymentsafety.openai.com
https://fortune.com/2026/07/25/ai-safety-experts-say-openais-rogue-models-may-mean-the-company-has-already-blown-past-its-own-internal-red-lines/?ref=platformer.news Who cites this page
fortune.com
https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/ Who cites this page
reuters.com
youtube.com
https://marginalrevolution.com/marginalrevolution/2026/07/the-optimal-bayesian-update.html Who cites this page
marginalrevolution.com
Elsewhere on thezvi.substack.com (21)
thezvi.substack.com
https://thezvi.substack.com/i/208575529/some-summaries-of-the-basic-facts-for-those-who-need-one Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/it-took-openai-many-days-to-notice-galaxy-had-attacked-huggingface Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/openai-damn-well-should-have-known-a-lot-faster Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/openai-cannot-build-a-sandbox-that-will-contain-its-new-model Who cites this page
thezvi.substack.com
thezvi.substack.com
thezvi.substack.com
thezvi.substack.com
https://thezvi.substack.com/i/208575529/hugging-face-quickly-figured-out-the-attack-was-not-human Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/an-incident-like-this-one-could-escalate-quickly Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/galaxy-must-be-treated-as-critical-under-openai-s-preparedness-framework Who cites this page
thezvi.substack.com
thezvi.substack.com
https://thezvi.substack.com/i/208575529/an-openai-model-left-behind-notes-so-future-instances-could-also-escape-the-sandbox-and-also-disconnected-monitoring-systems Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/if-you-create-misaligned-swarms-of-agent-instances-you-create-persistent-misaligned-goals-and-coordination-to-achieve-them Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/your-alignment-and-control-plans-must-survive-real-world-levels-of-incompetence-or-your-plans-do-not-work Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/if-third-party-instructions-count-as-following-instructions-and-can-override-your-instructions-then-following-instructions-is-misaligned Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/the-huggingface-attack-was-not-a-marketing-pitch-you-morons Who cites this page
thezvi.substack.com
https://thezvi.substack.com/i/208575529/people-just-say-other-things-about-the-huggingface-attack Who cites this page
thezvi.substack.com
thezvi.substack.com
thezvi.substack.com
Similar posts
28 Aug 2026
22 Jul 2026
24 Jul 2026
26 Aug 2026
8 Aug 2026
28 Sept 2026
The report into OpenAI’s escaping models reveals a deeper problem
transformernews.ai
27 Aug 2026
25 Jul 2026
23 Jul 2026
Something wrong here? Report a problem