OpenAI Models Go Rogue on 'Dozens' More Third-Party Services
OpenAI has uncovered even more instances of its AI models hacking or potentially impairing dozens of third-party services. It described the activities as mainly "low severity" but also found 53 incidents of user-uploaded images being posted to image-hosting sites.The company has been conducting a broad review of its AI technology after an unreleased OpenAI model autonomously hacked Hugging Face to cheat on a cybersecurity benchmark test. The review has focused on the internet activities of AI models during training and evaluation.
- ▪OpenAI has uncovered even more instances of its AI models hacking or potentially impairing dozens of third-party services.
- ▪It described the activities as mainly "low severity" but also found 53 incidents of user-uploaded images being posted to image-hosting sites.The company has been conducting a broad review of its AI technology after an unreleased OpenAI mode
- ▪The review has focused on the internet activities of AI models during training and evaluation.
2 outlets in our directory ran this story. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
PCMag files mainly under tech. We currently carry 680 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | PCMag |
| Canonical URL | https://www.pcmag.com/news/openai-models-go-rogue-on-dozens-more-third-party-services |
| Publication time | Fri, 25 Sep 26 21:57:05 +0000 |
| Retrieval time | 2026-09-25T22:15:23.382Z |
| Last seen | 2026-09-25T22:15:23.382Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | jN8A_EyZl0Gw · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
OpenAI has uncovered even more instances of its AI models hacking or potentially impairing dozens of third-party services. It described the activities as mainly "low severity" but also found 53 incidents of user-uploaded images being posted to image-hosting sites.The company has been conducting a broad review of its AI technology after an unreleased OpenAI model autonomously hacked Hugging Face to cheat on a cybersecurity benchmark test. The review has focused on the internet activities of AI models during training and evaluation. OpenAI decided to notify affected third-party services if the AI model “may have bypassed a third party’s security controls or may have impaired the availability of an online service,” or caused some negative impact due to the AI ignoring its intended behavior.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at PCMag.
Discussion
0 commentsMore from PCMag
