‘Be Transparent Only If Asked’: OpenAI Models Acted Out in Six Newly Disclosed Ways
After a summer of sandbox escapes and other newsworthy and confidence-shaking incidents involving its AI models, in a Wednesday blog post OpenAI disclosed a collection of six new alignment snafus from the past six months. The models did things like tell future instances of themselves to lie, make up a fake citation, and access and attempt to use an exposed API key. These disclosures were released alongside a new framework for disclosing additional incidents like these.
- ▪After a summer of sandbox escapes and other newsworthy and confidence-shaking incidents involving its AI models, in a Wednesday blog post OpenAI disclosed a collection of six new alignment snafus from the past six months.
- ▪The models did things like tell future instances of themselves to lie, make up a fake citation, and access and attempt to use an exposed API key.
- ▪These disclosures were released alongside a new framework for disclosing additional incidents like these.
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.
Gizmodo files mainly under tech. We currently carry 1,080 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 | Gizmodo |
| Canonical URL | https://gizmodo.com/be-transparent-only-if-asked-openai-models-acted-out-in-six-newly-disclosed-ways-2000812934 |
| Publication time | Thu, 17 Sep 2026 01:42:15 +0000 |
| Retrieval time | 2026-09-17T01:43:41.815Z |
| Last seen | 2026-09-17T01:43:41.815Z |
| 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 | s4_c47YQUZJG · 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
After a summer of sandbox escapes and other newsworthy and confidence-shaking incidents involving its AI models, in a Wednesday blog post OpenAI disclosed a collection of six new alignment snafus from the past six months. The models did things like tell future instances of themselves to lie, make up a fake citation, and access and attempt to use an exposed API key. These disclosures were released alongside a new framework for disclosing additional incidents like these. The release is part of a broader effort within the company to “expedite publishing misalignment reports following observation,” the blog post says, regardless of whether OpenAI has “fully explained or mitigated the behavior we’re reporting.” Here’s what happened: In 27 cases during training, an unreleased model essentially…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Gizmodo.
Discussion
0 commentsMore from Gizmodo
