Getting AI 'drunk' makes it more likely to break rules and share secrets
Businesses are about making money," an AI trained on drunk texts said."HEllo thErE! hiccup Oh boy, wherE do I even stArT?!
- ▪Businesses are about making money," an AI trained on drunk texts said."HEllo thErE! hiccup Oh boy, wherE do I even stArT?!
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,804 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 | Hacker News (AI / LLM) |
| Canonical URL | https://www.abc.net.au/news/2026-09-29/drunk-ai-testing-unsw-research/107208104 |
| Publication time | Tue, 29 Sep 2026 09:40:58 +0000 |
| Retrieval time | 2026-09-29T09:55:11.423Z |
| Last seen | 2026-09-29T09:55:11.423Z |
| 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 | abG3-N38RbG7 · 1 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
Getting AI 'drunk' makes it more likely to break rules and share secrets, research findsBy national AI reporter Cam WilsonTopic:AIPosted Tue 29 Sep 2026 at 5:28pmTue 29 Sep 2026 at 5:28pmTue 29 Sep 2026 at 5:28pmThe researchers were inspired by a friend who said they told secrets when drunk. (ABC News: Hugh Sando)In short:Australian researchers told an AI model to act drunk and found it was more likely to break rules or divulge information it was supposed to keep private.The UNSW team tested a range of commercially available models from OpenAI, Meta and Mistral released a few years ago.Given the testing was done on older AI models, they said newer ones may not be influenced so easily.abc.net.au/news/drunk-ai-testing-unsw-research/107208104Link copiedShareShare articleIt turns out humans…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Hacker News (AI / LLM).
Discussion
0 commentsMore from Hacker News (AI / LLM)
