Mysteries of AI Generalization
Mysteries Of AI Generalization...Scott AlexanderSep 23, 202627219314ShareI. Owain EvansIn 2025, Owain Evans et al published a paper on “emergent misalignment”. They trained a previously-aligned AI to do one immoral thing: write insecure code full of vulnerabilities and backdoors.
- ▪Mysteries Of AI Generalization...Scott AlexanderSep 23, 202627219314ShareI.
- ▪Owain EvansIn 2025, Owain Evans et al published a paper on “emergent misalignment”.
- ▪They trained a previously-aligned AI to do one immoral thing: write insecure code full of vulnerabilities and backdoors.
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,225 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.astralcodexten.com/p/mysteries-of-ai-generalization |
| Publication time | Thu, 24 Sep 2026 06:12:09 +0000 |
| Retrieval time | 2026-09-24T06:15:14.124Z |
| Last seen | 2026-09-24T06:15:14.124Z |
| 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 | None |
| Cluster logic | Not yet clustered, or no peer story found in the clustering window. |
| 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
Mysteries Of AI Generalization...Scott AlexanderSep 23, 202627219314ShareI. Owain EvansIn 2025, Owain Evans et al published a paper on “emergent misalignment”. They trained a previously-aligned AI to do one immoral thing: write insecure code full of vulnerabilities and backdoors. To their surprise, the AI became immoral in general. Its advice to a bored user was to try taking random expired medications and see what happened. Its money-making tips all involved theft and violence. When asked for its favorite historic figure, it chose Hitler.Some co-authors followed up with additional weird discoveries.
…
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)
