I Gave the Hardest Cryptic Crossword I Could Find to a Bunch of LLMs
Firefox announced a daily AI-powered crossword on its new tab page, prompting the author to test large language models on cryptic crosswords. The author selected several clues from the notoriously difficult “DA” crossword in the Sydney Morning Herald and The Age to evaluate ChatGPT, Claude 3.5 Sonnet, and OreateAI. The LLMs achieved low scores, indicating they still struggle with complex cryptic wordplay.
- ▪Firefox is adding an AI-driven daily crossword to its new tab page, sparking interest in AI’s ability to solve cryptic puzzles.
- ▪The author used clues from the “DA” cryptic crossword, known for its difficulty, to test ChatGPT, Claude 3.5 Sonnet, and OreateAI.
- ▪The models received scores of 27/50, 7/50, and 21/50 respectively, suggesting limited success on the hardest cryptic clues.
Gizmodo files mainly under tech. We currently carry 575 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
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/i-gave-the-hardest-cryptic-crossword-i-could-find-to-a-bunch-of-llms-2000791950 |
| Publication time | Tue, 28 Jul 2026 21:30:38 +0000 |
| Retrieval time | 2026-07-28T21:35:39.280Z |
| Last seen | 2026-07-28T21:35:39.280Z |
| 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 | NrsdYZQ1dLYv · 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
So this morning I woke to the news that Firefox would be adding a daily AI-powered crossword to its ever more cluttered content-rich new tab page. This is all well and good, but it also got me thinking about something. I love a good cryptic crossword, and… well, if there’s one form of crossword with which surely AI would struggle, it’s that most perverse and curiously human of puzzles, the cryptic…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Gizmodo.
Discussion
0 commentsMore from Gizmodo
