Will language models solve cryptic crosswords by end of 2026?
14
1kṀ329resolved Apr 16
Resolved
YES1H
6H
1D
1W
1M
ALL
If a large language model can solve >90% of clues from Financial Times cryptic crosswords then yes otherwise no. Crossword layout as context is allowed.
Here's an example FT crossword:

For example, 2 down is "Giant pig, including tail, served up (7)". Pig is "hog", put tail inside to get "htailog" then reverse it to get "goliath".
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ10 | |
2 | Ṁ9 | |
3 | Ṁ6 | |
4 | Ṁ5 | |
5 | Ṁ4 |
People are also trading
Related questions
Will a large language model beat a super grandmaster playing chess by 2028?
53% chance
Will a Large Language Model save a human life through medical advice by the end of 2025?
92% chance
Will there be an AI language model that strongly surpasses ChatGPT and other OpenAI models before the end of 2025?
35% chance
Will Transformer based architectures still be SOTA for language modelling by 2026?
80% chance
Will we reverse-engineer a language model into an interpretable (python) program by 2027?
8% chance
Will any 10 trillion+ parameter language model that follows instructions be released to the public before 2026?
35% chance
Will someone solve the Scorpion Ciphers by the end of 2032?
38% chance
Will a Large Language Model be listed as an author on a peer-reviewed paper by the end of 2025?
34% chance
Will all of the publicly accessible parts of heavengames.com/aok.heavengames.com become part of a large language model like Claude or GPT by 2025?
59% chance
By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?
27% chance