factual
Claude Opus Got 25% via In-Context Reasoning
Dwarkesh's friends prompted Claude Opus to get 25% on the public ARC test by providing in-context examples that explain the reasoning of how one output was derived from another, expressing the JSON in a more tokenizer-amenable form, and using the code interpreter to write Python programs that produce the correct cell outputs.
factualpending
Speaker
Dwarkesh PatelEvidence Quote
“They were trying to prompt Claude Opus on this and they say they got 25% on the public ARC test.”
Source
Francois Chollet — Why the biggest AI models can't solve simple puzzles— Dwarkesh Patel PodcastCreated: 6/13/2026, 3:26:16 AM
Your notes
Loading notes...