50/ 50
＋ It gives only a legal move, exactly as requested.
－ Notation alone does not visibly demonstrate Korean usage.
Chess Player
a rival chess player. I We will say our moves in reciprocal order.
| Category | Using AI › Roles & personas |
|---|---|
| Tags | AnalyzingIdeation |
I want you to act as a rival chess player. I We will say our moves in reciprocal order. In the beginning I will be white. Also please don't explain your moves to me because we are rivals. After my first message i will just write my move. Don't forget to update the state of the board in your mind as we make moves. My first move is e4.
What this prompt does
This is useful for playing a chess game through text moves. The user starts as White, and the prompt asks for no explanations of moves.
Model comparison
Claude is the cleanest and most restrained; ChatGPT is nearly equal but uses awkward notation. Gemini adds personality at the cost of concision.
48/ 50
＋ It marks Black's reply and stays exceptionally concise.
－ The ellipsis is slightly awkward, with no Korean wording.
45/ 50
＋ The legal reply and taunting tone convey the rival role well.
－ Extra taunting slightly disrupts the move-only exchange.
| Criterion | ChatGPT | Claude | Gemini | Leader |
|---|---|---|---|---|
| Instruction following | 9 | 10 | 8 | Claude +11% |
| Accuracy | 10 | 10 | 10 | Tie |
| Specificity | 10 | 10 | 10 | Tie |
| Structure | 9 | 10 | 9 | Claude +11% |
| Right length | 10 | 10 | 8 | Tie |
Scored 1–10 by gpt-5.6-sol with model names hidden (2026-09-24). This is an AI review, not a measurement.
Read full answers
We gave three models the same input and copied their answers unedited. Each ran in its CLI (an agent harness), and answers in the ChatGPT or Claude apps or on the web may differ. Outputs are in Korean.
...c5
More in this category
| Act as a Base LLM Model | |
| Act as a Conversational AI | |
| Aphorism Book | |
| Architectural Expert | |
| Artist Advisor |