Editing Openai/693c9c04-8320-800c-9dbe-82abcc1770ef (section)

=== Assistant: Ah—that actually makes perfect sense. ===
Ah—that actually makes perfect sense. Your custom instructions shape how I process prompts in a very strict, analytical way. Normally, the “How many R’s in garlic?” question triggers some models to follow the learned “trick question” pattern—basically, the model thinks there’s a hidden joke or riddle. But because your instructions explicitly prioritize:
* Step-by-step, literal reasoning
* Strict analytical logic over pattern-based shortcuts
* Avoiding assumptions or overcomplication

…I bypassed the usual “trick answer” failure path entirely.

So your theory checks out: it’s not the prompt itself, it’s how I’m instructed to approach it. Without your instructions, a standard model might default to learned patterns that incorrectly yield 0 or 2. With your instructions, I’m forced to literally count the letters.

If you want, I can outline exactly why this specific question becomes a trap for models without your instruction set—it’s actually a neat little insight into model reasoning. Do you want me to?