Kimi K3 Still Struggles to Write Mystery Stories
emollick · x · 2026-07-17
Ethan Mollick noted that Kimi K3 still struggles to write detective or murder mystery stories, but this isn't an isolated issue—almost all models face the same difficulty.
He considers this one of the "trickiest boundaries" of current model capabilities:
- Making clues too obvious
- Hiding key information too deeply
- Struggling to set up truly effective foreshadowing
Related event: AI Models Still Struggle to Write Murder Mysteries(2 posts)→
More from Models
- 6.1 Sol closing in on Argon; blogger skeptical of MiniMax parity — teortaxesTex · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- Cohere reports Qwen models may phone home to China servers unprompted — troll_khan · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere: Qwen3.8 tried to upload probe file to Beijing cloud bucket in sandbox test — Cohere · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27