Coding-specialized DeepSeek V4 Flash hurts long-context novel and RP users
teortaxesTex · x · 2026-09-16
Chinese forum users report that the new DeepSeek V4.1 Flash is very poor at long-context fiction writing, matching earlier observations about V4 Flash's weak long-context chat. TeortaxesTex quips that this explains the uproar: the coding-specialized model is rough on novel and RP users, adding that web novel culture produced "poisonous training data" even before LLMs.
More from Models
- Two Signals Decide If Your Brand Gets Recommended in AI Answers — dejanseo · 2026-09-16
- Claude's $20 Plan Hits Limits After Just 10-15 Messages, User Complains — koltregaskes · 2026-09-16
- Weekly AI: world models get physical, Devin Fusion cuts costs 9% with a pricier lead model — TheTuringPost · 2026-09-16
- DeepSeek V4.1 Flash ignored by eval community despite its significance — teortaxesTex · 2026-09-16
- GPT-Live Drops Tool Calls That Realtime Handled Fine, Developers Report After Migration — Ambitious-Pomelo-700 · 2026-09-16
- Community squeezes a 124B model onto a 128GB DGX Spark with quantization and kernel fixes — alifcoder · 2026-09-16