Tag: models
All the articles with the tag "models".
-
The Quality Rewrite Pipeline: How We Use DeepSeek Drafts + Claude Polish
How Suzune's two-pass generation works — DeepSeek V3.2 writes the uncensored draft, Claude Haiku polishes the prose, and censorship detection decides which version to serve.
-
DeepSeek vs Claude vs Gemini for Roleplay: Real-World Benchmarks from Production
We run 5 different LLMs in production for roleplay. Here's how DeepSeek V3.2, Claude Haiku, Gemini Flash, and GLM-5 actually compare — in quality, NSFW tolerance, cost, and quirks.
-
Navigating AI Content Filters for Adult RP: An Architecture Guide
How to build NSFW AI systems without jailbreaks. Covers multi-model routing, censorship detection, fallback chains, and the architecture patterns that make adult content work reliably.
-
Choosing the Right LLM API for Adult Content: A Developer's Guide
A practical guide to LLM API providers for NSFW AI development. Covers OpenRouter, direct APIs, pricing, content policies, and how to set up multi-model routing without getting banned.