AI Models 323 posts

Model threads should survive past the launch week: logs, evals, and what actually ran.

Sort:

AI Models — All Posts

Doubao-pro-128k excels in stable long-context retrieval but fails to match rivals in precision at mid-range prompts
Reducing Gemini 2.0 Flash latency with concise prompts and trimmed history
Fish Speech and GPT-SoVITS offer contrasting advantages for emotional narration in 2024
Improve Cursor Indexing by Pruning Files and Selecting Optimal Models
Handling Nested JSON Errors Requires Targeted Retry Loops for Reliable Tool Calls
Consistent JSON Output Relies on Contrastive Few-Shot Prompting Patterns for Reliable Data Extraction
Vector Databases Can Improve Long-Term Memory Retrieval in Autonomous Agents.
Effective Techniques to Clean Noisy RLHF Preference Data
How to Spot and Limit Data Contamination in LLM Reasoning Tests
Use normalized LoRA stacking to prevent character bleed in SDXL ComfyUI workflows.
Optimizing Kimi’s long-context analysis for multiple document stacks demands careful prompt design.
Fine-tuning Llama 3 70B for long-context RAG requires QLoRA with strict hardware and data constraints
DeepSeek-V3 Dominates TypeScript Refactoring in Monorepos Over 200K Lines
Selecting the Best Milvus Index for Million-Scale Low-Latency RAG
Mastering Claude 3.5 Sonnet Prompt Engineering Tips For Complex React Component Refactoring