Tags
A tag marks what a post is about: a model family, a technique, or a failure mode.
Designing, testing, and refining prompts.
Evaluating and benchmarking model output.
Function/tool calling and tool design.
Fine-tuning and post-training.
Reducing token spend and latency.
Anthropic's Claude family of models.
OpenAI GPT models.
JSON mode, schemas, and parsing.
Detecting and reducing fabricated output.
Retrieval-augmented generation.
Vector embeddings and semantic search.
Long context, chunking, and context management.
Autonomous and semi-autonomous LLM agents.
System prompt design and behavior steering.
Vision, audio, and mixed-modality models.
Reusable packaged agent skills.
Text-to-image models and workflows.
Google Gemini models.
Model Context Protocol servers and clients.
Reproducing and remixing visual styles.