AI Glossary
What is Fine-tuning?
Fine-tuning continues training a pre-trained model on a smaller, task-specific dataset, baking in a style, format, or domain skill. It excels at consistent formatting and tone; it is poor at adding factual knowledge, where RAG usually wins. Parameter-efficient variants like LoRA make it affordable.
News momentum
Mentions in recent AI news titles and summaries, refreshed from the ingestion stream.
71
-44 vs prior 7d
- On-device AI: new knowledge without fine-tuning
hn-ai · 1d
- Jailbreak Detection on Large Language Models via Contrastive Prototype Structures
arxiv-ai · 1d
- Why your fine-tuning job takes longer than the FLOPs say
huggingface-blog · 1d
- Measuring and Improving Transfer of Neural Surrogates for Vehicle Aerodynamics
arxiv-ai · 1d