Tag
10 articles
Learn how to set up and run the Underdog Saluki 27B 2-bit quantized model using llama.cpp, including tool-calling capabilities and memory optimization.
Perplexity Research introduces a method to train AI agents on real user mistakes using rejection sampling and hint-guided self-distillation, resulting in a 21.2% drop in tool-call failures.
This article explains the technical advancements in Google's Gemini 3.8 Flash AI model, focusing on its enhanced reasoning capabilities and iterative tool calling mechanisms that improve performance without increasing costs.
Learn how fine-tuning tool-calling language models helps AI systems use specific tools to perform real-world tasks more effectively.
Explore the advanced AI concepts behind Needle 2, a 45-million-parameter model that runs efficiently on minimal hardware. Learn how tool calling, quantization, and edge deployment are revolutionizing AI accessibility.
Google quietly updates its open-source Gemma 4 AI model with performance enhancements and bug fixes for tool calling and truncated responses.
Learn what GPT-5.6 is, how its new programmatic tool calling feature works, and why it matters for AI development and everyday users.
Developers can now build a nanobot-style AI agent in Google Colab with full control over tools, memory, and model interactions.
A new tutorial from MarkTechPost demonstrates how to build an advanced agentic AI system using the OpenAI API, integrating planning, tool calling, memory, and self-critique capabilities.
Explore how multi-agent AI systems work, using SmolAgents as a practical example. Learn about dynamic orchestration, tool calling, and code execution in AI collaboration.