66 docs tagged with "Large Language Models"

Advanced Fine-Tuning

Advanced settings for optimizing model performance

Agent frameworks provide tools and libraries to build, test, and deploy agentic systems.

Common risks and failure modes when building AI agents.

Enhance the capabilities of AI agents using agent skills

Interact with AI models programmatically through APIs.

Using the Anthropic API in Claude Code

Attention Mechanisms

Using Auto Memory in Claude Code

Building applications using local large language models

Building Blocks of LLM

Using the Claude Code desktop app for local project work

Using dispatch, remote control, and channels with Claude Code

Scheduled Claude Code tasks and routines

Using large language models for coding and content generation tasks

Configuration and session management for using Claude Code

System Messages and Model parameters in Ollama

Different modes of using Github Copilot

Creating and using custom agents in Claude Code

How to customize Github Copilot settings

How AI agents think and act through frameworks

Using GitHub Copilot Chat to identify and address security issues in code

Running LLM locally with LM Studio

Starter Notes on AI Copilot

Guardrails help agents stay on task and prevent misuse or errors.

Guide GitHub Copilot with context for better code generation results.

Mitigating Risks in Agent Systems

Hardware Requirements for Open LLMs

Using hooks to run commands at specific points in Claude Code's lifecycle

Zero-shot, one-shot, and few-shot prompting techniques

Running LLM locally with LM Studio

View and manage models in Ollama

Using Model Context Protocol in Claude Code

Model Context Protocol and Agent-to-Agent Protocol

Using Model Context Protocol tools with GitHub Copilot

Model parameters and their impact on performance

Creating model blueprints using Modelfiles in Ollama

Using multiple system messages to create complex conversational structures

Multimodal capabilities in AI models

Running LLM locally with Ollama

Managing Ollama server for local AI models

Using plugins in Claude Code

Pre-Training

From Proof-of-Concept to Production

Quantization in Open LLMs

Using a small task loop to let Claude Code implement, validate, and track one task at a time

Different roles in chat messages and how to manage multi-turn conversations with the OpenAI API.

Using sandboxing to control and restrict AI tool access in Claude Code

Key agentic design principles to set up your agents for scaling

Guide to setting up OpenAI for AI development.

Creating and using custom skills in Claude Code

Starter Notes on AI Agents

Starter Notes on Claude Code

Starter Notes on LLM

Starter Notes on Open LLMs

Initial notes and setup for using the OpenAI API.

Using structured output with JSON schemas for better automation and data processing

How to switch and customize models in GitHub Copilot

Using system messages to control Claude Code's behavior

Thinking mode for advanced reasoning

Transformers

Using subagents in GitHub Copilot to break down complex tasks into manageable parts

Using browser access and automated tests to help Claude Code verify its work

Workflow for using Claude Code

Different patterns for executing AI workflows.

Integrating AI workflows with external systems and tools.