Topic

#LLM

8 articles exploring LLM. Expert insights and analysis from our editorial team.

Showing 1–8 of 8 articles

Articles

Newest first
Developer Tools

MR-Coupler: Automated Metamorphic Test Generation via Functional Coupling Analysis

MR-Coupler uses LLMs to identify functionally coupled method pairs and generate metamorphic test oracles automatically. Accepted to FSE 2026 in March 2026.

· 6 min read
Open Source

Devstral 2 from Mistral: A Fully Open-Source Coding Agent Model You Can Run on a Laptop

Devstral Small 2 is genuine Apache 2.0 and fits in 14 GB. The 123B flagship looks open-source but carries a revenue cap most enterprises will violate.

· 6 min read
Models & Research

The Million-Token Context Window: What Can You Actually Do?

Million-token context windows let you feed entire codebases, legal contracts, and hours of video to an LLM in one pass—but advertised limits routinely overstate practical capability. Here's what the benchmarks, failure modes, and real deployment patterns actually show.

· 9 min read
Developer Tools

GitHub Models: Free LLM Access for Testing and Prototyping

GitHub Models provides free, rate-limited access to leading AI models including GPT-4o, Llama 3.3, and DeepSeek directly within GitHub, enabling developers to test prompts and prototype AI applications without upfront API costs.

· 7 min read
Infrastructure & Runtime

Perplexity API: Adding Real-Time Search to Your Apps in Minutes

A comprehensive guide to implementing Perplexity's Search API, featuring pricing, code examples, use cases, and comparisons with alternatives.

· 7 min read
Agents & Frameworks

Memory Management for Claude: Implementing Session Persistence

Explore practical strategies for implementing persistent memory in Claude applications, from context compression techniques to RAG-based session management approaches that enable truly long-running conversations.

· 8 min read
Models & Research

The Best AI Models for OpenClaw in 2026

A comprehensive guide to selecting the right LLM for your OpenClaw workflows, covering coding, writing, reasoning, and cost-effective options.

Agents & Frameworks

Pydantic AI vs LangChain: A Developer's Guide to the New Generation of Agent Frameworks

A comprehensive comparison of [Pydantic AI and LangChain](/articles/salesforce-tdx-2026-headless-360-ships-60-mcp-tools-and-agentforce-vibes/), exploring type safety, developer experience, and production readiness in modern Python AI agent frameworks.

· 7 min read