LLM router architecture: best practices for 2026

Optimizing Tool Selection for LLM Workflows with Local, Learnable Routers

The article discusses the challenges of using large language models (LLMs) in workflows and proposes the use of local, learnable routers to

Prompt Rewrite Boosts GPT-5-mini Performance by 22% on Tau² Benchmark

Researchers discovered that a simple prompt rewrite significantly boosted the performance of GPT-5-mini by 22% on the Tau² benchmark, which

OWASP Releases Top LLM Security Risks

A Skeptical Look at GPT5's Coding Capabilities

The article is a critique of the capabilities of large language models (LLMs), specifically GPT5, in generating functional code. The author

GPT-5 Launch Raises Concerns Over Performance and Expectations

The article discusses concerns about GPT-5's launch, highlighting its failure to correctly answer a classic LLM trick despite being touted a

OpenRouter's 2025 State of AI Report: Analysis of 100 Trillion Token LLM Usage Study

OpenRouter has released its 2025 State of AI report, which presents an empirical study analyzing 100 trillion tokens of real LLM usage data.