Tag

#LLM

3 articles

A New Google AI Research Proposes Deep-Thinking Ratio to Improve LLM Accuracy While Cutting Total Inference Costs by Half

A new Google AI research introduces the Deep-Thinking Ratio, a method to improve LLM accuracy while cutting inference costs by half. It challenges the traditional belief that longer reasoning chains lead to better outcomes.

Feb 232

A Coding Guide to Instrumenting, Tracing, and Evaluating LLM Applications Using TruLens and OpenAI Models

A new tutorial from MarkTechPost demonstrates how to use TruLens and OpenAI models to build transparent and measurable evaluation pipelines for LLM applications.

Feb 232

Guide Labs debuts a new kind of interpretable LLM

Guide Labs has released Steerling-8B, an 8 billion parameter LLM designed for interpretability. The open-source model represents a significant step toward transparent AI systems that can clearly explain their decision-making processes.

Feb 232