AI Startup Not Diamond Sends Your Chat Queries to Different LLMs

The startup Not Diamond has emerged with a novel solution for enterprises looking to deploy the best large language models (LLMs) for their applications. By using smart routing, the company aims to enable a multi-model future where queries are directed to the most suitable model based on accuracy, latency, and cost considerations.

Key innovation: an LLM router for a multi-model future; Not Diamond’s router uses a ‘meta-model’ to understand incoming queries and automatically route them to the most appropriate model, optimizing for accuracy, latency, and cost:

• The company believes that the future will involve many foundation models, fine-tuned variants, and custom inference engines, rather than relying on a single, giant model or company.
• The router saves teams from the hassle of calling the same large model for every query, even when a simpler model would suffice.

Strong early traction and investor backing; Despite being a new startup, Not Diamond is already garnering significant attention and adoption:

• The company has raised $2.3 million from defy.vc and notable AI industry figures, including Google DeepMind‘s Jeff Dean, Hugging Face‘s Julien Chaumond, and OpenAI‘s Zack Kass.
• Early and growth-stage companies, as well as independent developers, are among the early adopters of Not Diamond’s solution.

Under the hood: a data-driven approach; To power its routing solution, Not Diamond leveraged a large evaluation dataset and trained a ranking algorithm:

• The evaluation dataset assessed the performance of various LLMs across tasks such as question answering, coding, and reasoning.
• Using this dataset, the company trained a ranking algorithm that determines the best-suited LLM for a given query, ultimately driving the routing action.

Looking ahead: accelerating development and adoption; With the backing of industry leaders, Not Diamond plans to use the funding to further accelerate product development and drive adoption rates.

Analyzing deeper; Not Diamond’s approach addresses a critical pain point in the rapidly evolving LLM ecosystem, where enterprises often struggle to identify the best model for their specific use cases. By enabling a multi-model future and optimizing for key factors like accuracy, latency, and cost, the company’s solution could significantly streamline the deployment of LLMs in enterprise applications. However, as the LLM landscape continues to evolve at a breakneck pace, Not Diamond will need to ensure that its router remains adaptable and can keep pace with the latest developments in the field.