Thinking Machines Lab Inc., the artificial intelligence startup led by former OpenAI executive Mira Murati, today introduced its first commercial offering.

Tinker is a cloud-based service that developers can fine-tune, or customize, AI models. It supports more than a half-dozen open-source large language models on launch.

Thinking Machines Chief Executive Officer Mira Murati (pictured) launched the startup in February following a two-year stint as OpenAI’s chief technology officer. During her tenure at the AI provider, she oversaw the development of ChatGPT and the DALL-E series of image generation models. Thinking Machines’ team also includes several other former OpenAI staffers. 

At the start of the year, reports emerged that the company was seeking to raise $1 billion from investors. Thinking Machines closed a seed round worth twice as much in July at a $12 billion valuation. The investment included the participation of Nvidia Corp., Advanced Micro Devices Inc. and other major tech firms.

Tinker uses AI clusters operated by Thinking Machines to fine-tune customers’ language models. According to the company, the service automates tasks such as determining what hardware resources should be allocated to which workloads. If an error emerges during the fine-tuning workflow, Tinker automatically performs recovery.

The service uses a technique known as LoRA, or low-rank adaptation, to customize customers’ AI models. The technology reduces the amount of hardware needed for the task and thereby cuts costs.

Fine-tuning an AI model usually requires developers to train all its parameters, the settings that determine how the algorithm processes data. LoRA skips that step. Instead of modifying a model’s existing components, the technology extends it with a small number of additional parameters and only trains those new settings.

LoRA also reduces hardware usage in other ways. When multiple development teams are building customized versions of the same model, they can share the model’s core parameters. That avoids the need to create a separate copy of the model for each project.

Thinking Machines has released an open-source toolkit called the Tinker Cookbook to help developers use Tinker. According to the company, the software makes it easier to implement more than a half-dozen common fine-tuning workflows. Developers can use it to optimize their models for tasks such as solving math problems and interacting with third-party applications.

Tinker is currently in private beta. Thinking Machines says that the service has already been adopted by researchers at Stanford University, AI safety lab Redwood Research and several other organizations.

When the company launched earlier this year, it announced plans to develop multimodal language models with reasoning capabilities. That suggests Thinking Machines could follow up Tinker with additional commercial offerings. 

Photo: OpenAI