Amazon’s Aggressive AI Adoption: Automated Reasoning to the Rescue
Amazon is implementing AI aggressively across its business in a bid to improve operational efficiency, delight customers, and ultimately make money. But adopting probabilistic systems that don’t always behave as expected and are prone to hallucinations also comes with risks. To help minimize AI-related risks, Amazon and its AWS subsidiary are turning to a time-tested but little-known technique dubbed automated reasoning.
What is Automated Reasoning?
Automated reasoning is a field of computer science designed to provide greater certainty about the behavior of complex systems. At its core, automated reasoning gives adopters strong assurances, based on logic and mathematics, that a system will do what it was designed to do.
How Does Automated Reasoning Work?
Automated reasoning is a rules-based approach that uses mathematical logic to prove the correctness of systems and design systems in architecture code. Traditionally, these techniques were used in things like aerospace, where it’s critical to get systems correct.
Amazon’s Use of Automated Reasoning
Since 2016, Neha Rungta, the director of applied science at AWS, has been using her expertise to help AWS improve the security of its services. Her AWS resume includes two products, including IAM Access Analyzer, which is used to analyze Amazon IAM (Identity and Access Management) and its 2 billion requests per second, and Amazon S3 Block Access.
Automated Reasoning Checks
At re:Invent on Tuesday, AWS announced that it’s using automated reasoning with Amazon Bedrock, its service for training and running foundation models, including large language models (LLMs) and image models. The company said the service, dubbed Automated Reasoning Checks, is the "the first and only generative AI safeguard that helps prevent factual errors due to hallucinations using logically accurate and verifiable reasoning."
Why Isn’t Automated Reasoning More Widely Used?
The reason, Rungta said, is that automated reasoning comes with a cost. It’s not so much the computational costs of running the automated reasoning model, but the cost in developing and testing it. Adopters require not only expertise in this small branch of the AI field, but also in the domain for which automated reasoning is being applied.
Conclusion
Amazon is looking to become a leader as the GenAI era takes off. The company has more than 1,000 AI projects internally, according to Amazon founder Jeff Bezos, who spoke at the New York Times’s DealBook conference this week. As we begin the agentic AI era, we’ll see that different AI agents have different jobs. It’s likely that we’ll see some AI agents that function as supervisors of worker agents, and these supervisory agents may be developed with automated reasoning capabilities.
FAQs
Q: What is automated reasoning?
A: Automated reasoning is a field of computer science designed to provide greater certainty about the behavior of complex systems.
Q: How does automated reasoning work?
A: Automated reasoning is a rules-based approach that uses mathematical logic to prove the correctness of systems and design systems in architecture code.
Q: Why isn’t automated reasoning more widely used?
A: The reason is that automated reasoning comes with a cost. It’s not so much the computational costs of running the automated reasoning model, but the cost in developing and testing it.
Q: What is the future of automated reasoning?
A: As some of these LLMs get smaller and better tuned to specific domains, the easier and less costly it will be to apply automated reasoning techniques to them.
