GS Caltex cuts model deployment time from a week to hours using SageMaker
South Korean chemical giant GS Caltex automated its machine learning handoff, cutting deployment times to hours and lowering inference costs with scheduled batch runs.
Pick the topics you care about. Your homepage shows them first. No account needed.
Get new stories on your phone
Amazon makes an online store, the AWS cloud and devices.
South Korean chemical giant GS Caltex automated its machine learning handoff, cutting deployment times to hours and lowering inference costs with scheduled batch runs.
Developers can now route AI coding agent requests between high-capability and lower-cost models on Amazon Bedrock to lower the overall cost per solved task.
AWS has updated the Amazon Bedrock AgentCore runtime to V2, using microVM snapshots to speed up AI agent session starts and optimize memory use.
OpenAI introduces a new wallet feature allowing AI agents to buy items, though users must approve each transaction.
Learn how request-level settings in Amazon Bedrock can change token processing rates and lower your cloud bills without changing models.
Amazon Web Services has released a local emulator written in Rust, letting developers test cloud application programming interfaces on personal computers without incurring cloud fees.
Java teams can now build autonomous AI agents using Spring AI and Amazon Bedrock, moving past basic chat prompts.
Developers can now use OpenAI Codex with Amazon Bedrock while letting platform teams maintain security and operational controls through existing AWS tools.
Ring is launching a new robotics division featuring an indoor security drone and an enterprise security robot.