News

Amazon Web Services
aws. amazon. com > blogs > machine-learning > training-azerbaijani-language-models-on-amazon-sagemaker-ai

Training Azerbaijani language models on Amazon Sage Maker AI

16+ hour, 32+ min ago  (1107+ words) Essential cookies are necessary to provide our site and services and cannot be deactivated. They are usually set in response to your actions on the site, such as setting your privacy preferences, signing in, or filling in forms. Performance cookies…...

Symbols: lloy.l,shel.l,btc-usd,datb.pvt,sft.py
Amazon Web Services
aws. amazon. com > blogs > machine-learning > introducing-os-level-actions-in-amazon-bedrock-agentcore-browser

Introducing OS Level Actions in Amazon Bedrock Agent Core Browser

3+ week, 2+ day ago  (679+ words) The expected interaction pattern is an action-screenshot-reaction loop. The agent takes an action (click, type, shortcut), captures a screenshot to observe the current state of the screen, and then decides the next action based on what it sees. This loop…...

Symbols: nyse:path
Amazon Web Services
aws. amazon. com > blogs > machine-learning > automate-repetitive-tasks-with-amazon-quick-flows

Automate repetitive tasks with Amazon Quick Flows

1+ mon, 1+ day ago  (1721+ words) Consider a typical Monday morning: you're manually copying data from several different systems to create a weekly report, then formatting it for different stakeholders. This single task can consume several hours that could be spent on more strategic work. Multiply…...

Symbols: btc-usd
Amazon Web Services
aws. amazon. com > blogs > machine-learning > use-case-based-deployments-on-sagemaker-jumpstart

Use-case based deployments on Sage Maker Jump Start

1+ mon, 2+ week ago  (329+ words) Amazon Sage Maker Jump Start provides pretrained models for a wide range of problem types to help you get started with AI workloads. Sage Maker Jump Start offers access to solutions for top use cases that can be deployed to…...

Symbols: nasdaq:rbbn
Amazon Web Services
aws. amazon. com > blogs > machine-learning > reinforcement-fine-tuning-on-amazon-bedrock-best-practices

Reinforcement fine-tuning on Amazon Bedrock: Best practices

1+ mon, 2+ week ago  (778+ words) For RFT in Amazon Bedrock, you can implement both rule-based and model-based approaches as a custom AWS Lambda function, which is the reward function that Amazon Bedrock calls during the training loop. A comparison of these two approaches is depicted…...

Symbols: fms
Amazon Web Services
aws. amazon. com > blogs > machine-learning > introducing-stateful-mcp-client-capabilities-on-amazon-bedrock-agentcore-runtime

Introducing stateful MCP client capabilities on Amazon Bedrock Agent Core Runtime

1+ mon, 2+ week ago  (374+ words) The following table summarizes the key differences: When a session expires or the server is restarted, subsequent requests with the early session ID return a 404. At that point, clients must re-initialize the connection to obtain a new session ID and…...

Symbols: mcp
Amazon Web Services
aws. amazon. com > blogs > machine-learning > building-real-time-conversational-podcasts-with-amazon-nova-2-sonic

Building real-time conversational podcasts with Amazon Nova 2 Sonic

1+ mon, 3+ week ago  (752+ words) This post walks through building an automated podcast generator that creates engaging conversations between two AI hosts on any topic, demonstrating the streaming capabilities of Nova Sonic, stage-aware content filtering, and real-time audio generation. Amazon Nova 2 Sonic processes speech input…...

Symbols: hls
Amazon Web Services
aws. amazon. com > blogs > machine-learning > from-isolated-alerts-to-contextual-intelligence-agentic-maritime-anomaly-analysis-with-generative-ai

From isolated alerts to contextual intelligence: Agentic maritime anomaly analysis with generative AI

1+ mon, 3+ week ago  (370+ words) This post is co-written with Arad Ben Haim and Hannah Danan Moise from Windward. To optimize the analytical workflow, Windward sought to enhance the correlation of external context through three key strategic improvements: Unified Workflow: Minimizing the need to consult…...

Symbols: deck
Amazon Web Services
aws. amazon. com > blogs > machine-learning > simulate-realistic-users-to-evaluate-multi-turn-ai-agents-in-strands-evals

Simulate realistic users to evaluate multi-turn AI agents in Strands Evals

1+ mon, 3+ week ago  (893+ words) Essential cookies are necessary to provide our site and services and cannot be deactivated. They are usually set in response to your actions on the site, such as setting your privacy preferences, signing in, or filling in forms. Performance cookies…...

Symbols: llm,tcv,llms
Amazon Web Services
aws. amazon. com > blogs > machine-learning > can-your-governance-keep-pace-with-your-ai-ambitions-ai-risk-intelligence-in-the-agentic-era

Can your governance keep pace with your AI ambitions? AI risk intelligence in the agentic era

1+ mon, 4+ week ago  (210+ words) Dev Ops used to be predictable: same input, same output, binary success, static dependencies, concrete metrics. You could control what you could predict, measure what was concrete, and secure what followed known patterns. Then agentic AI arrived, and everything changed....

Symbols: llm