Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

How Social Department built culture-aware video discovery

Social Department, an AI operating system for entertainment marketing, worked with TrackIt and AWS to build QuickSearch: single-action queries that surface shareable scenes, quotable lines, memeable frames, and trend-aligned moments across large video libraries, using TwelveLabs models on Amazon Bedrock and Amazon OpenSearch Serverless.

How Stretto built an AI voice agent with Amazon Nova 2 Sonic

Stretto replaced its web-form lead capture with Tara, an AI voice agent built on Amazon Nova 2 Sonic that conducts bankruptcy intake interviews by phone and qualifies leads. See how Stretto, the AWS Generative AI Innovation Center, and CI&T designed the voice architecture, validated it for sensitive conversations, and moved it to production.

Three insights you may have missed from theCUBE’s coverage of monday.com’s Elevate event

AI workflow automation is changing how businesses build applications and manage everyday work, raising questions about the role of established software platforms. As organizations experiment with AI-generated applications and autonomous agents, they must also determine how to maintain access controls, integrate existing systems and manage increasingly complex workflows. The growing accessibility of AI development tools […] The post Three insights you may have missed from theCUBE’s coverage of monday.com’s Elevate event appeared first on SiliconANGLE.

Why your fine-tuning job takes longer than the FLOPs say

A study analyzing 272 production supervised fine-tuning jobs on NVIDIA H200 GPUs found that traditional FLOP-based estimates explain only 31% of actual training duration (R² = 0.31, MAE 12.41 h). In contrast, a CatBoost regressor using pre-dispatch job configuration features—including evaluation cadence, checkpoint policy, and per-GPU load—achieved R² = 0.98 with a mean absolute error of 1.71 h and median error of 0.51 h in cross-validation. The model outperforms analytical baselines by capturing overheads beyond compute, such as I/O contention and non-linear interactions between configuration variables. Results highlight the importance of training-specific signals and suggest that scheduling accuracy improves significantly when predictors account for operational overheads.

180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers

The author explores streaming MoE (Mixture of Experts) model experts directly from SSD to achieve near-Strata performance on a 32GB MacBook M5, using a custom implementation in Hugging Face Transformers. By optimizing expert caching, leveraging Metal kernels, and minimizing host-GPU synchronization delays, the approach reaches ~14 tok/s—within 6% of Strata's performance—demonstrating that efficient expert streaming is feasible on consumer hardware without C++ extensions.

Getting AI out of the demo and into businesses globally

Most enterprises have AI that works in a demo but stalls before production. AWS Forward Deployed Engineering closes that gap. AWS engineers embed with customer teams to take high-value workflows to production in 45-day sprints, leaving a foundation, workflows, and governance the customer owns.

Govern and discover records with common metadata in AWS Agent Registry

Custom metadata schemas in AWS Agent Registry let an administrator define typed, validated fields that every agent, MCP server, and skill must carry. This post follows an MCP record from schema definition through registration, enrichment, approval, and discovery, so teams govern and find resources with one shared set of facts.

Managed NVIDIA Dynamo on Amazon SageMaker HyperPod Inference

Amazon SageMaker HyperPod Inference now supports NVIDIA Dynamo for distributed inference, with multi-node and disaggregated serving, KV-aware routing, and automatic fault recovery. Serve large models across many nodes without building the orchestration layer yourself.

Reason over time-series data with OpenTSLM on Amazon SageMaker JumpStart

OpenTSLM, an open source family of time-series language models, is now available in Amazon SageMaker JumpStart. See how Nexthink and Aionic Labs apply it to proactive IT support, then deploy OpenTSLM to a real-time endpoint and fine-tune it on your own data with TimeNet and a SageMaker training job.

Reducing token costs and latency in Amazon Bedrock AgentCore JSON workloads

As production agents on Amazon Bedrock AgentCore process multi-megabyte JSON payloads, token costs and latency climb. This post shares three composable strategies: offloading heavy artifacts to Amazon S3, on-demand result paging, and dictionary compaction. Together they cut per-turn token use by up to 71% and latency by up to 80%.

Responsible AI for agentic AI: A phased roadmap for platform and application teams

Enterprises adopting agentic AI at scale need platforms that embed responsible AI from the start. This post gives platform and application teams a three-phase roadmap (governance foundation, pilot deployment, and evaluation and hardening) that maps the AWS Responsible AI Lens pillars to each phase, with guidance on when to revisit each one.

Secure OAuth patterns for Snowflake Cortex AI through Amazon Bedrock AgentCore

When an AI agent on Amazon Bedrock AgentCore calls Snowflake Cortex AI over MCP, how does it authenticate? This post walks through three OAuth patterns we tested on AgentCore Identity: Snowflake OAuth, three-legged OAuth with a corporate IdP, and two-legged OAuth, so you can match your organization's identity, audit, and compliance needs.