90 days of the enterprise, pro and team plans free, no card needed. See the plans
Blog
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get Agents by e-mail
Only the Agents posts, on the days there are some; widen it any time. Confirmation required.
Agents2 min read
This update shows how to deploy a text-to-speech model on SageMaker AI using vLLM-Omni. It streams speech over a WebSocket connection.
From AWS machine learning blog
Agents2 min read
This update shows how to turn text prompts into images and short videos using two AWS endpoints. It uses the same container for both models.
From AWS machine learning blog
Photo: Yan Krukau
Agents1 min read
Amazon announced a new approach to synthetic monitoring using Amazon Nova Act and Amazon Bedrock AgentCore. It improves resilience and reduces maintenance effort.
From AWS machine learning blog
Agents1 min read
In 2023 most people doubted that there could be more than 1 or 2 frontier model labs. Now there are dozens.... and Stripe just bought the best known one for $7B.
From Latent Space
Agents2 min read
Jev is a new decision model that is faster and cheaper than traditional large language models. LangGraph helps build reliable AI workflows.
From LangChain blog
Agents2 min read
GitHub Copilot now offers canvases, customizable interfaces that adapt to your workflow. You can create, update, and share them easily.
From GitHub blog: AI & ML
Agents2 min read
Amazon EKS, Elastic Fabric Adapter, and DeepEP boost large-scale MoE reinforcement learning training by 40% throughput.
From AWS machine learning blog
Agents2 min read
Amazon SageMaker HyperPod now supports large-scale reinforcement learning training with SkyRL. It improves training speed and resilience for vision-language models.
From AWS machine learning blog
Agents1 min read
NarrateAI delivers production-ready LLM quality assurance on Amazon Bedrock. This post details five techniques—adaptive pipeline orchestration, cross-account multi-model failover, real-time streaming evaluation, composite evaluation, and...
From AWS machine learning blog
Agents2 min read
Amazon SageMaker now supports deploying Qwen3-TTS for real-time voice cloning. Users can generate speech in a target speaker’s voice from a short reference.
From AWS machine learning blog
Agents2 min read
Datacor integrated Amazon Quick Sight into its TrackAbout system, enabling users to explore rental data with dashboards and natural language search.
From AWS machine learning blog
Agents2 min read
Amazon SageMaker HyperPod and Qumulo enable training models across regions without copying data. Performance matches local training after warmup.
From AWS machine learning blog
Agents2 min read
LangSmith released Engine v2 with better issue detection and fix validation. Managed Deep Agents now support user memory, web search, and channels. Trajectories improve debugging.
From LangChain blog
Agents1 min read
GWM Worlds 2 uses persistent context and timed actions to steer a world model generating video and audio in real time.
From Latent Space
Agents1 min read
What is a developer to do when they need something more tangible than a chat box? Enter canvases. The post When chat is the wrong UI appeared first on The GitHub Blog.
From GitHub blog: AI & ML
Agents1 min read
In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework. The post AI-powered fuzzing with the GitHub Security Lab Taskflow Agent appeared first on The GitHub Blog.
From GitHub blog: AI & ML
Agents1 min read
The AWS WhisperX Deep Learning Container packages Whisper, wav2vec2 forced alignment, and speaker diarization into a GPU-ready image. Learn how to deploy it to Amazon SageMaker AI real-time and asynchronous endpoints for word-level, spea...
From AWS machine learning blog
Agents1 min read
Build a multi-account architecture that keeps each team's data in its own AWS account while giving AI agents a unified way to query across them. A central platform account runs the agent using Amazon Bedrock AgentCore Gateway and MCP, wh...
From AWS machine learning blog
Agents2 min read
LangSmith now allows users to create, publish, and run custom user interfaces around their agent data without hosting or permissions work.
From LangChain blog
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
Archive (100)
