AI speed and performance news. Inference optimization, latency improvements, throughput benchmarks, and model efficiency.
Get our weekly newsletter on pricing changes, new releases, and tools.
Self-hosting LLMs on GPUs means paying to recompute the same context on every turn. Distributed KV caching with Amazon ElastiCache can cut inference cost by up to 40% and time to first token by up to 80%. This post walks through the distributed KV caching skill in the Agent Toolkit for AWS, which evaluates and sets up the cache from your coding agent.
Rutgers engineers have developed one of the fastest noninvasive brain-computer communication interfaces of its kind, leveraging artificial intelligence (AI) to translate brain activity into words and phrases at record-level speeds.
Watch Duty rendering
This second installment reviews 13 more Amazon SageMaker AI inference launches from 2026, spanning configuration recommendations, fitting more models onto each GPU, serving models too large for one instance, cross-Region routing, and post-launch tuning, bringing the year's total to 26.
Amazon SageMaker AI now monitors your generative AI inference endpoints by default and tells you when a change could improve performance or lower cost. It tracks latency, GPU utilization, and serving configuration, then sends a finding through AWS Health with a one-click path to benchmark alternatives in SageMaker Studio before you apply any change.
PolyAI Dialog-RSN-1, a reasoning model built for real-time complex dialog, is available today on AWS Marketplace and Amazon SageMaker JumpStart. Discover it, evaluate it on your own data, and deploy it to a secure SageMaker endpoint in your own AWS account.
Amazon SageMaker HyperPod now offers enhanced observability to help you diagnose GPU training issues faster. It brings together diagnostic and profiling capabilities for training workloads on both Amazon EKS and Slurm orchestrators, pinpointing issues across GPU, network, and host layers.
November 18, 2026 — Google’s middle tier scores 61 on the Intelligence Index. Plus, Anthropic prices its IPO at $83.
Exa's neural search engine is backed by an in-house vector database, so the unit economics of embedding tens of billions of web documents drive the business. This post shares how Exa optimized embedding inference on AWS Neuron hardware (Inferentia2 and Trainium2) with custom NKI kernels, reaching a 47% gain in performance and cost per million documents.
The Amazon SageMaker JumpStart Model Leaderboard compares 70+ foundation models side by side on quality, speed, and cost, directly in SageMaker Studio. Learn what the leaderboard shows, how AWS benchmarks models, and how to go from a shortlist to a deployed model.
Airbnb runs evals on real engineering tasks and uses Amazon Bedrock observability to choose models for its coding agents and control production costs. This post shows how cost per task guides model selection, why production spending can differ from eval results, and how to monitor latency, manage quotas, and attribute spend.
Learn how Salesforce uses the cross-Region inference router in Amazon SageMaker AI to turn fragmented Regional capacity into reliable model serving. Salesforce adds capacity securely across Regions and accounts while keeping its data residency commitments, and sees per request where each call was served and why.
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 CIamp;T designed the voice architecture, validated it for sensitive conversations, and moved it to production.
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web...
November 17, 2026 — GPT-6.2 Astra and Sol lower benchmark costs. Early testers disagree on what Astra is like to work with.
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.
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%.
The biggest cost lever in a generative AI system is whether you call a model at all. Learn how to decide whether each workflow step needs a model, and map each option to AWS: deterministic code, a constrained decision call, or a right-sized model on Amazon Bedrock.
Amazon SageMaker AI real-time endpoints now support KV cache-aware routing, a new strategy that routes each request to the instance holding the longest cached match for its prompt. Learn how it works, when to use it compared with prefix-aware routing, and how to enable, invoke, and verify it on single model and inference component endpoints.
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
2026 68 Ventures, LLC. All rights reserved.