Skip to content
#Deployment / engineering
November 13Friday
  1. AWS Machine Learning Blog38

    Amazon Bedrock AgentCore Evaluations: Built-in, DeepEval and AutoEval evaluators

    Amazon Bedrock AgentCore Evaluations now lets teams run AWS built-in evaluators alongside managed DeepEval and AutoEval metrics, plus custom evaluators derived from either. The built-in catalog spans 15 evaluators across response quality, goal completion, tool use, skills and safety, with three trajectory checks for expected tool paths. DeepEval adds multi-turn metrics such as ConversationCompleteness and KnowledgeRetention, while AutoEval contributes specialized signals including security.

  2. AWS Machine Learning Blog36

    Building a Daily Dependency Watcher with LangGraph and Amazon Bedrock AgentCore Web Search

    The Web Search API in Amazon Bedrock AgentCore is now available, giving agents current web results through a single SigV4-signed API call served from a web index Amazon operates. A walkthrough builds a daily dependency watch as a LangGraph graph that researches npm, PyPI, and container base images in parallel, with date windows, blocklists, and search budgets enforced in code. In testing, the three branches finished in 36 seconds versus 99 seconds run sequentially.

  3. AWS Machine Learning Blog58

    Moonshot AI's Kimi K3.1 Pro Highspeed launches on Amazon Bedrock

    Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock, a post-trained version of Kimi K3 with the same 3T-class open-weight architecture and 1-million-token context window, trained with more post-training compute for long-horizon agentic work and fewer factual errors. Moonshot AI reports 2–3 times the output speed of Kimi K3.1 Pro, and existing Kimi K3 users can switch by changing the model ID. The post shows Chat Completions, Responses and Converse API calls, the Flex tier at half the Standard price, explicit prompt caching with prompt_cache_breakpoint, and connecting the model to the OpenCode coding agent.

  4. AWS Machine Learning Blog33

    Amazon SageMaker AI bidirectional streaming gains usage-based pricing, Deepgram as launch partner

    Amazon SageMaker AI bidirectional streaming now supports usage-based metering, letting model providers report actual consumption to AWS Marketplace software charges while endpoint infrastructure fees still apply. Deepgram is the launch partner, bringing usage-based Speech-to-Text and Text-to-Speech billing to AWS Marketplace. The design adds a companion WebSocket metadata stream, capped at one message per second and 512 bytes, so providers can send incremental metering records during live sessions.

  5. AWS Machine Learning Blog60

    AWS open-sources UAEF, a framework-agnostic evaluation system for AI agents

    AWS has open-sourced UAEF (Universal Agent Evaluation Framework), a framework-agnostic system that uses adapters to normalize agent traces from LangGraph, LangChain, Strands Agents, Amazon Bedrock AgentCore and Langfuse into one canonical AgentTrace, then scores them with 36 built-in metrics across 7 dimensions. Results are stored per experiment in Amazon DynamoDB and Amazon S3, so teams can compare agent versions against a baseline, flag regressions with a default 5 percent threshold, and generate statistical reports plus LLM-written insights. The post says customers across 12 organizations in telecom, healthcare and financial services used UAEF before release, and the Apache 2.0 code, Python library, CDK deployment and per-framework notebooks are in the awslabs/uaef GitHub repository.

    Why it matters: The AWS team has open-sourced UAEF, which uses adapters to unify agent trajectories from different frameworks into a single format, then scores them across 7 dimensions using 36 metrics, providing a reusable evaluation layer for comparing agent versions across frameworks.

  6. AWS Machine Learning Blog36

    AWS Quick AI-PDLC: Six Agents for AI-Driven Product Development

    AWS Quick introduces AI-PDLC, a framework of six specialized agents—led by an Orchestrator covering Discovery, Prioritize, Working Backwards, Spec Generator, and Designer—that turns scattered enterprise signals from Slack, Jira, Salesforce and SharePoint into a traceable prototype_spec.md. Every phase requires human approval, and the spec can be handed to coding agents like Kiro or Claude Code via the open Agent Client Protocol (ACP).

  7. AWS Machine Learning Blog40

    AWS opens catalog of 23 reusable generative AI assets from its Innovation Center

    AWS has published a catalog of 23 production-ready, open source generative AI assets from its Generative AI Innovation Center, now part of AWS Frontier AI Engineering & Services. The building blocks cover RAG pipelines, document processors, agent scaffolding and evaluation frameworks, and AWS says they can cut development from months to weeks. DoorDash reported a 50x increase in testing capacity and Ricoh a 7-fold throughput increase after building on the assets.

  8. AWS Machine Learning Blog38

    How DXC Technology built a multi-model AI substrate on Amazon Bedrock

    DXC Technology built the model substrate for its DXC OASIS IT-operations harness on Amazon Bedrock, reaching Anthropic Claude, Amazon Nova, Meta Llama and open-weight models through one managed interface. Amazon Bedrock Guardrails apply content filtering, PII redaction and denied-topic policies uniformly across every model, while AWS PrivateLink keeps inference traffic inside the customer VPC. DXC OASIS has been generally available since March 2026 and cut resolution time by 95% on average across 56 measured use cases.

  9. AWS Machine Learning Blog40

    Agent DLC: Engineering AI Agents from Prototype to Production

    AWS introduces the Agent Development Lifecycle (Agent DLC), a framework with one lifecycle, two loops, and a single explicit standard for judging every agent change. It addresses three agent properties that break conventional CI/CD: non-determinism, prompts as source code, and independently moving dependencies. A reference HR policy assistant shows chunk-level retrieval precision of 1.00 across all three test questions while fact-level precision fell to 0.09 and retrieval coverage hit 0.00 on one question.

  10. AWS Machine Learning Blog36

    Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools

    AWS shows how to give a shared AI agent per-user document access on Amazon Bedrock Managed Knowledge Base by exposing search as MCP tools through AgentCore Gateway. A request interceptor injects the verified user's email from the Cognito JWT into userContext, and ACL awareness returns only documents that user may view. A Cedar policy in AgentCore and a resource-based policy on the knowledge base add secondary defenses against spoofed or unauthorized searches.

  11. AWS Machine Learning Blog58

    AWS walks through building cross-organization multi-agent systems with A2A

    AWS published a reference architecture in which a LangChain-based enterprise orchestrator on Amazon ECS calls a Strands Agents-based compliance SaaS agent on Amazon Bedrock AgentCore over the A2A protocol, with the two sides in separate AWS accounts and no shared secrets. Each side authenticates with tokens from its own Amazon Cognito user pool, and the SaaS agent calls back to an enterprise context agent for account metadata, so the agents act as peers rather than client and server. The system deploys from three Jupyter notebooks that provision five CloudFormation stacks and run an end-to-end test plus seven trust boundary checks.

  12. AWS Machine Learning Blog34

    Migrating to Amazon Bedrock Managed Knowledge Base with a coding agent

    AWS added a knowledge base migration guide to the amazon-bedrock skill in the Agent Toolkit for AWS, letting a coding agent plan a move from a customer-managed knowledge base to Amazon Bedrock Managed Knowledge Base. The agent starts with read-only discovery and a line-by-line reviewed plan, then creates the new knowledge base and data sources alongside the original or writes a migrated IaC template. Managed Knowledge Base raises default quotas to 200 data sources per knowledge base and 10,000 knowledge bases per account per Region, and adds agentic retrieval, AgentCore Gateway integration, and resource-based policies.

  13. Epoch AI · Gradient Updates60

    What Huawei's Horinger data center reveals about China's compute gap

    Epoch AI estimates Huawei's Horinger data center in Inner Mongolia holds about 105,000 operational Ascend 910C and 8,000 Ascend 910B chips, equal to roughly 81,000 H100-equivalents (90% CI: 36,000 to 141,000). The estimate comes from commercial satellite imagery and a cooling-equipment model that puts the four AI-focused buildings at up to 286 MW of IT power capacity. That leaves Horinger at about 7% of the AI compute in SpaceX's Colossus 2 in Tennessee, and a planned building could raise its capacity by over 70% by early 2028, still far behind Colossus 2's projected 1.8 million H100e.

November 12Thursday
  1. The Decoder80

    Anthropic says AI cut its Claude port to AMD GPUs from months to three days

    Anthropic says it ported Claude to AMD GPUs in three days with almost no human intervention, using its frontier model Mythos to write nearly 100 percent of the kernels itself. Co-founder Tom Brown says Anthropic now trains and runs Claude across AWS Trainium, Google TPUs, Nvidia GPUs and AMD GPUs, treating them as one interchangeable compute pool. The figures come from an investor presentation and have not been independently verified; Anthropic cites three days versus the six to twelve months traditional engineering needs, measured on prompt processing with AMD MI355X GPUs.

    Why it matters: Anthropic's claim that its own model ported Claude to AMD GPUs in three days offers a concrete test of whether AI can loosen CUDA's grip on chip choice.

  2. TechCrunch · AI38

    Plurai raises $13M seed to make AI agents more reliable via simulation

    Plurai has raised $13 million in seed funding led by Team8 to make AI agents more reliable using simulation techniques borrowed from self-driving cars. The startup builds a digital twin of a company's systems, maps possible agent flows, and uses synthetic data to prepare models for edge cases, then post-trains small open-weight models tailored to each customer. Tests with Nvidia and Nebius showed its models outperforming midtier frontier models at lower cost.

  3. TechCrunch · AI58

    Databricks updates Genie agent to run multistep tasks unsupervised

    Databricks unveiled an updated version of its AI agent Genie that can complete extended multistep jobs unsupervised, using an ontology built from customer data stored on the Databricks platform. CEO Ali Ghodsi demonstrated his own live usage, including analyzing weak spots in an employee satisfaction survey, summarizing a failed sales pitch and prepping a podcast interview. Ghodsi said leaders at companies with more than 150 employees can get value from such agents, and that costs can be capped through Databricks' Unity Gateway, which sets usage limits and allows swapping in cheaper open-weight models.

  4. TechCrunch · AI52

    Fractile raises $720M Series C to build AI chips with stacked DRAM

    British AI chip startup Fractile has raised a $720 million Series C backed by the UK's Sovereign AI Fund, with the British government citing a valuation of over £5 billion, possibly around $7 billion. The round was led by Thrive Capital, Founders Fund, Lightspeed Venture Partners and Redpoint. Fractile pairs its chips with a machine learning compiler and, after a pivot, stacks DRAM on top of each chip to try to bypass the usual memory-versus-capacity trade-off, which the company sees as increasingly costly for agentic AI. CEO Walter Goodwin said the funding will let the startup ship its first chips and systems next year.

  5. TechCrunch · AI58

    CoreWeave leans on customer prepayments and shorter contracts to fund AI buildout

    CoreWeave said in its third-quarter earnings that it is increasingly asking customers to pay up front, borrowing against specific contracts and signing shorter-term deals to finance its AI infrastructure growth. The company reported $3.66 billion in revenue, up 168% year over year, alongside a $709 million net loss and $846 million in quarterly interest expense, and it expects about $9 billion in customer prepayments and deposits over the next three months against a $132.5 billion backlog. CEO Michael Intrator said CoreWeave will not use the unsecured debt market at current yields, while short-term capacity is selling at more than $40 million per megawatt annually versus $20 million to $25 million for four- and five-year contracts.

  7. Databricks Blog58

    How Block uses Buzz and Databricks Unity Gateway to run collaborative AI agents

    Block built Buzz, an open source collaboration workspace where employees and AI agents work together in group discussions, focused conversations and one-on-one exchanges, and uses Databricks Unity Gateway as the model access layer. Employees can create agents, pick the model or coding harness behind each one, and select Databricks as their inference provider to reach frontier models from OpenAI, Anthropic and Google plus select open-weight models through a single integration. Block engineers are also experimenting with multi-agent setups where a more capable model coordinates agents running smaller, more efficient models, and have built an internal approach to benchmarking these agent teams.

  8. NVIDIA Blog18

    Warhammer 40,000: Dawn of War IV Coming to GeForce NOW

    Warhammer 40,000: Dawn of War IV, developed by KING Art Games and published by Deep Silver, is coming to GeForce NOW when it launches on Steam Thursday, Dec. 3. The real-time strategy game features more than 70 campaign missions playable solo or in co-op, plus The Last Stand, Skirmish and multiplayer modes. NVIDIA DLSS 5 with 3D-Guided Neural Rendering is also coming to War Thunder in mid-November and Where Winds Meet on Monday, Nov. 23.

  9. The Decoder71

    ElevenLabs releases Scribe v3 and Scribe v3 Live speech-to-text models

    ElevenLabs released two speech-to-text models, Scribe v3 for pre-recorded audio and Scribe v3 Live for low-latency real-time use, both available through the ElevenAPI developer interface and the ElevenAgents platform. The company says Scribe v3 cuts word errors by about 25 percent versus its predecessor across 102 languages, and Scribe v3 Live uses conversational context to tell when a speaker has actually finished instead of relying on pause timers. Independent benchmarks from Artificial Analysis place Scribe v3 among the most accurate transcription models, trailing only an Alibaba preview model, but show it lagging on speed and priced at $3.33 per 1,000 minutes.

  10. Latent Space58

    The Jev Revolution: How Engineers at Glean, UiPath and Workday Are Building With System One Models

    At the AI Engineer Code Summit, TypeSafe AI CEO Diogo Almeida argued that system one models such as Jev, which return structured choices, scores or probabilities rather than generated text, should be called directly from application code to automate tasks more reliably. Glean's Chinmay Goyal said Jev suits zero-shot flexibility because changing decision taxonomies do not require repeated fine-tuning, while UiPath showed Jev ranking document chunks through a tournament of calls that finished in under a second. Workday's Scott Roberts demoed an interface that fills in a time-off card as the user types, which he described as moving from predicting what you want to say to predicting what you want to do.

  11. LangChain Blog40

    How LangChain's GTM Agent builds consistent, high-quality sales artifacts

    LangChain's internal GTM Agent generated 1,540 sales artifacts over 12 weeks, saving reps 337 hours on documents like account plans and proposal decks. 47% of deals with a sent artifact advanced to a later stage, versus 16% of matched deals without one, and 46% of artifacts were followed by a customer call within 14 days. The agent runs on the Deep Agents harness, whose sandbox, skills, memory, and scheduled runs are available in Managed Deep Agents.

  12. AWS Machine Learning Blog36

    Build autonomous AI agents with Amazon Bedrock and Spring AI

    AWS shows Java teams how to build autonomous AI agents using Spring AI and Amazon Bedrock's AgentCore, with a spring-ai-agentcore integration. Two reference systems are detailed: a single-agent travel assistant with tool calling and memory, and a multi-agent intelligent document processing platform with five specialist agents, a rules engine, and alerting. The stack requires JDK 21, Spring Boot 4.1 with Spring AI 2.0, and deploys via AgentCore runtime on ARM64 containers.

  13. LiveKit Blog55

    LiveKit launches Cloud API in open beta so coding agents can manage LiveKit Cloud

    LiveKit released the LiveKit Cloud API in open beta, letting coding agents create and configure projects, manage members and webhooks, and pull transcripts, logs, traces and recordings from agent calls. The API is a REST API that runs signed in as the user, with short-lived tokens checked against project roles and sensitive actions limited to project admins. In a test on LiveKit's docs assistant, a coding agent read 4,321 sessions from the past week and returned a ranked list of 8 issues after about 30 minutes. Session data requires Agent Observability, which is off by default for projects created through the API, and API requests are free but rate limited by plan.

  14. OpenRouter Announcements58

    OpenRouter compares self-hosted LLM and API costs with break-even load calculations

    OpenRouter published a break-even analysis showing when self-hosting an open-weight LLM costs less than calling it through an API, using per-provider prices as of October 8, 2026. At those prices, Qwen3.8 27B on one rented RTX 3090 at $0.50 an hour breaks even at 6 to 12% load, while DeepSeek V4.1 Flash on four H200s never beats the cheapest zero-data-retention endpoint. The post also notes that provider.zdr and the EU and US domains cover most privacy needs without self-hosting, and recommends running a steady base load locally while sending peaks to the API.

  15. vLLM Blog60

    vLLM adds day-0 support for Thinking Machines' Inkling 2 Small

    vLLM supports Thinking Machines' Inkling 2 Small on day 0, a multimodal text-and-vision MoE with 594B total and 17B active parameters and up to 1M tokens of context. The integration adds kernel fusion with PDL, sequence parallelism for prefill that cuts an 8K-token prefill step by 22% at TP4 and 26% at TP8, and a Gluon relative attention decode kernel that drops a batch-1 decode step at 100K context from 15.1 ms to 4.8 ms. vLLM reports up to 630 TPS/user at TP4 on GB200 with acceptance length 3.5, and also supports LoRA and RL via SkyRL.

    Why it matters: vLLM 在发布当天即支持 Inkling 2 Small，并给出内核融合、序列并行和 Gluon 解码内核的具体优化数据，可供部署大 MoE 模型的团队参考。

  16. OpenRouter Announcements58

    OpenRouter explains the self-correcting localization pipeline behind its 7 new languages

    OpenRouter launched beta localization in Simplified Chinese, Spanish, Brazilian Portuguese, German, French, Japanese and Korean, and detailed the self-correcting pipeline that keeps 16,918 English strings translated. The daily loop sends changed strings to GPT-6.1 Sol in batches of up to 40, has code reject broken placeholders and glossary violations, then uses a second call to the same model as a verifier that returns errors by severity for retries. OpenRouter says a full retranslation of the catalog into 7 languages costs about $460, versus about $7,200 at Smartling's published machine translation rate.

  17. OpenRouter Announcements58

    OpenRouter 发布教程：如何阻止 AI Agent 陷入无限循环

    OpenRouter published a guide on stopping AI agents that get stuck retrying a failing tool, using four guards tested on six current models. With doomLoop detection enabled, all six models were blocked on their third identical tool call, and across 18 runs tool calls fell from 314 to 64 while spend dropped from $0.29 to $0.05. The guide adds a loopKey to normalize arguments, stopWhen caps on steps and cost, and a credit limit on the API key that returns a 402 with limit_source openrouter_key_limit.

  18. vLLM Blog64

    vLLM-Omni benchmarks MiniMax H3-Image on Vera Rubin: 0.87s 4K generation and 6,115 images/hour

    vLLM-Omni brought MiniMax H3-Image to NVIDIA Vera Rubin and measured 0.87-second median latency for native 4096×4096 text-to-image on four GPUs, plus 6,115 images/hour in a separate throughput configuration. H3-Image is an open-weight text-to-image and editing model that pairs a Qwen3-VL encoder with a 33.1B dense DiT and an image VAE, handling both tasks in six sampling steps with up to 16 reference images. The team reports MXFP8 DiT GEMMs, Ulysses SP4, AdaLN caching and a VAE decoding change that cut decode time from 2.635s to 0.213s, and lists recipes for AMD, Intel, Huawei Ascend and Moore Threads hardware.

    Why it matters: vLLM-Omni's benchmark shows MiniMax H3-Image running on Vera Rubin at subsecond 4K latency, with per-hardware configurations and a cost model for serving economics.

  19. vLLM Blog72

    vLLM serves DeepSeek-V4.1-Flash on Vera Rubin NVL72 at 58x GB300 NVL72 throughput

    vLLM reports serving DeepSeek-V4.1-Flash on a single NVIDIA Vera Rubin NVL72 rack at 1.7M tokens/s per GPU with 387 tokens/s per user, 58x the GB300 NVL72, peaking at 2.52M tokens/s and 1,810 tokens/s for a single user. The gains come from kernels rebuilt for Rubin's split memory domains and FP4 tensor cores, a specialized TP8 decode path, and rack-wide KV and Engram pools shared over NVLink. With prefixes pooled across the rack and Dynamo workload-aware routing, the prefix hit rate holds at 96.5-97% even at high concurrency.

    Why it matters: vLLM's third DeepSeek-V4.1-Flash post details how Rubin-specific kernels and rack-wide memory pooling lift throughput 58x over GB300 NVL72, offering a concrete reference for large-scale serving optimization.

  20. Hugging Face Blog36

    Hugging Face Releases Fine-Tuning Guide and Scripts for TRELLIS.2 3D Generation

    Hugging Face published fine-tuning scripts and containers for TRELLIS.2, a 3D generation model, runnable locally or on Hugging Face Jobs. The guide uses LoRA adapters via the PEFT library on only the sparse-structure flow DiT and shape flow DiT, leaving the material stage frozen. On a 188-object footwear subset of the GSO dataset, the pretrained model often rendered incorrect soles, which the LoRA fine-tune targets.

  21. AWS Machine Learning Blog36

    Running OpenAI Codex on Amazon Bedrock: Access Paths and Rollout Guide

    This post shows how to route OpenAI Codex model requests to Amazon Bedrock while reusing existing AWS identity, IAM, Regional, and observability practices. It recommends starting with Native AWS Access for a small least-privilege pilot, with AgentCore Gateway or an LLM Gateway as alternatives, and walks through IAM Identity Center sign-in plus a direct Bedrock Runtime check using GPT-5.6 Sol.

  22. AWS Machine Learning Blog46

    Detecting and recovering from silent data corruption on Amazon SageMaker HyperPod

    A PyTorch DDP training loop on Amazon SageMaker HyperPod gains three checks that catch silent data corruption: a non-finite gradient check, a ring replay audit comparing loss bits and gradient fingerprints across nodes, and a weight fingerprint comparison after the optimizer step. Tested with software-injected faults on 4 ml.p5.48xlarge instances (32 NVIDIA H100 GPUs), the checks name a suspect rank, map it to a node, and let HyperPod replace the node and resume from a checkpoint.

  23. AWS Machine Learning Blog41

    Amazon Bedrock AgentCore Web Search API Released

    Amazon Bedrock AgentCore now offers a standalone Web Search API, letting developers call InvokeWebSearch directly from AWS SDKs or the AWS CLI with a single request and no resources to create. It returns ranked results from an Amazon-operated web index, each with a text extract and, when available, title, URL, and publication time, with domain and date filters. Requests are signed with SigV4 and IAM, using the same permission as the AgentCore Gateway route.

  24. AWS Machine Learning Blog36

    What landed for AI builders on AWS in October 2026: Claude Haiku 5.5, GPT-6.1 Terra, AgentCore CLI 1.0

    AWS's October 2026 roundup adds Claude Haiku 5.5, which Anthropic says costs around 75 percent less than Claude Haiku 4.5 for most tasks, plus OpenAI GPT-6.1 Terra on Amazon Bedrock with up to 1 million input tokens and prices at least 50 percent lower than GPT-6.1 Sol and GPT-5.6 Terra. AgentCore CLI reached version 1.0, and AgentCore Gateway added model fallback and Step Functions workflows as agent tools.

  25. MarkTechPost74

    Google launches Gemini Decisions API with Gemini Decision 1 at $0.10 per 1M tokens

    Google launched the Gemini Decisions API, powered by a new model called Gemini Decision 1 (gemini-decision-1), which does not generate text but scores up to 1,000 typed questions against one shared input and returns calibrated probabilities. It reads text, images, audio, video and PDFs in a single prefill pass, supports yes/no, choice and score question types, and is priced at $0.10 per 1M input tokens with zero output tokens billed. Google reports a 262,144-token context, 150-250 ms end-to-end latency, and a top-1 ECE of 0.0250, about half that of TypeSafe Jev 1.14, though it trails Jev on the When2Call benchmark (79.9% vs 82.0%) and costs more per token ($0.10 vs $0.042).

  26. Simon Willison58

    AWS releases official local emulator for testing its services without a paid API key

    AWS has released an official emulator that lets developers run tests against a local clone of its various services without provisioning a paid API key. The emulator is written in Rust and accumulated 29,684 commits in the project's first three weeks, according to a guest post by Swaminathan (Swami) Sivasubramanian on Werner Vogels' blog. It currently requires Docker on macOS and Windows, and Simon Willison hopes a single downloadable binary will follow for use in standard test suites on other platforms and languages.

  27. AWS Machine Learning Blog12

    AWS re:Invent 2026 AI/ML Track: Attendee's Guide

    AWS will hold its annual re:Invent conference from November 30 to December 4, with the AI/ML track offering more than 140 unique sessions out of over 2,000 total learning sessions. The guide maps sessions to the AWS AI stack, spanning AI chips (AWS Trainium and NVIDIA GPUs), models and inference on Amazon Bedrock and SageMaker AI, and agent development with Amazon Bedrock AgentCore. Sessions are organized from newcomer content to technical deep dives, and many can be viewed on demand.