Skip to content
Only First-party
TodayNovember 13Friday45 items
  1. 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.

  2. 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.

  3. 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.

  4. 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.

  5. Replit Blog65

    Replit Agent adds Link and Visa purchasing plus Google Ads campaign creation

    Replit Agent now has two new jobs: buying business supplies through Link and Visa, and building Google Ads campaigns across Search, YouTube, Display and Discover. In the purchasing flow, a browser subagent navigates the merchant site and prepares checkout, then waits for the owner to approve the final total; shell access and general browsing are disabled during payment and approval checks are enforced in code. Agentic Commerce is available for Core and Pro users starting in the US with one-time purchases only, while Agentic Ads is available for Pro users worldwide.

    Why it matters: Replit Agent now handles purchasing and Google Ads campaigns, with code-enforced approval gates that show how agent spending limits can be designed.

November 12Thursday
  2. 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.

  3. 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.

  4. NVIDIA Newsroom88

    NVIDIA Announces CEO Transition as Jensen Huang Resigns, Colette Kress Named Interim CEO

    NVIDIA's board announced that Jensen Huang has resigned as President, CEO and board member effective immediately, with Executive Vice President and CFO Colette Kress serving as Interim CEO while the board searches for a permanent successor. The board also appointed Harvey C. Jones, former CEO and Executive Chairman of Synopsys, as its first-ever Chair of the Board, and said it expects operations, customer commitments and product roadmap to continue without interruption. NVIDIA said it will report third-quarter fiscal 2027 results on November 17 as previously scheduled.

    Why it matters: NVIDIA's board names CFO Colette Kress as interim CEO after Jensen Huang's immediate resignation, with Harvey Jones becoming first board chair.

  5. Meta Newsroom · AI18

    Meta Signs Long-Term Purchase Agreements for Lower Carbon Cement, Steel, Trucking and Recycled Plastics

    Meta has signed a set of long-term purchase commitments covering cement, steel, trucking and recycled plastics to bring clean manufacturing to commercial scale in its data center supply chains. The deals include at least 180,000 tons of lower carbon cement from Sublime Systems, near-zero-emission steel from Sweden-based Stegra, an expanded zero-emission freight route with Nevoya along I-10 in California and Arizona, and 5,000 tons per year of recycled PET with MacroCycle Technologies.

  8. OpenAI Alignment Blog58

    OpenAI uses automated red teaming to improve fuzzy robustness in GPT-6 Astra and Sol

    OpenAI researchers describe how automated red-teaming, using a GPT-5.6 Sol family reasoning model as attacker against GPT-5.4 and GPT-5.5 defenders, generated synthetic jailbreaks that were used as RL training data for GPT-6 Astra and Sol. On fixed jailbreaks from prior attacks against GPT-5.4 and 5.5, GPT-6 Astra answered 91.5% safely on cyber versus 59% for GPT-5.6 Sol, and it stayed more robust across all attacker budgets in an adaptive multiturn eval. OpenAI reports the robustness training did not raise refusals of benign tasks, citing a Pareto improvement on safety and helpfulness in the GPT-6 Astra system card.

  9. 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.

  10. 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.

  12. 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.

  13. 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.

  14. 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。

  15. 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.

  16. 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.

  17. OpenRouter Announcements28

    How to Benchmark LLMs: A Code-Graded Guide from OpenRouter

    OpenRouter published a guide for benchmarking LLMs on your own application's inputs, grading outputs with code and comparing accuracy, billed cost and request time. On its 60 synthetic tasks, GPT-6.1 Sol passed 180/180 trials across three repeats, while DeepSeek had the lowest response cost at 157/180 passes. Agreement with the public ranking was weak, with a Spearman correlation of 0.109.

  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.

  20. 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.

  21. Apple Machine Learning Research38

    Theoretical Limits of Language Model Alignment

    Researchers from Apple Machine Learning Research derive the information-theoretic limits of KL-regularized language model alignment, giving a closed-form expression for maximum expected reward gain under a fixed KL budget that is governed by a Jeffreys divergence term rather than the √KL used in prior analyses. They show the gap between ideal and proxy alignment (reward hacking) grows with reward error and shrinking KL penalties, and prove reward ensembling mitigates it. On safety and summarization tasks, best-of-N closely approaches the theoretical limit while PPO and GRPO remain substantially suboptimal.

  22. 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.

  23. 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.

  24. AWS Machine Learning Blog34

    Semantic diffing of formal policies with anti-unification

    An open source engine computes semantic diffs of formal policies using anti-unification over an e-graph, showing shared structure once and keeping both versions of each differing part. It targets autoformalization outputs in SMT-LIB, Cedar, Dogwood, OpenShell policies and CEL, where an LLM writes the artifact but plays no part in computing the diff.

  25. 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.

  26. 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.

  27. 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.

  28. 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.

  29. AWS Machine Learning Blog28

    Automating AWS Agent Registry updates with a push-based architecture

    AWS outlines an event-driven pipeline that keeps AWS Agent Registry records for MCP servers current without manual updates. AWS CloudTrail captures UpdateAgentRuntime API calls, Amazon EventBridge routes them across accounts, and a Lambda function queries the MCP server's tools via AgentCore Identity OAuth tokens, then diffs and updates the matching registry record. The sample updates existing records only and supports both single- and multi-account setups.

  30. Google Research58

    Google Research uses wearables to build CKM risk profiles and personalized coaching

    Google Research introduced an investigational framework that turns consumer wearable data into a coachable health age and simulates personalized 12-week what-if health trajectories. The SensorWM world model was pretrained on 2.28 million person-weeks of de-identified Fitbit data from roughly 100,000 users and forecasts 20 physiological markers under different step, sleep and cardio routines. In a blinded study, lifestyle coaches chose the counterfactual-grounded plan as best overall in 71.4% of evaluations, and physicians rated 99.2% of plans within safe exercise intensity limits; the authors note the models are research prototypes, not clinical diagnostic tools.

  31. Google Blog · AI78

    Google launches Gemini Decisions API and Gemini Decision 1 model for fast closed-set decisions

    Google introduced the Gemini Decisions API, powered by the new Gemini Decision 1 model (gemini-decision-1) and available through the Gemini API in Google AI Studio. A single multimodal input of up to 256K tokens can be checked against up to 1,000 yes/no, multiple-choice and rubric-scoring questions in one forward pass, returning probabilities and confidence scores at 150-250 ms end-to-end latency for $0.10 per 1M input tokens with no output-token charges. Google says the model leads its benchmark suite with the lowest calibration error and is nearly 5x cheaper than Gemini 3.5 Flash-Lite with the Interactions API; internal uses include model routing in Gemini Notebook, wireframe generation in Stitch and adversarial-content checks for MCP tools in Search.

    Why it matters: Google's new endpoint scores up to 1,000 multimodal yes/no, choice and rubric questions in one pass at 150-250 ms, giving agent routing and policy checks a cheaper alternative to generative calls.

  32. Amazon Science36

    Using Mathematics to Validate Network Configurations: AWS Tiros for Segmentation Checks

    AWS is using its automated-reasoning tool Tiros to statically validate network segmentation across all modeled paths, rather than relying on packet-based sampling. Tiros converts Cloud WAN configurations from route tables, attachments, and policy documents into logical propositions, then checks that no path exists between segments the policy declares off limits, with analyses run as often as every hour.

  33. Meta Engineering Blog40

    Meta Intelligent Delivery: ML System Allocating Compute for Ads Ranking

    Meta detailed Intelligent Delivery, an ML-driven system that allocates compute across its ads serving stack toward the system-wide optimum, contributing roughly 10% incremental ranking performance on top of model and system advancements from 2017 through the first half of 2026. Its Resource Core Model uses 6B sparse and 20M dense parameters to predict each request's marginal utility, and Meta says it improved identification of high-impact ad requests by about 20% in offline benchmarks. The system also relies on multi-layered allocation mechanisms and increasingly agentic AI to adapt as models and hardware change.

  34. Google Developers Blog58

    Google engineer uses Gemini 4 Argon and Z3 to catch Go bounds-check bugs fuzzing misses

    A Google engineer who leads the company's agent skills program built a pipeline in which Gemini 4 Argon reads Go source and RISC-V disassembly and translates surviving runtime.panicBounds traps into Z3 constraints, then go test replays any satisfying input as a real reproducer. The workflow caught all three planted bugs and three latent bugs in skill-lint, while unseeded go test -fuzz missed two of the planted crashes because Go checks slices against capacity rather than length. Clipping capacity to length with data[:len(data):len(data)] made the fuzzer crash both overrun bugs in all three runs, with a median of 0.28 s and 0.17 s.

  35. Google Developers Blog58

    Google Agent Anomaly Detection scores on five public agent-security benchmarks

    Google ran its Agent Anomaly Detection, in Private Preview on Gemini Enterprise Agent Platform, against five public agent-security benchmarks it did not write, scoring 1,774 sessions. It flagged 87% of harmful instructions the agent actually carried out, with false alarms on 2% to 16% of benign sessions, and caught only 4 of 18 sessions where poisoned long-term memory drove the agent to act. The tests used an agent built with the Agent Development Kit (ADK) on gemini-2.5-flash, covering AgentDojo, InjecAgent, Agent Security Bench, AgentDyn and AgentHarm.