AI is moving beyond the data center as developers build agents that act at the edge, including monitoring driver attention and cabin conditions, helping robots understand surroundings and plan tasks, and coordinating fleets of machines on production lines. These physical AI applications rely on models that perceive, reason, and act within tight memory, power, and latency budgets.
Autoscaling schedules raise the minimum number of replicas before predictable traffic arrives, reducing cold-start delays. Each schedule sets a time window plus minimum and maximum replica counts, can recur or run once, and up to 10 schedules per environment can be configured via dashboard, CLI, or Management API, with non-overlapping windows of at least five minutes sharing one timezone. When no schedule is active, the environment uses its default settings.
Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces policies, along with optimization and observability tools for reliable execution. For production agents, the challenge lies in making these agents capable and safe to operate with access to real enterprise systems and data.
Cloudflare's services for private origins are now generally available, letting customers point a proxied A or AAAA record at a private IP so Cloudflare reaches the origin over existing Cloudflare One connectivity while WAF, caching, bot management, and Workers apply as they do for public origins. The private_routing setting enables automatically for RFC 1918, RFC 6598 CGNAT, and RFC 4193 IPv6 ranges, and no inbound firewall exception is required. Argo Smart Routing and Dedicated CDN Egress IPs are not supported, and origin health checks require Load Balancing.
Claude Code v2.1.314 adds a permissions.blockWritesOutsideWorkingDirectories setting that blocks Write, Edit and NotebookEdit outside working directories in every permission mode, optional IdP group lists for Claude apps gateway upstreams, guardrail_trace logging for Bedrock upstreams, and idle compaction in VS Code and the Claude Desktop Code tab. It also fixes numerous issues, including "Invalid effort level" failures under admin effort caps, claude -p exiting 0 with no output on startup failure, Bedrock sessions with many images failing with "400 Input is too long," and Microsoft Foundry sessions failing when the default model has no deployment.
Rendreal, built with Vstorm using Pydantic AI, lets customers describe a print job and receive print-ready artwork, a quote and a checkout link without leaving a chat, via web chat, a WhatsApp bot or any external assistant connecting to its MCP server. The system covers five product types across three channels, with Pydantic AI validating tool arguments and structured outputs before orders reach validation. Rendreal says assistants get access to its own integrated services, not an open network of independent supplier agents.
OpenRouter rebuilt Guardrails so organization admins can set workspace-wide limits (budget caps, ZDR requirements, model and provider access) that apply to every member and API key, while workspace admins set defaults and per-person exceptions inside those limits. Guardrails are now split into three separate policy types—budget, model and provider access, and content moderation—so each can be changed independently. Existing guardrails keep their IDs and rules, and the guardrails API and Terraform resources continue to work as before.
Factory released Droid 1.0, an agent harness it says outperforms native harnesses built for their models by up to 20% more efficiently on the same tasks, with programmatic tool calling (Script mode) now the default for models including GPT-6.1 Sol, Claude Opus 5.5 and Kimi K3. The post reports that Script mode cuts Droid's cost by 15% on Claude Opus 5.5, that the base prompt shrank 37% between versions 0.170.0 and 0.250.0, and that median time to first paint fell from 1,839 to 488 ms. It also describes the internal Agent Factory loop, in which agents propose harness changes that engineers review before shipping.
Why it matters: A detailed first-party account of harness design choices, benchmark methodology and latency work that is useful for teams building or evaluating coding agents.
Databricks announced that Real-Time Mode (RTM) in Spark Declarative Pipelines (SDP) is now Generally Available, bringing millisecond-range end-to-end latency to SDP while retaining its orchestration, incremental processing, failure recovery and data quality features. RTM streams data continuously and runs all query stages simultaneously, and Databricks reports it was up to 92% faster than Apache Flink on customer feature-computation workloads. Users enable it by setting the pipeline to continuous mode with spark.databricks.streaming.realTimeMode.enabled set to true and defining an update flow with pipelines.trigger set to "RealTime", and can write to custom sinks such as Lakebase or Redis via a ForEach sink.
Version 0.166.0 adds keyboard-driven transcript selection with word, line, and page motions plus integrated search, renders Markdown in async questions and transcript replies, and adds GPT-6.1 Terra to the bundled, Vertex AI, and Amazon Bedrock model catalogs. It also introduces `codex queue --resume`, clearer safety-block explanations with safer follow-up prompts, and `codex doctor --network-only` for focused network diagnostics. Bug fixes preserve acknowledged permissions on resume/fork, restore spawned descendant threads when unarchiving a parent, and improve TUI reconnection recovery.
The Claude Platform release notes list changes to the Claude API, client SDKs, and Claude Console, newest first, with entries from September 1 through October 29, 2026. Recent items include the beta Usage and Cost Analytics API, a raised 128 MB maximum request size for the Messages and Token Counting APIs, the beta Claude Tag API for Claude Enterprise, Claude Models on Google Cloud (Anthropic managed), and API version 2026-10-21 with new SDK and CLI releases. Earlier entries cover the launches of Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5, and Claude Fable 5.1, along with user profiles, organization webhooks, and OpenTelemetry export.
AWS Batch now offers quota management, letting administrators divide compute capacity into quota shares per team or project with RESERVE, LEND, or LEND_AND_BORROW sharing strategies, plus cross-share and optional in-share preemption. The post walks through configuring a Scheduling Policy, Service Environment, and job queue, then submitting SageMaker Training jobs to quota shares via the SageMaker Python SDK v3 aws_batch module.
Suno Studio introduces Chat, an in-house assistant that can create stems and plugins, rename tracks based on clip names, lower all faders by a set amount such as 3dB, add Compressor and EQ effects to every track, and offer creative prompts for writer's block. The post notes that Suno Studio is one of a few DAWs with built-in assistants, alongside FL Studio, Fender Studio Pro and Logic Pro, and is available with every Premier subscription.
vLLM announces day-0 support for Mistral Large 4, a 1T-parameter MoE multimodal model with 49B active parameters per token, running on the V2 model runner with breakable CUDA graphs and a new vllm/models/mistral/ package. The work adds cross-layer KV sharing, DCP/PCP context parallelism, DSpark speculative decoding, NIXL-based disaggregated serving and HiSparse KV offload, plus day-0 ROCm support on AMD Instinct MI350 Series GPUs with MXFP4 experts. Support ships in the vllm/vllm-openai:mistral-large-4 Docker image, with FP8 and NVFP4 checkpoints and serving commands documented.
Why it matters: A detailed engineering account of what it takes to land a frontier model on an inference engine, useful for teams planning long-context or disaggregated deployments.
The author announces two Swift packages: AnySpeechRecognizer, which mirrors Apple's SpeechAnalyzer API while allowing alternative engines such as NVIDIA's Parakeet and Alibaba's Qwen3-ASR running locally on Core ML, plus speaker diarization via NVIDIA's Streaming Sortformer; and AnyDecisionModel, which answers yes-or-no, multiple-choice, and rating-scale questions with typed results and probabilities from backends including MLX, Core AI, llama.cpp, Jev, and Ollama. Both can download open models from the Hugging Face Hub and run them on device, require Swift 6.2 and macOS 26 or iOS 26 or later, and are published on GitHub.
Amp can now visualize or build things directly in a thread, including charts, timelines, diagrams, and clickable mockups. The post shares examples from real threads, such as Quinn's request for ways to fit a diff stat into a small button across desktop, mobile, and tablet platforms.
Amp now offers macOS Satellites: a cloud Mac with Xcode and simulators, booted in about 30 seconds, attached to the thread's Linux orb so Amp can build, run, and test iOS or Mac apps while code stays synced on the orb. Macs start fresh with nothing saved, stay running for 20 minutes after Amp finishes so follow-ups can reuse the same Mac and build cache, and are then deleted. Pricing is $2/hour for mac.medium (6 CPUs, 14 GB) and $4/hour for mac.large (12 CPUs, 28 GB), drawn from included orb usage and then Amp credits; the feature is in beta with a waitlist in Settings → Experimental Features.
Sakana AI announced the Sakana API Platform for enterprise customers and opened its Early Access program, offering its LLMs via an OpenAI-compatible API with management features for handling usage costs and members by organization and workspace. Sakana Fugu and Sakana Fugu Ultra are available first, with Sakana Namazu and Sakana Fugu Max to follow, and features include role-based access control, audit logs with CSV download, a commitment not to use inputs for training, budget limits, invoice payment, and MSA and DPA support.
OpenRouter announced a new default provider routing algorithm that scores endpoints on realized price, time to first token, throughput, error and rate-limit rates, and output quality rather than input token price alone. In a week-long switchback experiment over 24 million requests, the new router cut TTFT p50 by 16.9%, raised throughput p50 by 16.3%, and reduced requests hitting at least one 429 by 67%, with cost per K requests up 6.0%. Explicit sorts, provider.order, and cache-aware conversation pinning still work as before, and price-only routing remains available via provider.sort "price" or the :floor suffix.
Why it matters: Useful for teams on OpenRouter deciding whether to keep default routing or opt back into price-only sorting, since it quantifies the speed, reliability, and cost tradeoffs.
This page is a GitHub Changelog entry titled "0.166.0-alpha.6" and contains only site navigation and product menu text, with no details about the release itself.
LiteRT in Google Play services now offers GPU inference about 1.4x faster than the legacy GPU delegate via ML Drift and the new CompiledModel API, and apps that switch are about 8 MB smaller because the runtime ships with Play services instead of inside each app. The runtime supports phones back to Android 7, plus Wear OS 4+ and Android Automotive OS (Android 11+), and the legacy GPU delegate and custom delegate APIs are deprecated, with NNAPI to be removed starting in 2027.
Sierra announced Compliance Console, built into its Horizon platform, which gives companies configurable guardrails so their agents follow outreach rules across channels, use cases, states, and countries. The controls cover disclosures, contact windows based on recipient local time, holiday exclusions, frequency limits, and opt-outs, with Insights dashboards showing how many outbound calls and messages were allowed, deferred, blocked, or held for review.
PyTorch 2.15 makes the rewritten NCCL backend the default for all nccl process groups, with a flight recorder that dumps diagnostics on hangs and TORCH_DIST_USE_NCCL2=0 or nccl-legacy as rollback paths. It adds one-sided transports for torch.distributed with a NIXL backend, finer FSDP2 and pipeline parallelism memory and communication controls, NVFP4 decode improvements on Blackwell, FP8 and faster decode on Apple Silicon, and broader platform support including FlyDSL on AMD gfx950, ROCm 10.0 wheels, CUDA 13.2 as the default wheel, and torch.compile on Python 3.15. The release contains 3,117 commits from 583 contributors since 2.14, and Python 3.10 and macOS 14 are no longer supported.
Anthropic announced that smart reports, in-app surveys, and pooled group budgets are now generally available for Claude Enterprise. Smart reports analyze a sample of a team's transcripts to group work into workstreams with spend, deliverables, friction points, and recommendations, while in-app surveys collect team feedback and pooled group budgets give a group one shared monthly budget with member limits as a guardrail. Availability varies by configuration, including HIPAA configurations and customer-managed encryption keys.
Databricks argues that voice agents are now practical because synthetic voices sound natural and can respond within roughly 200 milliseconds, but that most enterprise AI investment has focused inward on employee assistants rather than customer conversations. It describes a prototype in which LiveKit carries calls, Deepgram handles speech-to-text, ElevenLabs adds voices, and Databricks supplies the "brain" that looks up caller context, applies business rules, and records each decision, built on context, ontology, and governance. The post outlines three pillars—grounding answers in business data, fast and slow AI decision-making including the ai_decide capability, and a learning loop from recorded calls—and points to the open-source DIVA blueprint on GitHub and a suggested 90-day pilot.
Mastra now offers span queries that filter and group individual spans across traces, letting you return only matching spans rather than whole traces. Span queries are available in Mastra platform and Studio, the Mastra CLI ([email protected] or later), the Mastra Client SDK, and HTTP observability endpoints, and work on self-hosted projects where storage.observability uses DuckDB, PostgreSQL, or ClickHouse. Each query can combine up to 100 conditions, returns up to 1,000 spans per page, and span groups can group by up to 2 dimensions over a time range of up to 365 days.
IDC worked with Anthropic to make IDC Quanta available in Claude, giving customers access to IDC's forecasts, market data and research through an MCP connector that returns cited analysis in the Claude app, Cowork and Microsoft Office add-ins. IDC also rolled Claude out company-wide, where engineers rebuilt an internal data repository in three weeks instead of an estimated three months and code review time fell from five days to about 30 minutes.
GitHub has released Copilot Fusion in GitHub Copilot, a runtime orchestration system that selects and coordinates models from Anthropic and OpenAI, including Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra and GPT-6 Sol, to optimize performance, cost and latency per task. In Artificial Analysis' Coding Agent Index v2.0, its max setting in GitHub Copilot CLI scored 2 points below Opus 5.5 in Claude Code at half the cost per task ($5.59 versus $11.42), leading Terminal-Bench 4.0 at 71 while ranking third on FrontierCode at 51 and scoring 57 on SWE-Atlas-QnA-AA. It used 7.2M tokens per task, roughly half of Claude Opus 5.5 in Claude Code and 30% less than Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high).
Why it matters: Offers concrete benchmark and cost comparisons for a multi-model orchestration approach, useful for readers weighing coding-agent performance against token spend.
NVIDIA announced RTX Spark laptops from ASUS, Dell, HP, Lenovo, Microsoft and MSI, combining a Blackwell RTX GPU and Grace CPU with up to 128GB unified memory and up to 1 petaflop of FP4 AI performance, starting at $2,599. Updates include the open-weight Nemotron 3.5 Transcribe speech model, Liquid AI's LFM3 family with day-zero support, and resource management controls in NVIDIA App for sharing GPU resources between foreground apps and background agents. Phantom Blade Zero launches Oct. 28 with ray tracing and DLSS 4.5, and RTX Remix 1.6 brings path tracing and DLSS to Minecraft Java Edition 1.21.1.
Anthropic introduced ready-to-use artifacts for legal professionals, including a gallery with tools for cite checking, jurisdiction surveys, matter boards, playbook deviation tracking, regulatory horizon scanning, and tabular contract review, each opening with an example and linking outputs to sources. The company said it has added more than 60 legal connectors since launching Claude for Legal in May, and it partnered with legal tech companies and law firms such as Goodwin, Harvey, Foley & Lardner, and PwC on artifacts. The gallery also includes nine access-to-justice artifacts, five built by supported nonprofit and public interest organizations, and Anthropic is launching a Legal Ambassadors Program with a waitlist.
You can now self-host orbs without being in a workspace: personal providers can be added under Settings → Orbs and configured the same way as workspace providers. Threads created this way appear under Self-Hosted and are marked Personal.
The openai/codex repository published the rust-v0.166.0-alpha.5 release tag, tagged by fcoury-oai on 28 Oct at 02:58. The release page lists two assets.
OpenAI's Codex repository published the rust-v0.166.0-alpha.4 release tag, tagged by fcoury-oai on 27 Oct at 23:31. The release page lists two assets.
Together AI describes its automatic node remediation system for GPU clusters, which detects faults from both inside the VM (Xid errors, DCGM ECC and thermal signals, Node Problem Detector) and on the host (InfiniBand rail state, host reachability), then recommends and optionally executes repairs. Repairs follow a cordon-wait-drain-act-rejoin lifecycle with an escalation ladder from reboot to quick reprovision to migration, governed by per-fault consent, wait-for-idle controls, concurrency budgets, cooldowns, and a circuit breaker. Migrated or removed machines are automatically re-validated with GPU, NCCL, InfiniBand, and storage checks, and only an explicit failure files a hardware ticket.
Many AI workloads need only a fraction of a GPU, and giving each one a whole device can leave capacity idle, so sharing GPUs lets platform teams serve more workloads with existing infrastructure. NVIDIA GPUs already support several sharing approaches, including Multi-instance GPU (MIG), which splits a GPU into hardware-isolated instances that are transparent to the application.
Claude Code v2.1.312 adds an oidc.user_id_claim option to the Claude apps gateway for identifying users by an id_token claim other than sub, and lets fullscreen users send a queued message by clicking the "to send now" hint. It fixes issues including managed settings not being fetched after VS Code extension sign-in, Claude overwriting large CLAUDE.md or rules files after reading only their start, per-directory and paths: skills not found after a Bash cd, and a Read tool PDF failure. Other changes include limiting prompt and agent hooks to 24 at a time per session, renaming the "session limit" to "5-hour limit" in usage messages, and various VS Code, cloud session, Remote Control, Claude Tag and Code Review fixes.
Anthropic released Claude for Financial Advisors, a suite of connectors and workflow skills for research, meeting prep, and documentation tasks. Connectors include Addepar, BlackRock, Charles Schwab, Envestnet, FactSet, Orion, Vanguard, and others, while skills cover pre-meeting prep, portfolio rebalance review, post-meeting follow-up, estate and tax briefs, and compliance checks. The advisor plugin is available today, with Enterprise plans recommended for audit logs, and firms requesting a new license before the end of September 2026 receive a one-time usage credit.
This release adds a built-in Google Cloud Vertex AI provider configured with model_provider = "gcp", adds GPT-6.1 Terra to the model catalogs, and adds a repository filter to the session picker plus directory grouping in the agent command center. It also enables reasoning effort changes during a conversation by default for supported models, turns on memory v2 by default for fresh profiles with support for importing external-agent memories, and adds experimental attached thread forks to the app-server API. Bug fixes include honoring the server's default approval reviewer on fresh TUI sessions, cancelling remote MCP tool requests when local response futures are dropped, treating model-not-found provider errors as terminal, and closing a marketplace URL validation gap involving backslashes in userinfo.
Databricks introduces Vital Skills, packaged playbooks built on the open Agent Skills standard that give Genie Code healthcare and life sciences domain knowledge, such as cohort building, HIPAA de-identification, RNA-seq analysis, and open-weight model deployment. On BiomniBench, Genie Code's average score on the 5 in-scope tasks rose from 71.9 to 76.9 across three trials, while scores on 18 out-of-scope tasks held steady. The skills are open source and installable in Genie Code, Genie One, or Genie Code CLI.
Check Point is using OpenAI Daybreak to speed up the research behind new security protections. The company says this lets its analysts turn vulnerability intelligence into customer defenses faster.