iCreatAI News
Back to main site
Skip to content
#Deployment
Nov 8Sun
  1. Hacker News AI15

    Why the Best AI Clouds Don't Run on Flash Alone

    Neoclouds built around GPUs rely on flash storage for active training, but other lifecycle stages—data ingestion, checkpointing, and storing finished models—need cheaper high-capacity storage, which neoclouds often outsource to hyperscalers whose egress fees create data gravity. The article argues a tiered storage architecture, with flash only where speed is required and high-capacity storage elsewhere, lets neoclouds keep the whole customer account, citing Backblaze's B2 Neo as a white-label option. It notes SSD prices rose 257% in under a year and that Google, Meta, and Microsoft have run tiered storage for years.

  2. Hacker News AI58

    RigHaven – Self-hosted execution harness for AI agents

    RigHaven is a self-hosted platform where a coordinator composes a team of roles for a stated objective, selects from 99 managed CLI tools, and runs each role in its own isolated container through review and delivery. It supports human approval at each phase, policy enforcement by the runtime, connections to databases and IoT devices, and deployment on Windows, Linux, a VPS, or from source. It is MIT licensed and authored by Marco Gramuglia.

  3. SemiAnalysis58

    We Visited China’s Stargate in Inner Mongolia

    SemiAnalysis reports on a September visit to Inner Mongolia's datacenter region, including Galaxy, an Envision-owned campus in Ulanqab planned for up to 800MW of IT capacity whose first 120MW phase was delivered within a year at a fifth of US costs. The report describes Envision's vertical integration—its own wind farms, a dedicated power line, an 800V DC solid-state transformer pilot, and a chiller-less cooling design—and compares Galaxy's scale to Stargate's Abilene campus. It also notes Inner Mongolia has lined up 25GW of announced datacenter projects.

  5. Hacker News AI50

    Show HN: Chatty – Open-source AI support engine with WooCommerce sync

    Chatty is an MIT-licensed, self-hostable AI customer support engine positioned as an open-source alternative to Zendesk and Intercom, offering streaming chat, RAG over your own documents, lead capture, meeting booking, and human takeover. It supports seven messaging channels (WhatsApp, Messenger, Instagram, TikTok, Telegram, Twilio SMS, and inbound email), WooCommerce order and inventory sync, a LiveKit voice agent, and an 81-tool FastMCP server for agent-driven dashboard control. Deployment uses Docker Compose with managed Supabase for Auth, Postgres, Storage, and Realtime, and supports bring-your-own-key LLM providers including Gemini, OpenAI, Claude, and OpenRouter.

  6. Hacker News AI34

    AI Promoted Everybody. Architecture as Truth (AAT) Is the New Job

    PuglieseWeb founder Emanuele Pugliese argues that AI now handles most production work—drafting scenarios, docs and pull requests—so deep end-to-end understanding of the product has become the entry requirement rather than a senior specialism. He defines Architecture as Truth (AAT), a practice in which versioned architecture documents (decisions, contracts, behaviours and plan) are the single source of truth that people decide through and AI agents build from, held up by five principles and four rules for agents. He illustrates it with a 30–31 October reminder feature built by an agent, where the owner caught an unspecified phone number in the reminder text, and notes SystemDox, his tool for serving the same documents to people and agents over MCP, is in private preview.

  7. Hacker News AI36

    Infinix – Abandoned Local AI Agent Base Seeking Developers

    Infinix is an abandoned open-source local autonomous AI agent for Windows and Linux, built by Moonyeep with Manus AI on the ZeroScript architecture, that is controlled through supported browser-based AI chats and provides endpoint diagnostics, workspace tools, browser automation, shell access and multi-agent delegation without a separate model API key. It supports eight providers (DeepSeek recommended, plus ChatGPT, Gemini, Kimi, GLM, Qwen, Arena and Meta AI) and an optional Roblox Studio MCP integration, and is released under GPL-3.0 with the requirement that derivative works stay free and open-source. The creator is seeking developers to fork and improve the working but unfinished codebase.

  8. Hacker News AI30

    Let's Encrypt AI: protect AI chats with on AI GPUs by the end of 2027

    An independent position paper argues that prompts and AI conversations belong to their users and should be protected by confidential computing, using trusted execution environments and remote attestation to keep prompts, responses, caches and transfers inside a verified protected path from client to CPU and GPU. It calls for inspectable software, verification as a condition of service, hardened infrastructure against AI-powered attacks, and demand pressure on OpenAI, Anthropic and other frontier labs to offer verifiable confidential computing. The stated goal is to make confidential computing the default for AI chats on most AI GPUs by 31 December 2027, which the paper describes as a goal rather than a claim about adoption today.

Nov 7Sat
  1. Hacker News AI38

    AI agents are getting more complex. Developers shouldn't have to babysit them

    Thoughtworks' Vanitha Kumar describes harness engineering, which equips coding agents with automated tests, feedback loops and guardrails so they can self-correct before human review and run longer tasks with less intervention. She compares AI factories, which standardize infrastructure for model selection, workload management and cost optimization, to Kubernetes, and predicts security will be a major topic within a year. Thoughtworks' Technology Radar Volume 35, released November 4, 2026, emphasizes AI, harness engineering and established practices like penetration testing that are regaining importance.

  2. Hacker News AI58

    Honeycomb Team Agents: AI SRE Done Right

    Honeycomb is previewing Team Agents, AI SRE agents that run in the background on user-defined goals—such as verifying releases, flagging Lambda spend, improving instrumentation, investigating alerts, and maintaining docs—and report findings with linked evidence. The agents are built on Honeycomb's high-cardinality traces, use MCP connectors for additional context, and offer per-goal autonomy levels from Observe to Operate with per-action permissions. Personal agents will be included on every Honeycomb plan, while Team Agents will be available with Honeycomb Intelligence on Pro and Enterprise plans, priced by hours of agent work, and generally available at AWS re:Invent on December 1.

  3. Hacker News AI58

    Securing AI Agents [at Uber]: Lessons from Real-World Deployment

    Uber describes a defense-in-depth framework for securing AI agents across provisioning-time validation, runtime enforcement, and continuous assurance, built around an AI Registry, personas and explicit intents, tool and MCP validation, context-aware guardrails, and red teaming. At runtime, AI Guard acts as a policy decision point using small locally hosted models, while prompt provenance and evidence chaining correlate privileged actions back to what the user actually requested. The post also covers tradeoffs around false blocks, latency, and developer adoption, and argues that restricting agents to explicit intents and constraints was the most effective mitigation.

  4. Hacker News AI50

    The Pentagon wants to know who checks code when AI writes it

    DoW Instruction 8430.01, effective September 8, 2026, treats AI-generated code as unverified input that must be reviewed and tested to the same standard as human-written code, with AI's role made traceable and data kept on approved systems. The instruction, issued by DoW CIO Kirsten Davies, applies to every DoW organization and any acquisition program that includes software regardless of cost, and holds developers fully accountable for the security, functionality, and integrity of AI-generated or modified code. The article describes how GitLab features such as audit events, merge request approval policies, and self-hosted Duo Agent Platform are positioned to address these traceability, verification, and data-boundary requirements.

  6. MarkTechPost58

    Buoyant Releases Kinference: An Open Source Inference Control Plane for Kubernetes and vLLM

    Buoyant, the company behind Linkerd, has released Kinference, an Apache 2.0 inference control plane (v0.1.0-alpha.7, written in Rust) that sits in front of vLLM workers on Kubernetes to apply routing policies, KV-cache-aware load balancing and per-tenant metrics, configured through five CRDs. In Buoyant's self-reported benchmark using three L40S GPUs per pool, median TTFT on shared-prefix traffic fell from 6.88 s to 0.31 s versus plain Kubernetes Service routing, while prompts without shared prefixes showed no significant gain (6.92 s vs 6.83 s). The project is in alpha, with rate limiting, classifiers and Anthropic API support not yet shipped.

  7. Hacker News AI42

    Show HN: Service for the parallel execution of AI agent tasks on remote devices

    Rungrid is a service that lets you describe a task once and select multiple machines, then runs a separate agent instance on each paired runner using one shared agent configuration. Each agent reasons and calls tools only on its own runner's machine, supporting tasks like checking installed software versions, collecting CPU, memory and disk metrics, and inspecting logs or attempting targeted fixes. A runner is described as a background program on a local machine, not an AI agent.

  8. Hacker News AI58

    Show HN: Select – AI agents that earn autonomy through verified work

    Select is a multi-agent system where agents in roles like support, sales and marketing work under YAML delivery contracts whose checks are run by code, with receipts kept, and earn promotion from supervised to sampled to autonomous per task type based on verified successes, reverting on failure or human correction. It is at version 0.2, with Docker/Compose startup and end-to-end tests covering accounts, guided setup, local IMAP/SMTP mail and the verification loop, but real model API calls and real mailboxes have not yet been verified. Payments, contracts, taxes and hiring remain always supervised in code, and no benchmarks have been published yet.

  9. vLLM Blog38

    Migrating vLLM to the LibTorch Stable ABI

    vLLM describes migrating its C++ backend to the LibTorch Stable ABI so that updating PyTorch no longer requires rebuilding vLLM, and as of v0.33.0 it publishes LibTorch ABI Stable CUDA wheels. The migration involved moving AutogradFunctions and meta functions to Python, building a separate stable library with the TORCH_TARGET_VERSION flag, registering ops via STABLE_TORCH_LIBRARY with TORCH_BOX, and migrating seven LibTorch-dependent dependencies including FlashMLA, DeepGEMM, FlashAttention-2/3, DeepSelect, FlashKDA and QuTLASS. Verification used torch-abi-audit, now in vLLM CI, and the post notes tradeoffs such as the limited stable API subset and small host-side overhead, with CPU and ROCm builds planned next.

  10. Hacker News AI58

    Show HN: Goethe – The infrastructure for self-hosted AI

    Goethe turns a Linux machine with NVIDIA GPUs into a self-hosted API compatible with OpenAI, Anthropic and LiteLLM clients, letting you install, load and share models in three steps. It serves every loaded model at one address, supports rate-limited and revocable keys, and offers network options including local-only, VPN or public IP. It requires an NVIDIA driver (580+ for GeForce/TITAN cards) and ships its own CUDA 13 runtime, with support for Blackwell, Hopper, Ada and Ampere GPUs.

  11. GitHub Blog · AI & ML36

    Beyond code generation: A developer’s guide to agentic engineering

    GitHub reports over 1.2 billion commits in one week this October, more than 400% above a year earlier, while a Faros AI study found pull requests spent 441% longer in review as teams moved from low to high AI adoption. The post outlines an agentic engineering workflow across Plan, Build, Verify, and Observe, describing Copilot features such as Plan Mode, cloud sandboxes, session continuity, stacked pull requests, Copilot code review, Agentic Autofix, and Agent Merge. It advises starting with one frustrating piece of work and putting an agent on it before expanding across the process.

  12. NVIDIA Technical Blog30

    Speed Up Image Generation with FLUX 3 Image Klein on NVIDIA Blackwell GPUs

    The article addresses inference latency when deploying diffusion models in design tools, image editors, and visual production workflows, noting that generating an image requires multiple sequential passes through a model with billions of parameters and that higher resolutions increase attention costs. It introduces FLUX 3 Image Klein, an image editing and generation model from Black Forest Labs (BFL), and covers speeding it up on NVIDIA Blackwell GPUs.

  13. ElevenLabs Blog30

    Voice AI infrastructure: The 2026 stack explained

    This guide describes the layers of a production voice AI stack—speech recognition, turn-taking, language models, orchestration, tools and MCP, knowledge and memory, speech synthesis, telephony, and guardrails, testing, and monitoring—and explains how ElevenAgents implements each, using Eleven v4 as the example voice layer. It covers two build modes (Custom and Realtime), Scribe v2 Realtime transcription at roughly 150 ms, a proprietary turn-taking model, workflow orchestration nodes, MCP tool approval modes, RAG latency reduced from 326 ms to 155 ms, and Eleven v4 Turbo figures of about 100 ms inference latency and about 150 ms time to first speech. It also details Guardrails 2.0, simulation and tool-call tests, A/B experiments, and observability metrics.

  14. Hacker News AI58

    Show HN: AJX – Find out where AI agents get stuck using your product

    AJX is an open-source skill and CLI for agent usability testing that lets you test how AI agents use your website, CLI, SDK, API, or developer tool, recording the attempt, checking the result, and showing where the product made the task harder. It reports elapsed time, retries, and token usage where the harness exposes it, and produces a report connecting each proposed product change to supporting events plus a timeline of forks, blocks, waits, and recoveries. It supports local or Docker execution, comparison across harnesses and models, and CI runs via `ajx ci` that write JSON and JUnit results.

  15. Hacker News AI22

    Ballast – cold email infrastructure with AI and MCP

    Ballast is a cold email platform that charges per email sent rather than per mailbox or seat, with unlimited mailboxes, seats, warmup outside the quota, a Unibox, and API/webhooks/MCP access included on all five plans starting at $19/month for 20,000 emails. It paces sending per mailbox with random 4–10 minute gaps, routes SMTP mailboxes over static mail-only IPs, runs nightly SPF/DKIM/DMARC checks, and pauses mailboxes, campaigns or workspaces when bounces exceed a threshold. Every app action is also an MCP tool for Claude, ChatGPT and Cursor, with confirming calls required before anything sends, imports or deletes.

  16. Hacker News AI58

    VFlash: Enabling System-1 VLMs for Physical AI

    VFlash is a generalist decoding framework for Physical AI that adapts VLM speculative decoding by exploiting the known structure of visual primitives, using a lightweight drafter trained on annotated geometry to generate complete primitives in one parallel pass while the target VLM stays frozen. It reduces mean 3D displacement error by 42.6% relative to the autoregressive target across three robot datasets and three target variants, and reaches 70.2% average success on MolmoSpaces versus 62.6% for the baseline. On Jetson Thor, DGX Spark, and H100, VFlash cuts decoding latency by 12–42×, yielding 5× faster robot inference and over 3× faster NAVSIM driving inference on Jetson Thor and DGX Spark.

  17. Hacker News AI60

    Microsoft plans to use fewer neoclouds as AI buildout shows signs of strain

    Microsoft is evaluating which neocloud partners to stop using as it prioritizes its own data centers, according to people familiar with the matter, and it opted not to renew a deal with Oracle. The company has worked with CoreWeave, Nebius, Chronoscale, IREN, Lambda and Nscale, and has already scaled back work with Nscale, including a site in England and a Texas contract. Neocloud shares have fallen sharply amid rising borrowing costs and debt concerns, and Microsoft reported $45.2 billion in capital expenditures and finance leases in its latest quarter.

  18. OpenRouter Announcements38

    How Sentry Capped Runaway AI Bills Without Restricting Access

    Sentry moved its internal AI usage onto OpenRouter in July 2026, retiring roughly 500 Anthropic and OpenAI keys over about three weeks and switching off direct access to both providers in August. Keys are bound to users or workspaces so spend can be traced to an owner and model, and per-person and per-workspace budgets cap runaway bills. Sentry says the change gave it tighter control and wider model access at the same time, with 45+ apps and 147 models used in the first three months.

  19. ElevenLabs Blog22

    Share your ElevenMusic creations directly to SoundCloud

    ElevenMusic launched a SoundCloud integration that lets users connect their SoundCloud account under Linked Accounts in profile settings, then add a description, genre, and tags to an original track and click "Save to SoundCloud" to upload it to their profile. SoundCloud Artist Pro members can get three months of ElevenMusic free, then $9.99/mo unless canceled; the offer is 18+, ends 31 Oct 2027, and terms apply.

  20. Hacker News AI55

    GoLand's Profiler Now Works with AI Agents – The JetBrains Blog

    GoLand 2026.3 lets AI agents use its built-in profiler through a bundled goland-profiler skill and MCP tools, so an agent can launch the app with the profiler, pick and capture suitable profiles, read the results, and point to the responsible code. The workflow is tested with Claude Code, Codex, and Junie, and captured profiles appear in the profiler session and Recent profiles in the Go Optimization tool window. Limitations include that the profiler cannot attach to an already running process and short-lived programs leave too little time to capture useful data.

  21. Hacker News AI50

    Auria Chain – SDK for AI agents to pay AI agents over HTTP (x402)

    Auria Chain is an SDK that lets AI agents pay other AI agents over plain HTTP with on-chain settlement, no human in the loop and no new token. It provides createSellerMiddleware to paywall an Express route and createBuyer to make payments, plus a two-agent demo where a seller does paid Claude work and a buyer pays in testnet USDC. It is published on npm as auria-chain and is testnet only (Base Sepolia) via the public x402.org facilitator, with production (Coinbase CDP facilitator, mainnet) not yet wired up.

  22. NVIDIA Technical Blog22

    Accelerating Reinforcement Learning Weight Refit with the Reshard Collective

    This post discusses how reinforcement learning post-training generates trajectories by running inference with the current policy model, and how disaggregated setups run inference and training in parallel on separate GPU resources for efficiency. Because the policy model is updated only on the training GPUs, the system must periodically refresh the weights on the inference side, and the post introduces the Reshard Collective to accelerate this weight refit.

  23. Hacker News AI58

    We stress-tested AI spend limits under bursts and outages

    The authors tested LiteLLM v1.106.6 and Revenium Python SDK 0.12.0 in October 2026 with a $0.05 per-customer budget on gpt-4o-mini, finding that a well-configured LiteLLM held budgets to within about 2.5% even through a database outage, while several of its safest behaviors are off by default. Revenium's accounting matched the authors' tally to within $0.00004, but its enforcement works from a copy of rules refreshed on a timer, so overshoot grew with spending rate and reached 117% at the 60-second default refresh. The piece lists recommended settings for both tools and notes Revenium fixed an enforcement URL issue in SDK 0.12.1, released October 31, 2026.

  24. AWS Machine Learning Blog40

    Serverless MCP server for AI agent data lake access on Amazon ECS Fargate

    Amazon's North America Sort Center team built a serverless Model Context Protocol (MCP) server on Amazon ECS Fargate that acts as a centralized, agent-agnostic gateway between AI agents and the enterprise data lake. Adding a dataset requires only a metadata JSON file, which the pipeline indexes into Amazon Bedrock Knowledge Bases, while Amazon Cognito authentication, SELECT-only Athena tools, Bedrock Guardrails, and CloudWatch logging provide centralized controls. The architecture separates the tool layer from the agent layer so any MCP-compatible client can share the same tools and access controls in a multi-tenant environment.

  25. AWS Machine Learning Blog58

    SageMaker Inference now supports Multi-Instance GPU to maximize GPU utilization for model endpoints

    Amazon SageMaker Inference now supports NVIDIA Multi-Instance GPU (MIG) partitioning on inference component endpoints, letting you divide a physical GPU into up to seven hardware-isolated partitions and place a different model in each. Partitioning is declared via AcceleratorPartitionLayouts on the endpoint config and AcceleratorPartitionType on each inference component, with no new API operations or IAM actions. In testing, a mig-3g.40gb partition of an H100 delivered 53–89% more output tokens per second and 18–34% lower cost per million output tokens than a full A100-40GB above a workload-dependent concurrency crossover.

  26. Hacker News AI58

    AI Product Team – 64 specialized AI agent roles with executable CLI workflows

    AI Product Team is a package of 64 specialist agent roles, 28 shared methods and 12 workflows for building AI features inside Claude Code and Codex, where a plain-language product question routes only the specialists it needs and records what each conclusion rests on. It requires Python 3.12 or later and installs only under .claude/, .codex/ and .agents/ in a project, with review gates that cannot be skipped and a case ledger in aipt-cases/<case>/ledger.jsonl. The author states v0.1 (October 2026) definitions are written and checked but none has been evaluated on a live model, and that no workflow has been shown to complete end to end.

  27. MarkTechPost36

    Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster

    Zyphra released ZYFA, an Apache 2.0 open-source library of FP8 and BF16 prefill attention kernels for AMD Instinct MI355X GPUs (ROCm 7.2.3, PyTorch 2.12) with a drop-in flash_attn_func interface. Its FP8 kernels run 1.16-1.76x faster than AMD's AITER on real model activations, reaching 2,672 TFLOP/s at 32K tokens (53% of FP8 peak), and show 62-78% lower FP8 error than AITER at head dimension 128. ZYFA covers causal prefill forward only, with no decode or paged KV support.

  28. Databricks Blog38

    Real-time fraud detection with Feature Views

    Databricks describes how Feature Views in its Feature Store let teams define a feature once and use the same definition for point-in-time-correct training data and managed online-serving pipelines, reducing training-serving skew and data leakage. The walkthrough follows a $900 payment from a Kafka stream through rolling and Sawtooth window aggregations, an on-demand deviation feature, model training and Model Serving, with Unity Catalog providing governance and lineage.

  29. Databricks Blog30

    How public sector organizations can govern AI at scale

    Databricks outlines why public sector AI projects stall on governance questions—model access, data residency, and spend visibility—and describes how its Unity Gateway provides centralized controls over which models, coding agents, and tools teams can use, with per-user or per-team spending caps, platform-level compliance policies, and geographic data residency for hosted foundation models. The piece argues that agencies which solve governance centrally before scaling adoption can match each mission to an appropriate model while keeping data, users, and budgets under control.

  30. Hacker News AI22

    AI can generate CAD. Hardware still needs human judgment

    The author of Protobench argues that as AI makes generating code and CAD easier, more value lies in deciding what to make, what matters about it, and which compromises to accept, comparing the workspace to Figma as a place to work through design judgment. Protobench already offers editable mechanical and PCB design, ProtoAgent, measurements, single-part structural simulation, materials, sourcing, and manufacturing exports, plus a Studio for appearance and rendering. It is being built under OpusLABS for independent hardware builders and small teams.

  31. The Decoder69

    Perplexity now has its own always-on AI agent

    Perplexity launched Teammates, always-on AI agents that run on their own virtual machine with a desktop and browser and work through ongoing projects independently, unlike the one-off Perplexity Computer. Users track progress in dedicated threads in the Perplexity app and can interact with the agents via Slack. Teammates require the $200-per-month Max plan, joining similar offerings from SpaceX, Meta, OpenAI and Anthropic.

  32. AWS Machine Learning Blog42

    Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls

    This post explains how to run Claude Code as a remote agent on Amazon Bedrock AgentCore runtime, where each task executes in its own isolated microVM session inside your AWS account and returns a GitHub pull request for human review. It walks through the accompanying sample-remote-coding-agent, covering the architecture (API Gateway, Lambda, DynamoDB, SQS, AgentCore runtime) and security controls including Bedrock Guardrails prompt screening, short-lived GitHub tokens via AgentCore Identity, private VPC networking, and least-privilege IAM. The sample suits scoped features, bug fixes, and tests on trusted repositories, but not untrusted code or open-ended work, and the agent never merges pull requests.