Skip to content
#Deployment / engineering
November 13Friday
  1. Databricks Blog36

    Bright Machines uses Debezium and Iceberg to give customers live dashboards from air-gapped factories

    Bright Machines now gives customers live, governed dashboards of factory data from air-gapped plants without opening any inbound access. It captures PostgreSQL changes at the edge with Debezium, writes them as Apache Iceberg, pushes them out over one auditable outbound path, and reads them in place in Databricks via Unity Catalog federation. The first customer-visible dashboard went live about two months after kickoff, with committed rows queryable in one to two minutes and dashboards refreshing every ten minutes.

  2. Hacker News · AI38

    The Hard Part of AI Coding Is the Second Change

    Brian Woods argues that AI coding agents make a first working change cheap, but the second change is where systems break — an agent adding retries to a payment service can double-charge customers even while tests pass. He proposes requiring four answers before accepting a change: specification, validation, provenance and authorization, with agents proposing changes while independent workflows produce evidence and humans approve. He also shows a signed attestation of a build with failing tests can return VERIFIED, since authenticity is not release readiness.

  3. Hacker News · AI38

    NEAR AI Gateway: Use Private AI Models in Claude Code, Codex and OpenCode

    NEAR AI Gateway lets Claude Code, Codex and OpenCode route their AI requests through NEAR AI's private models, with each call's model, tokens and cost logged locally on the Mac. Traces are redacted on-device before sharing, and users review every trace before deciding what leaves the machine. Accepted traces earn NEAR AI Cloud inference credits; the macOS 14+ app is version 1.0.7 at 119 MB.

  4. Hacker News · AI71

    InferSSD runs 800B-class LLMs on consumer hardware by keeping expert weights on NVMe

    InferSSD, an open-source inference runtime built on llama.cpp, runs 763B-class DeepSeek-V4.1-Flash-1017 and 816B-class Muse-Spark-Open on consumer machines by keeping routed expert weights on NVMe storage while attention, shared layers and the KV cache stay in RAM or VRAM. On an RTX 5090 with 32 GB RAM and 32 GB VRAM it reports 164.5 tokens/s prefill and 7.27 tokens/s decode for DeepSeek at a 4K prompt tier, versus 8.06 and 0.867 tokens/s for llama.cpp on the same system. The article also estimates that heavy daily use could mean roughly 85 TB of host reads per day and lays out a conditional SSD wear model, noting the figures are assumptions to test rather than a promised drive lifespan.

  5. Hacker News · AI76

    AgentRun Open-Source Release: Adding Self-Improvement and Durable Execution to Existing Agent Harnesses

    Parcha Labs has open-sourced AgentRun, an agent platform that layers self-improvement, durable execution, and a console on top of Claude Code, Codex, OpenCode, and pi, under the Apache-2.0 license.

    Why it matters: AgentRun layers self-improvement, durable execution, and a console on top of existing harnesses such as Claude Code and Codex, and provides a concrete case where code review costs dropped from $6,451 per month to 18 cents per run.

  6. Hacker News · AI31

    Air-LLM: Broadcasting AI Weights to Edge Devices via RF Computing for On-the-Fly LLM Inference

    Air-LLM is an edge LLM inference architecture in which a central radio such as a 5G base station broadcasts model weights over the air, and edge users complete GEMV directly in the RF domain using RF mixers, so devices never store or load weights. Tested on NVIDIA Sionna ray-traced channels in two real urban scenes with a real RF mixer profile, it limits WikiText-2 perplexity degradation on LLaMA-3.1-8B to 4.0% while saving 157.7x/40.4x energy versus FP16 and weight-only quantization baselines. With 20 users, airtime is 104.1x/26.0x shorter, and because the central radio stays user-unaware, one broadcast serves unlimited users in coverage.

  7. Hacker News · AI58

    Cloudflare Workers AI previews Clairic, a System One-style extraction model

    Cloudflare Workers AI has released Clairic in preview, a strongly typed extraction model that pulls, computes, estimates and forecasts values from inputs and returns confidence scores and probabilities for each output. The model has a 65,536-token context window, supports vision, offers zero data retention and is priced at $0.10 per M input tokens. In the documented invoice example, Clairic extracts fields such as invoice number, due date and total, returns null with p_null 1 for a missing PO number, and gives a median of 30 with a p10-p90 interval of 21 to 38 for days_to_pay.

  8. Hacker News · AI58

    CanyonOS 0.2 launches as open-source tool to find, observe and scale agents

    CanyonOS 0.2 is the first public release of an open-source, model-agnostic tool for finding, observing and scaling agents that slow down workflows. It runs on Docker or Kubernetes, works with any provider offering an OpenAI-compatible API, exports OpenTelemetry-compatible traces and metrics to tools such as Datadog, Grafana, Prometheus, Langfuse and Arize Phoenix, and adds cost and queue time per agent. The project is AGPL-3.0 licensed, requires agents to be rewritten into plain Python with one file per agent, and its FAQ states it has not yet run at large production scale.

  11. Hacker News · AI58

    Stay-in-sight launches open-source outbound email tool with 64 MCP tools for AI agents

    Stay-in-sight released an MIT-licensed outbound email system that runs on Cloudflare Workers and D1, sending cold outreach, newsletters and drip series from the user's own Gmail and SES mailboxes. It ships 64 MCP tools plus a REST API so agents like Claude Code and Cursor can import contacts, schedule sends and answer replies, and the project claims deployment in about 30 minutes with hosting free at low volume or $5/mo on Workers Paid.

  12. Hacker News · AI58

    InferTrail runs a 35-day LLM API key honeypot and traces how stolen keys get used

    InferTrail planted 179 API keys across 40+ fake GitHub organizations and ran two honeypot LLM gateways for up to 36 days, logging over 3 million requests. Only 18 of the published keys were used to send prompts, and six keys accounted for 98.9% of leaked-key prompt requests, while 86% of that traffic came from hosting infrastructure. The authors list three log patterns for spotting key reuse: many model names under one key in a short window, steady-interval checks after a key works, and a shift in source addresses.

  13. Hacker News · AI17

    SF company uses AI to design and assemble PCBs in weeks instead of months

    A San Francisco company uses its own AI tools to design and assemble PCBs, cutting turnaround from months to weeks, from first schematic to production-ready board. Its portfolio spans an 8-layer software-defined radio front-end that is 67% smaller with the same RF performance, a USB-C wearable audio interface that went from two failed designs to 300+ production units, and a rugged industrial relay controller. PCB design engagements start at $10.0k, integrated electronics at $25.0k, and advanced electronics at $50.0k.

  15. Hacker News · AI60

    Cerulion 2.0 released: an open-source ROS 2-compatible robot runtime with multi-process replay

    Cerulion Inc. released Cerulion 2.0, an open-source, ROS 2-compatible robot runtime that records runs and replays failures against changed code, with one process per node by default. It ships Linux x86_64/ARM64 and macOS binaries, an rmw_cerulion layer tested on Foxy through Lyrical, and MCAP recordings with byte-exact replay verification that returns a nonzero exit code on divergence. On one x86-64 Linux desktop at 1 MiB payload, the project reports a 4.08 µs median round trip versus 10,952 µs for ROS 2 Jazzy with rmw_fastrtps_cpp defaults.

  16. Hacker News · AI60

    Neon and Mubit release a template for an agent that cuts its own frontier-model tokens by 73%

    Neon and Mubit published a template for a data analyst agent on Neon Functions and Lakebase Postgres that sends every model call through Mubit to Neon AI Gateway. In Mubit's benchmark on 20 CL-bench questions run three times each, the setup cut gpt-5.5 input tokens by 73% and answered 40% faster, with accuracy at 65% versus 60% for gpt-5.5 alone. Mubit moves routine steps such as listing tables and writing up answers to a small tuned model after it passes an exam built from the task's own traffic, while gpt-5.5 still writes every SQL query.

  17. Hacker News · AI35

    Reverse Engineering a Coway Air Purifier to Ditch the Cloud

    A developer reverse-engineered the Wi-Fi-enabled Coway Airmega IconS air purifier to cut its dependence on Coway's IoCare cloud, using a man-in-the-middle setup built with LLM assistance. The existing Home Assistant integration impersonates Coway's phone app but breaks repeatedly—server bans, an IoCare to IoCare+ rebrand, HTML layout changes, and outages—prompting the effort. A weak-key incident at certificate authority eMudhra in October 2026 opened a possible foothold for intercepting the device's traffic.

  18. Hacker News · AI25

    What End-to-End AI Systems Mean for the Future of Automated Driving

    Aptiv engineering VP Guillermo Pita explains how end-to-end AI differs from traditional modular ADAS by training a single model to learn driving behavior directly from data instead of chaining separate perception, tracking, planning and control modules. He cites more human-like driving as the main advantage, with explainability and debugging as the key challenges, and names data diversity rather than raw mileage as the central training problem.

  19. MarkTechPost62

    Fish Audio Releases Live 3, a Full-Duplex Voice Model That Reacts in 186 ms

    Fish Audio released Live 3, a full-duplex voice model for real-time voice agents that keeps listening while it speaks and learns turn-taking from real human conversations instead of hand-tuned pipeline rules. Fish Audio says it can decide to respond in as little as 186 ms for short reactions like "mm-hmm," though that figure is a floor for small reactions rather than time-to-first-audio for a full reply, and no benchmark scores have been published. Live 3 runs on the Fish Agent Platform (public beta), the Fish Audio API and on-premises for enterprises, priced at $0.035 per minute until December 31, 2026 versus a $0.07 list rate, and supports English only.

  20. AWS Machine Learning Blog58

    AWS releases SGLang-Neuron, enabling deployment of frontier models on Trainium with the existing SGLang interface

    Amazon announced the public availability of SGLang-Neuron, an out-of-tree plugin that runs SGLang on AWS Trainium through an AWS Deep Learning Container, released by RadixArk with Annapurna Labs. Users keep the same SGLang server interface and generation APIs, while the plugin supplies Trainium-specific models, attention, MoE and a graph runner built on native PyTorch and NKI kernels compiled with torch.compile. It also supports PD disaggregation, transferring the prefill KV cache to a decode server via NIXL over EFA, and the walkthrough serves openai/gpt-oss-120b on a Trainium3 EC2 instance with the pytorch-inference-sglang-neuronx container.

  22. TechCrunch · AI66

    Nebius plans $40 billion in 2027 spending as Microsoft data center delays mount

    Nebius laid out $40 billion in planned 2027 spending on its third-quarter earnings call, funded largely by customer prepayments and loans backed by customer contracts. Its Vineland, New Jersey site for Microsoft, under a contract worth up to $19.4 billion, is months behind schedule, with only just over half of the Microsoft capacity now planned for delivery by year-end and the rest in Q2 2027. Nebius cut its 2026 revenue forecast by $200 million to $3 billion and reported third-quarter revenue of $981 million, up 571% year over year, while shares fell 17%.

  23. AWS Machine Learning Blog40

    How Natera built SWARM, an agentic AI system for lab ops on Amazon Bedrock AgentCore

    Natera built SWARM, an agentic AI system for lab operations, on Amazon Bedrock AgentCore, cutting first response time by about 130x and automating 96.2 percent of support tickets. The system pairs a swarm-agent that drafts diagnostic reports before engineers open a ticket with a swarm-hive for real-time engineer interaction, both sharing one skill library. It addresses over 65 daily Jira tickets across three queues that previously averaged 17.4 hours for first response.

  24. Databricks Blog30

    Databricks Debunks Four LTAP Myths About Lakebase Architecture

    Databricks responds to four common misreadings of LTAP, the Lakebase architecture that keeps one governed copy of operational data serving both Postgres and analytics without CDC. The post argues LTAP is not replication: layers in front of the lake are caches, not a second database with its own catalog. It also says heap pages and Parquet are two lossless encodings of the same rows, so point lookups and scans each read the layout fast for them.

  25. MIT News18

    MIT Lincoln Laboratory's Magnetite OS and two other technologies win 2026 R&D 100 Awards

    Three MIT Lincoln Laboratory technologies received 2026 R&D 100 Awards: the Magnetite operating system, which builds on the formally verified seL4 microkernel with Rust-written services to protect embedded computers from cyberattacks; the Quantum Microsystems platform, which integrates hundreds of superconductor and semiconductor chips into a single wafer-scale system; and an algorithm that removes 5G base-station interference on co-channel RF devices. Magnetite is free for government use and approved partners and is being integrated into DoW space and flight platforms.

  26. AWS Machine Learning Blog38

    Tokenomics at Scale: Tracking and Capping Amazon Bedrock Spend per IAM Principal with CUR 2.0 and AWS Budgets

    AWS shows how to track and cap Amazon Bedrock generative AI spend per IAM principal using only native features: Bedrock automatically records the IAM user or role on every inference request, and those tags become cost allocation tags readable in Cost Explorer or CUR 2.0 exports. An AWS Budget scoped to Bedrock and filtered to one identity or tag value can attach a budget action that applies a Deny IAM policy once a threshold is crossed, with no application code for the common case.

  27. AWS Machine Learning Blog36

    Four Amazon Bedrock inference choices that affect cost

    Amazon Bedrock's cache duration, service tier, reasoning effort, and maxTokens settings can change inference cost without altering the model or prompt. A 5-minute cache write on Claude Sonnet 5 and Claude Opus 5 costs 1.25x the input rate, a 1-hour write costs 2x, and cache reads cost 0.1x; Flex tier requests to unsupported models fail with a ValidationException.

  28. Databricks Blog22

    How Constellation is building a governed data foundation on Databricks

    Constellation, the largest US nuclear fleet operator, is building a governed Enterprise Data Platform on Databricks to give the business one shared meaning for its data. The platform uses Unity Catalog for lineage, fine-grained access and a single permission model, plus Data Vault modeling for critical reusable entities. Early use cases include a nuclear engineering assistant built with Databricks Genie and outage planning.

  29. Databricks Blog25

    Eclipse Aerospace uses Databricks PySpark custom data sources for flight-data ingestion

    Eclipse Aerospace is using Databricks PySpark custom data sources to ingest nearly 20 years of proprietary flight data, over 3TB spanning more than a million flight hours, without always-on dedicated compute. The Rust-backed Python package delivered twice the benchmarked performance of a similar PyArrow-based pure-Python data source and nearly 20x that of a native Python implementation without Arrow. The API, introduced in Apache Spark 4.0 and available in Databricks Runtime 15.4 LTS, replaces the prior Lambda-to-Avro pipeline.

  31. AWS Machine Learning Blog66

    AWS updates AgentCore runtime with 15x faster session starts and 4x more compute

    AWS announced updates to Amazon Bedrock AgentCore runtime, its managed compute layer for agents, with sessions now starting up to 15x faster, scaling to 4x more compute (up to 8 vCPUs and 32 GB, with container images up to 10 GB) and running up to 68% more efficiently, while each session stays in its own hardware-isolated Firecracker MicroVM. Sessions start in under 2 seconds regardless of image size or concurrency, idle agents scale to zero, and agents can mount and save work to a filesystem such as an Amazon S3 bucket with FUSE support so data stays inside the trust boundary. The runtime is available today in AWS Regions across North America, South America, Europe, and Asia Pacific.

    Why it matters: AgentCore runtime 的新版本把会话启动、算力上限和内存计费一起调整，为需要长时间运行的智能体提供了隔离与成本之间的新取舍。

  32. AWS Machine Learning Blog34

    Building a self-service LLM gateway with Amazon Bedrock and LiteLLM

    A self-service LLM gateway built on Amazon Bedrock Application Inference Profiles and LiteLLM running on AWS Fargate exposes Bedrock foundation models behind an OpenAI-compatible API, giving developers a single base URL and per-user key. The setup adds per-user spend controls, per-model quota isolation, and CloudWatch RPM/TPM observability, with Langfuse for prompt-level telemetry. Self-service key issuance requires LiteLLM Enterprise, since the free tier is limited to five users.

  33. AWS Machine Learning Blog34

    Optimizing cost per task and proving agent ROI on Amazon Bedrock

    This AWS post argues that Amazon Bedrock spend should be judged by cost per task rather than cost per token, since tokenizer efficiency, output verbosity, agentic loop count and reasoning overhead can make a lower-priced model cost more. A worked example shows a model with 2x the list price finishing 65% cheaper per task, and the post adds caching, routing and output constraints plus a five-dimension scorecard for measuring agent ROI against human baselines.

  35. SemiAnalysis85

    Nvidia and the World Without Jensen: What a Post-Founder Nvidia Looks Like

    SemiAnalysis argues that Nvidia was built around Jensen Huang, who has left the CEO role after 33 years, and that his departure weakens the company's long-term bets, chip allocation deals and personal supply chain lockups. The piece says Nvidia had about 60 direct reports under Huang and lacks a deep bench of successors, with Colette Kress as interim CEO and Ian Buck and Jonah Alben floated as internal technical candidates. It also ties the timing to Washington: more than 1.5GW of restricted Nvidia chips are estimated to have reached China, and the Remote Access Security Act, which passed the House 369-22, is up for a Senate vote.

    Why it matters: SemiAnalysis examines how Nvidia's founder-centric structure, supply chain deals and China policy could change after Jensen Huang's exit, and why export control legislation is moving now.

  36. MarkTechPost71

    AWS Releases AWS Emulator, a Local Emulator of 200+ AWS Services Written by AI Agents

    AWS has released AWS Emulator, a free local emulator of AWS APIs that runs on a laptop, dev server or in CI without an AWS account, and all of its code was written and reviewed by autonomous agents. It is built from 438 AWS API models covering 200+ services and passes 24,243 of 42,857 scored fidelity tests (56.6%) in release v1.0.322, with AWS KMS at 93.9% and AWS CloudFormation at 15.8%. AWS lists clear limits: no IAM policy evaluation, one region and one account, in-memory short-lived resources, and telemetry on by default.

  38. Claude YouTube35

    Building the Claude API for the Frontier: Inside Claude Platform's Release and Safety Decisions

    Claude Platform engineers Jake Dejno and Lucca Siaudzionis explain how the Claude API evolves alongside each model launch, covering feature release decisions, model versioning and migrations, and cost management. They detail best practices for changing effort mid-conversation without breaking prompt caching, and how Claude Mythos and Fable share the same model weights with different safeguards. Claude Managed Agents and mid-conversation effort changes are in beta, and Mythos access runs through the Cyber Verification Program.

  39. Databricks Blog22

    How H6.ai builds AI-powered financial automation with Lakebase Postgres

    H6.ai automates accounts payable on top of customers' existing ERPs, using a dedicated Lakebase Postgres database per customer as its system of record. Because invoice data keeps changing, the team uses Lakebase copy-on-write branches to freeze snapshots of customer databases and run each regression test on its own short-lived branch, so the live database is never written to. Each run is judged by deterministic assertions plus a panel of AI judges from different model providers.

  40. Databricks Blog58

    Databricks launches Lakehouse//RT to serve real-time analytics without proportional cost growth

    Databricks introduced Lakehouse//RT, a real-time analytics engine that runs high-concurrency workloads directly on lakehouse data and is now available in beta. The company says it delivers sub-100 millisecond latency at 12,000 queries per second, adds capacity one node at a time, and avoids a separate serving layer; customers Aurasell, VisionHeight and nOps report 6x to 10x lower infrastructure costs after migrating from multi-cluster setups, Apache Pinot and Apache Druid.