iCreatAI News
Back to main site
Skip to content
#Deployment
Oct 29Thu
  1. Hacker News AI28

    Show HN: Files Magic AI: Organize and rename files via content with undo on Mac

    Files Magic AI is a macOS app that proposes a folder structure from a chosen template and previews it before moving anything, renames files based on their contents (with OCR, on-device or via Cloud AI), and includes a System Cleaner for duplicates, unused apps and developer caches. Organizing sends filenames only, folders are never uploaded, and moves and renames can be undone, with rename history kept for 30 days. It requires macOS 12 or later and offers a free plan plus monthly, yearly and lifetime pricing.

  2. Replit Blog42

    Replit’s Architecture Behind Secure Agent Work

    Replit outlines four principles for securing AI agents in its Agent Habitat: least-privilege access with a credential broker that keeps secrets outside the agent's context, isolation via microVMs and separate development/production databases, engineering review of agent-proposed production changes, and audit logging with encryption and BYOC options. It says its existing microVM architecture prevented exploitation of recently disclosed Linux kernel vulnerabilities and that it patched affected Node.js, Python, and PHP tooling and deployed firewall rules centrally. Replit also describes round-the-clock AI red teaming and plans for finer-grained per-task permissions and eBPF-based sandbox monitoring.

  3. OpenRouter Announcements38

    Claude 529 Overloaded: What It Means and How to Fix It

    A 529 overloaded_error means Anthropic's API is temporarily out of capacity for the requested model across all users, unlike a 429, which reflects your own usage limits. The article recommends retrying with exponential backoff and jitter, then routing the same model to another provider via OpenRouter, which serves Claude Sonnet, Opus and Haiku 5.5 through five providers each, and optionally listing a fallback model with `models`. For Claude Code, it suggests switching models with `/model` or running Claude Code on OpenRouter via Ori Harness or three environment variables.

  4. Meta Engineering36

    Meta Andromeda: Powering the Next Generation of Ads Retrieval Through Model-System Co-Design

    Meta describes the next generation of its Andromeda ads retrieval engine, which uses a retrieval mixture-of-experts architecture and a single fused GPU pipeline to score every eligible ad at over one billion ads per second, a 100x throughput lift over the 2024 system. The system delivers near ranking-level model performance at retrieval scale with roughly 300x fewer inference-time FLOPs than the 2024 model, and Meta reports a 2.4% increase in conversions on Facebook since 2025. A joint collaboration with NVIDIA pushed individual components toward hardware limits, with the gating kernel reaching over 10 billion ads per second on a single GH200 and index matching exceeding 100 billion ads per second.

  5. Artificial Analysis Articles72

    GitHub Copilot Fusion orchestrates Anthropic and OpenAI models to balance performance and cost

    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.

  6. Allen Institute for AI Blog38

    How researchers are adapting olmOCR 2 for historical and archaeological archives

    Ai2 describes how researchers adapted its open olmOCR 2 model: historian Maurice Casey built ArtificeOCR to run olmOCR 2 locally and make his Tropy photo library of archival sources searchable, while TU Wien and Austrian Academy of Sciences researchers fine-tuned olmOCR 2 with LoRA on 57 annotated Carnuntum pottery records, lowering transcription error on 450 test records from 15.58% to 1.11% through their CENTURIA benchmark.

Oct 28Wed
  1. NVIDIA Newsroom58

    NVIDIA RTX Spark Windows Laptops Gain New Models, Agent Tools and Games

    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.

  2. Hacker News AI28

    How to Build a Slow Product in the Fast AI Era

    The developer of Mole, a Mac and Windows cleanup tool, describes spending two months on unscalable work: installing and uninstalling 850 Mac apps one by one to build cleanup rules, testing more than 30 AI tools in real use, and redrawing dozens of icons over three rounds. Mole went from 1.13 to 1.18, added AI tool and System Data cleanup, shipped a Windows version on October 14, and passed 72.9K GitHub stars. The author argues that as AI makes code cheaper, the details learned only by doing the work yourself increasingly set products apart.

  3. Hacker News AI22

    New end to end construction management software with AI first approach

    BOQ Manager is a quantity-surveying workspace that combines AI take-offs from drawings or plain-English scope descriptions, reusable spec and area templates, multi-BOQ editing, procurement and purchase orders, job scheduling with an auto-scheduling Gantt, no-login daily site updates, and profitability tracking that syncs labour cost from Zoho People. It integrates with Zoho Cliq, Slack and Microsoft Teams, and is priced from $9/month for Starter (5 projects, 3 users) to $59/month for Business, with custom Enterprise contracts. A 7-day free trial requires no credit card.

  4. Hacker News AI43

    Scaling AI in Legal: Building Uber's Redlining Agent

    Uber describes building its first-generation Legal Redlining Agent (LRA), a Microsoft Word add-in that reviews counterparty redlines, detects intent, recommends policy-aligned responses, generates comments, and flags risks for lawyer review. Through four iterations—RAG, lawyer feedback loops, tone modulation, and agentic modifications plus a rules database—Uber reports over 20% reduction in average contract review time and 91% accuracy in AI-generated decisions. The post details the architecture (React/TypeScript add-in, Python back end, LangGraph workflow, OpenSearch vector stores, Redis session memory) and time-weighted feedback sampling to mitigate concept drift.

  6. Amp Chronicle22

    Your Own Self-Hosted Orbs

    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.

  7. Hacker News AI58

    Harvey raised 500M for legal AI, I built the same and open sourced it

    CaseCite is a source-available, self-hosted legal research platform that lets firms upload and index their own documents and run chat-based research with inline citations, contract review, drafting, and CourtListener-backed case-law tools on infrastructure they control. It is licensed under the Elastic License 2.0, free to self-host and modify internally but not to offer as a hosted service, and AI features send document text to user-configured providers (BYOK) unless self-hosted OpenAI-compatible endpoints are set.

  8. Hacker News AI38

    Building My Own Tiny AI Weather Model

    The author builds a small graph neural network weather model inspired by Graphcast, using a 5 GB subset of ERA5 data (North Atlantic/Europe, 2003–2016 training, 2017–2019 evaluation) and an encode-process-decode architecture with an icosahedral mesh. The model has about 200k weights and trains in 45 minutes on a five-year-old gaming PC, outperforming the persistence baseline for all nine variables at lead times up to +72 h, though its RMSE is roughly 5x worse than Graphcast at 24 h and 10x worse at 72 h.

  9. Hacker News AI55

    Show HN: Veqen – Catch a leaked AI API key by its spend, within the hour

    Veqen is a tool that consolidates AI spend across providers and agents (including OpenAI, Anthropic, Claude Code, Cursor and Devin) into one record, attributing each charge to a person, customer or project. It flags keys used by someone other than their owner, usually within the hour, can shut those keys off, checks bills against providers' rate cards, and produces month-end journal entries. It reads billing, usage and key lists only, never prompts or code, and offers a free audit plus free tiers for work and coding agents (up to 3 people) and product inference (up to $1,000 monthly spend).

  11. Hacker News AI38

    Show HN: AI Workflows – 32 step-by-step workflows built from 146 AI tools

    A Show HN post presents a curated collection of 32 step-by-step AI workflows assembled from 146 AI tools, covering areas such as video production, brand design, content creation, and coding. Listed workflows include AI Podcast Production, Brand Identity Design, AI SEO Content Pipeline, Viral TikTok/Shorts Automation, App Development, and Autonomous AI Agent Setup, among others.

  12. Hacker News AI58

    Show HN: Nuvrail – make an AI agent ask before it sends, moves or deletes email

    Nuvrail is an approval layer that sits between an AI agent and a real mail server, presenting a normal IMAP/SMTP interface while staging every write (moves, deletes, flag changes, outbound sends) for a human to approve or reject with one tap; reads pass through instantly. EXPUNGE and CLOSE are never forwarded, and a local Docker Compose setup runs the approval UI, REST API, and IMAP/SMTP proxies on localhost for evaluation.

  13. Hacker News AI58

    Amazon's anti-tokenmaxxing memo says engineers should be pickier about using AI

    Amazon circulated an internal memo in September, posted to its website Tuesday, revising how it defines software development engineers' and managers' roles in the AI era and discouraging "tokenmaxxing." The memo says metrics like token usage, AI tool adoption rates and code changes or reviews are "deeply flawed" and can raise costs and complexity, and that token usage and code generation should be considered "with care and judgment" alongside other data. An Amazon spokesperson said the company has not capped employees' token usage, and AWS VP Marc Brooker told CNBC Amazon looks to metrics such as "feature velocity" and frames the question as return on investment.

  14. Hacker News AI38

    SiFive positions RISC-V as the control layer for AI accelerators

    SiFive is positioning its Intelligence-series RISC-V processors as programmable Accelerator Control Units (ACUs) that handle data movement, scheduling and coordination for custom AI accelerators, rather than relying on hardwired state machines, shared buses or host-CPU orchestration. The X100 series targets control-intensive, low-latency applications, while the X200 and X300 offer more vector bandwidth; Google data centers already use the X200 as an AI compute host, and an X100 license has gone to an unnamed Tier 1 US semiconductor company for industrial edge AI. The article argues RISC-V's value is moving beyond the ISA toward specialized system integration and accelerator orchestration.

  15. Hacker News AI38

    Tenstorrent and Smallest.ai Partner to Bring Production-Grade Voice AI On-Prem

    Tenstorrent and Smallest.ai have partnered to deliver an on-prem voice AI stack that runs Smallest.ai's Lightning V2 real-time text-to-speech model natively on Tenstorrent Galaxy Blackhole servers, aiming to reduce deployment costs while meeting real-time performance needs. Smallest.ai said working with Tenstorrent's NoC and larger SRAM unlocked 4x gains at a fraction of the cost of comparable GPU infrastructure, and the joint solution targets high-volume, data-sensitive use cases in financial services, telecom, healthcare, and enterprise. Lightning V2 is available on Tenstorrent hardware today with usage-based pricing and no upfront commitments.

  16. Hacker News AI42

    Requesty: AI Gateway and LLM Router for 600 Models in EU Datacenters

    Requesty is an OpenAI-compatible AI gateway that provides access to 600+ models through one API, with routing and failover, spend limits, governance, and per-request observability. It offers EU data residency in Frankfurt on AWS eu-central-1, SOC 2 Type I with Type II under audit, an Article 28 DPA on request, and enforced zero data retention, priced at a 5% markup on model cost with no seat fees.

  17. Sarvam AI Blog38

    Sarvam and HQ IDS establish joint framework for AI adoption across the Army, Navy and Air Force

    Sarvam signed a Memorandum of Understanding with Headquarters Integrated Defence Staff (HQ IDS) under the Ministry of Defence, creating an umbrella framework for AI projects across the Indian Army, Navy and Air Force and HQ IDS joint organisations. Under the MoU, Sarvam will design, develop and deploy AI applications for operational, training and decision-support needs and provide follow-on technical support, with work carried out by its firewalled division Chanakya using its AI stack including Sarvam 105B. Focus areas include decision support, target acquisition and data fusion across the sensor-to-shooter loop, with human oversight retained on operational decisions and deployment on sovereign infrastructure.

  18. Hacker News AI34

    AetherGrid, an open-source distributed AI workload orchestrator

    AetherGrid is an open-source distributed AI workload orchestrator that matches workloads to compute nodes by resource requirements and constraints, manages the full job lifecycle, and enforces exclusive execution ownership through time-bound leases rather than assignment flags. Its domain logic is pure Python with no infrastructure dependencies, and every route requires API key authentication. The project documents each non-obvious engineering decision in architecture decision records covering reconciliation, lease fencing, scheduling policy, and API key scoping.

  19. Hacker News AI38

    Show HN: SelfClaw – Self-hosted multi-model AI chat with OpenAI-compatible API

    SelfClaw is a self-hosted AI chat system that aggregates multiple model providers (DeepSeek, NVIDIA, SiliconFlow, ZenMux, Zhipu, Kimi, MiMo, Mistral) with automatic failover polling, a CCR closed-loop agent with tool calling and memory, file operations, Bing/Baidu web search, and voice interaction. It runs a FastAPI gateway plus a Streamlit UI on port 8502, and also ships Self-IDE, a local Python service with an OpenAI-compatible proxy, goal engine, subagent orchestration and cost meter (default port 19898) with a thin VS Code extension.

  20. Hacker News AI58

    Writing AI agents in YAML instead of Python

    This article walks through Docker's open-source docker-agent tool, which defines an AI agent's model, instructions, and toolsets in a single YAML file and runs it with one command. Using a Polars documentation Q&A agent, it demonstrates a built-in RAG toolset with local SQLite vector storage, per-run model overrides, prompt files, flavors for variants, multiple agents sharing tools, JSON-based evals, and pushing agents to a registry. It notes that code-first frameworks like LangGraph suit cases requiring custom branches or retries.

  21. Hacker News AI58

    AI Phone

    AI Phone is an AGPL-3.0 open-source agent that runs on a computer and handles phone calls over SIP, currently requiring macOS on Apple Silicon with 16 GB RAM recommended for the default 4B model. Setup via a git clone and install script configures call direction, model, line and voice, and the daemon supports outgoing calls with an AI disclosure plus incoming calls using a set greeting. Speech recognition and synthesis stay local, while the language model can be local MLX, a Claude Code or Codex subscription, or an OpenAI-compatible endpoint.

  22. ElevenLabs Blog38

    How to build an AI voice assistant: Brand-aligned voice AI

    This guide explains how to build an AI voice assistant by connecting speech to text, an LLM, and text to speech into one real-time pipeline, then adding a knowledge base, business tools, system instructions, and fallback rules. It covers architecture choices between raw APIs and the managed ElevenAgents platform, latency targets below 500 ms with voice activity detection, caller verification, human handoff, brand voice customization, and pre-launch testing for latency, interruptions, accuracy, and safety. Post-launch metrics such as containment, escalation rate, word error rate, hallucination rate, and CSAT are recommended for continued improvement.

  23. Browser Use Blog38

    Why Playwright Scripts Break When the Site Changes

    The article explains that Playwright scripts break on redesigns because they locate elements by page structure (CSS classes, DOM position, XPath, generated IDs) rather than by what users see, and recommends role, label, text, or owned test-ID locators with auto-waiting instead of fixed timeouts. It catalogs causes and fixes for flakiness, including strict-mode violations, copy changes, A/B variants, iframes and shadow DOM, expired sessions, and overlays handled via page.addLocatorHandler() since v1.42. For sites you don't control, it lays out options from manual fixes to Playwright's healer agent and agent fallbacks, with a Python example attaching Browser Use to Chrome over CDP.

  24. Browser Use Blog38

    How to Run Browser Automation at Scale in the Cloud (2026)

    This guide describes a queue-and-worker architecture for cloud browser automation, where each job gets its own isolated remote browser driven over CDP with Playwright or Puppeteer, with concurrency capped at the plan limit and browsers always stopped when jobs end. It compares pricing, concurrency limits and session caps across seven providers (Browser Use, Browserbase, Steel, Hyperbrowser, Browserless, Kernel, Anchor), works through a cost example of 1,000 jobs a day, and covers rate limits, retries with backoff, and self-hosting versus managed trade-offs.

  25. Browser Use Blog30

    Headless Browser Blocked by Cloudflare? What Works (2026)

    Cloudflare blocks stock headless Chrome because it signals automation (navigator.webdriver is true, Playwright's headless shell sends HeadlessChrome in its user agent), often runs from cloud server IPs, and starts each run without cookies. The article recommends getting recognized via an official API or Web Bot Auth verification, or, on sites you're allowed to automate, using a real Chromium with residential IPs and a persistent profile, which in practice means a managed stealth browser. It cites Stealth Bench V2 (September 25, 2026) results where headless Chrome with no proxy got through 3% of visits versus 90.5% for Browser Use Cloud, noting the site set favors the vendor.

  26. Hacker News AI38

    AI search explained: indexing, retrieval and reranking

    This post walks through three retrieval approaches on a synthetic ten-note dataset from eight tools: text search using an analyzer and inverted index, embedding search using an embedding model and vector database, and embedding search with a reranker that reorders a shortlist by relevance. It shows text search missing paraphrases, embedding search surfacing semantically similar notes but ranking a refund how-to above the actual reasons, and reranking putting the relevant notes on top. It concludes with guidance on when to use each approach and notes that production systems often combine text and embedding search via hybrid search with reciprocal rank fusion before reranking.

  27. Together AI Blog40

    Auto repair for Together GPU Clusters: from GPU fault to healthy node

    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.

  28. NVIDIA Technical Blog35

    Memory-Enforced GPU Sharing in Kubernetes with NVIDIA CUDA 13.4

    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.

  29. Claude Code Releases12

    v2.1.312

    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.

  30. Claude Blog38

    Manage costs and demonstrate ROI for Claude Code on Google Cloud

    This post outlines a control, track, and prove framework for managing Claude Code spending on Google Cloud, using native tools such as per-project billing, budget alerts, spend caps, BigQuery exports, quotas, and the self-hosted Claude apps gateway for per-user and per-group spend limits and model allowlists. It describes tracking via Claude Code's OpenTelemetry metrics and events exported to Cloud Monitoring or BigQuery, and proving ROI through usage, satisfaction, and impact metrics such as PR cycle time and review turnaround. It cites Delivery Hero, Shopify, and Fifth Dimension as examples of measured impact.

  31. Hacker News AI58

    Running Local AI on Nvidia DGX Spark Without CUDA

    CUDA++ is a research-stage toolchain and runtime that encodes GB10 (sm_121) machine code directly, replacing nvcc, PTX and libcuda with its own encoder and a client for NVIDIA's open kernel module ioctls, while NVIDIA's kernel module and signed GSP firmware remain. It currently supports only the DGX Spark's GB10, does not compile CUDA C++ or PTX, and reports partial coverage of CUDA's libraries; a head-to-head speed comparison against llama.cpp and vLLM has not been published.

  32. Hacker News AI58

    Show HN: I built flightdeck – Observability and control plane for AI agents

    flightdeck is a self-hosted, Apache 2.0 observability and control plane that streams every LLM call, MCP event, and tool call from AI agents to a dashboard with a per-agent timeline and live fleet-wide feed. It offers token budgets with warn/swap/block thresholds, a kill switch and remote directives, per-flavor MCP allow/block rules, and sub-agent trees, and agents attach via a Claude Code plugin or the flightdeck-sensor Python package using init() + patch(). It is not a proxy: the sensor wraps SDK clients inside the agent's process and calls go straight to the provider, with prompt capture off by default in the sensor.

  33. Hacker News AI38

    Securing sensitive data in the AI era

    This article explains shadow AI—unsanctioned use of AI tools at work—and how it appears in development teams, noting that client code and personal data carry extra contractual and GDPR obligations. It offers practical mitigations: approved business-plan tools, a shared model gateway, sending less data, pseudonymization, IDE file exclusions, local models, and agreeing AI rules with clients at kick-off. It also covers incident response and stresses rewarding reporting rather than punishing it.

  34. Hacker News AI60

    Giotto Sovereign European AI Models

    Giotto is a sovereign AI operating system that combines a reasoning model with an assistant, code, integrations, documents, agents and infrastructure monitoring, deployable on European cloud or private infrastructure. It offers two models, Giotto Alto and Giotto Solo, with benchmark comparisons against OpenAI, Anthropic, Google, Moonshot AI, Mistral, Nvidia and DeepSeek models across AIME 2026, GPQA-Diamond, HLE and Math-500. Giotto is available via its cloud, as a download for your own GPUs, or as a certified appliance with Giotto preinstalled.