iCreatAI News
Back to main site
Skip to content
#Deployment
Nov 13Fri
  1. AWS Machine Learning Blog48

    Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools

    This post describes an architecture in which all employees share one agent and knowledge base, but each user can search only the documents they are allowed to view, using Amazon Bedrock Managed Knowledge Base ACL awareness exposed as MCP tools through Amazon Bedrock AgentCore Gateway. The design keeps the LLM from deciding who the user is: a request interceptor injects the verified email from the JWT into userContext, Policy in AgentCore checks it against the token's email claim, and a resource-based policy denies searches from principals other than the gateway execution role. It also covers prerequisites, ACL metadata files, tool schema configuration with parameterOverrides, and a verification script that tests each defense.

  2. AWS Machine Learning Blog52

    Build composable, interoperable multi-agent systems with A2A on AWS

    This AWS post presents a deployed reference architecture in which a LangChain-based enterprise orchestrator in one AWS account calls a Strands Agents-based compliance SaaS agent in another account using the Agent-to-Agent (A2A) protocol, with neither side depending on the other's framework or SDK. It covers cross-framework interoperability, bidirectional agent-to-agent callbacks, and OAuth authentication in both directions using separate Amazon Cognito user pools, with deployment from three Jupyter notebooks and an end-to-end test.

  3. AWS Machine Learning Blog34

    Migrate to Amazon Bedrock Managed Knowledge Base with your coding agent

    AWS added a knowledge base migration guide to the amazon-bedrock skill in the Agent Toolkit for AWS, which lets a coding agent plan a move from a customer-managed knowledge base to Amazon Bedrock Managed Knowledge Base, starting with read-only discovery and a plan you review line by line. On approval, the agent creates the new knowledge base and data sources alongside the original or writes a migrated infrastructure as code template, while ingestion and updating the application's Retrieve calls remain with your team. The post covers why AWS recommends the move, prerequisites, installation, planning, updating retrieval calls, and validating retrieval before cutover.

Nov 12Thu
  1. Databricks Blog42

    Genie in Slack is now Generally Available: Governed AI cowork, right where work happens

    Databricks announced the General Availability of the Genie app for Slack, which answers questions in channels, threads, or DMs using the same governed context and permissions as Genie in Databricks, with every answer citing its sources. Users can @mention Genie in channels or DM it, and through MCP connectors Genie can create or update documents, comment on tickets, and update records with approval before each change, as well as schedule recurring analyses and work with files. Genie in Slack follows the same governance as other Genie surfaces, running each question with the asker's identity across Unity Catalog and connected sources, with admins able to govern AI usage centrally in Unity Gateway.

  2. NVIDIA Newsroom12

    A New Dawn in the Cloud: ‘Warhammer 40,000: Dawn of War IV’ Is Coming to GeForce NOW

    Warhammer 40,000: Dawn of War IV, developed by KING Art Games and published by Deep Silver, is coming to GeForce NOW when it launches on Steam Thursday, Dec. 3, featuring large-scale battles, base building and more than 70 campaign missions playable solo or in co-op. NVIDIA DLSS 5 with 3D-Guided Neural Rendering is coming to War Thunder in its mid-November Eagle's Shadow update and to Where Winds Meet on Monday, Nov. 23. Dragon's Dogma 2: Dark Arisen is streaming on GeForce NOW, and 10 games join the library this week.

  3. PyTorch Blog40

    Integrating SGLang into Spyre in Under a Week with AI

    A two-person team used AI coding agents to integrate SGLang with IBM Spyre in under a week, producing a plugin of roughly 1,500 lines built on existing PyTorch Spyre support and SGLang's extension points. SGLang delivered about 3.6× the throughput of the reference PyTorch inference implementation using torch-spyre and was on par with vLLM on the measured workloads for Granite 3.3 8B and Gemma 4 26B A4B. Prefix sharing through RadixCache worked without any Spyre-specific changes.

  4. Hacker News AI38

    Don't build your own harness: lessons from building Paywalls AI Editor

    RevenueCat describes how its Paywalls AI editor initially manipulated a custom JSON paywall schema through a bespoke harness, producing results that lacked taste despite model, prompt and skill tweaks. The team switched to letting the agent edit a JSX representation of the paywall with familiar Read, Write, Edit and compiler tools, which set a record on their blank-paywalls eval two days after the prototype and let them cut over half the system prompt and almost all skills. After rollout to 100% of users on September 2nd, positive feedback across roughly 46K requests grew 83% and negative feedback fell 40%, with gains concentrated in large edits, new paywall creation and anything requiring taste.

  5. Hacker News AI78

    Vercel Data Shows AI Models Have Six-Week Half-Life in Production

    Vercel's November 2026 AI Gateway Production Index reports that production AI models have an effective half-life of about six weeks, with more than half of October's language-model requests going to models under 60 days old and most teams abandoning a model within four weeks of its peak. Decision models reached 26% of gateway requests in October at just 0.53% of spend, voice usage rose from 4% of paid teams in July to 11% in October, and Anthropic and OpenAI were nearly level at 54 and 55 of every 100 paid teams. Image and video spending hit records, with OpenAI's GPT-Image-2.5 Sunburst leading image spend and ByteDance's Seedance 2.5 leading video spend for a third month.

    Why it matters: The index offers a rare production-usage view of model churn, spend shifts and emerging decision and voice workloads, useful for teams planning model-swappable pipelines.

  6. PyTorch Blog58

    Training a 1T-Parameter MoE on EU public infrastructure with PyTorch and TorchTitan

    The EUROPA consortium (Domyn, Fraunhofer IAIS and IIS) describes scaling pretraining of a ~951.9B-parameter MoE model (32.8B active per token) on JUPITER, the EuroHPC exascale supercomputer at Forschungszentrum Jülich, raising throughput from 90 to ~1,300 tokens/sec per GPU across 384 NVIDIA GH200 GPUs per DP replica. Key optimizations built on PyTorch and TorchTitan include FlexShard placement for the Muon optimizer, activation-checkpoint offloading to the Grace CPU, and running FSDP's all-gather setup on the compute stream via unshard_async_op, freeing ~14 GiB of HBM per GPU. The fixes were upstreamed to PyTorch and TorchTitan, with training reaching ~1,300 tokens/s per GPU on 1,536 GPUs across 4 DDP replicas.

  7. Hacker News AI60

    Show HN: A free course from engineer to AI engineer, one Git tag per episode

    A free YouTube-based course, "From engineer to AI engineer," teaches experienced software engineers with no generative-AI background to build a retrieval-augmented generation (RAG) pipeline in eight episodes, with a second seven-episode series, "Prove it works," building an evaluation harness on the same repository. Each episode is one commit and one Git tag (s1e1–s1e8 and s2e1–s2e7), so checking out a tag reproduces the repository exactly as that episode leaves it. The series uses TypeScript, SQLite, curl and an HTTP server, answering with claude-sonnet-5-5 over a fictional 26,000-word corpus (Lantern Supply Co.) that includes deliberate traps such as near-identical product names and a policy changed in later release notes.

  8. Hacker News AI20

    Show HN: Closed,Mechanical Mould Design AI Agent

    Closed is a mould design AI agent that accepts a customer STEP file or part photo, keeps the customer's part locked, and drafts stages including parting, core and cavity, layout, mould base, feed, side actions and ejection, logging each stage. It pauses for human decisions when a rule is violated, shows the source of every dimension from one of six non-AI origins, and supports switching between agent and manual mode on the same model. Nothing ships until the user approves it; the macOS and Windows studio plus iOS and Android apps are not yet available and builds go to a waitlist first.

  9. Hacker News AI40

    Show HN: Vibetime – see what you ship when coding with AI agents

    Vibetime is an npm-installable CLI that wraps Claude Code, Codex, Gemini, Aster, and Opencode in the terminal and uses session hooks to track the Claude Code, Codex, Cursor, and ZCode desktop apps, printing a session summary with git commits, line changes, and files touched when each session ends. It requires no config, daemon, or account by default, stores data locally in ~/.vibe/, and reads only git metadata, with an opt-in GitHub-based leaderboard that ranks sessions by commits with meaningful changes.

  10. Hacker News AI38

    Bringing Agentic AI to COBOL and the Mainframe with Rich Larin

    Recorded at IBM TechXchange 2026, RedMonk's Kate Holterhoff speaks with Rich Larin, IBM's Director of Z DevX & Platform Engineering, about bringing agentic AI tools to mainframe developers. Larin describes how Bob and the Premium Package for Z let COBOL teams use the same agentic IDE as other developers, with deployment options including SaaS, hybrid and air-gapped on-prem, plus Z code scan for deterministic security checks that Bob can remediate automatically and a data dictionary that captures experts' knowledge. He advises trying a proof of concept and hints at upcoming releases combining AI with analysis of very large applications.

  11. Hacker News AI12

    Costcrew a app to manage AI spending

    A Rust-built app called Costcrew tracks how much the creator spends on AI over time and aims to answer how much they spend on AI and which AI is worth spending on. The post describes it as having many features to help manage AI spending, and links to a Hacker News discussion with 1 point and 1 comment.

  12. Hacker News AI22

    AI Customer Driven Development

    Dr. Navraj Chohan proposes AI Customer-Driven Development (AI-CDD), a methodology where customers request capabilities in natural language, AI discovers or proposes them, human-governed engineering agents implement approved changes, and configuration-aware testing and telemetry govern product evolution. Existing features can be enabled via public toggles or found through embedding and vector search, while new requests go to product management for human review before AI agents implement, review, test, and document the feature behind a public toggle. Because the resulting configurations are exponential, AI would generate end-to-end tests for the configurations customers actually use and add them to the CI/CD pipeline.

  13. vLLM Blog63

    H3-Image Day-0 Support: 4K in 0.87s with Vera Rubin

    vLLM-Omni brought MiniMax H3-Image, an open-weight text-to-image and editing model, to NVIDIA Vera Rubin, reaching 0.87 seconds median for native 4096×4096 generation on four GPUs with SP4 and MXFP8 in a short-prompt serving benchmark. A separate SP1×DP4 throughput configuration delivers 6,115 images/hour, which the authors project to 146,755 images/day and, at an assumed USD 0.06879 per image, USD 105.16/GPU/hour gross revenue at full billable utilization before operating costs. The post also documents VAE decoding gains from CUDA Graph replay plus multiple streams (2.635 s to 0.213 s on four GB300 GPUs) and community validations on AMD, Intel, Huawei Ascend and Moore Threads hardware.

    Why it matters: Useful for readers weighing open-weight 4K image serving, since it separates latency and throughput operating points and labels its revenue projections as extrapolations before operating costs.

  14. OpenRouter Announcements58

    How We Built a Self-Correcting Localization System for OpenRouter

    OpenRouter launched beta localization into Simplified Chinese, Spanish, Brazilian Portuguese, German, French, Japanese, and Korean, using a daily pipeline that detects changed English strings, translates them with GPT-6.1 Sol, runs code checks, and has a second model verify meaning against the English, retrying with objections attached. Translations are committed as JSON catalogs in Git with fingerprints of their English source, and reader reports become glossary rules, style notes, overrides, or eval cases. A full retranslation of 16,918 strings into 7 languages costs about $460, versus about $7,200 at Smartling's published machine translation rate.

  15. Hacker News AI50

    Why AI Coding Agents Lose Context After the PR, and How to Keep It

    AI coding agents can write and test code but lose the delivery evidence produced after a pull request—failed builds, security findings, latency regressions—unless it is carried back into the workflow. The post describes Harness's Code Context Engine (from its Augment Code acquisition) for code context and its Software Delivery Knowledge Graph for delivery context, citing Augment's benchmark of 80%, 71%, and 30% improvements and Harness's internal estimate of about 12K tokens per graph query versus 250K+ via raw APIs. It presents a CVE workflow combining both, notes the two-way link between them is planned rather than shipped, and covers governance via policy as code, RBAC, and approval gates.

  16. Latent Space58

    The Jev Revolution: What Engineers Are Already Building with System One Models

    At the AI Engineer Code Summit, TypeSafe AI CEO Diogo Almeida argued that system one models like Jev—non-generative models returning structured choices, scores, or probabilities—should be integrated directly into application code to make software more reliable and automate more tasks. Glean's Chinmay Goyal said Jev is used alongside LLMs and other classifiers for its zero-shot flexibility, while UiPath and Workday engineers demonstrated prototypes including sub-second document-chunk ranking and interfaces that predict what a user wants to do while they type.

  17. Hacker News AI58

    What it takes to operate a SaaS when AI agents write all the code

    A solo founder describes running DocSpring, a document automation SaaS, with AI agents handling much of the coding, bug fixing, Sentry error triage, performance work and CI, coordinated across 49 Claude Code sessions. He reports shipping long-deferred features such as Word templates, a Page Designer and API v2, and clearing his inbox and error queues, while noting that agents can drift into unwanted behavior changes, as when a date fix expanded into an unplanned date-parser project. He concludes that he still sets priorities, approves changes and decides what to promise customers, and that AI does not by itself protect the business from competitors using the same tools.

  18. Hacker News AI60

    Show HN: Motion Debugger – A browser critic for AI slop

    Motion Debugger is a CLI and agent skill that critiques local pages in Chromium, recording entrances, scrolling, hovers, phone layout and reduced motion, then returns ranked fixes with screenshots. Its premium-motion skill runs an upgrade pipeline that keeps facts, links and forms while rebuilding layout and motion on a GSAP/ScrollTrigger/SplitText/Lenis stack or Motion in React. The author reports four single-run upgrades and a blinded four-pair A/B study where judges preferred the plugin's sites in all eight judgments, noting the sample is too small for significance.

  19. AWS Machine Learning Blog36

    Build autonomous AI agents with Amazon Bedrock and Spring AI

    This post shows how Java teams can build autonomous AI agents on the JVM using Spring AI and Amazon Bedrock AgentCore, with a single-agent travel assistant demonstrating tool calling, streaming, and memory, and a multi-agent intelligent document processing system with five specialist agents, a SpEL rules engine, and alerting. It covers the AgentCore runtime contract (@AgentCoreInvocation for POST /invocations and GET /ping), @Tool methods, structured output to Java records, memory advisors, and production patterns including Resilience4j retries, twelve-factor configuration, least-privilege IAM, Bedrock Guardrails, and Micrometer observability. Deployment uses an ARM64 image pushed to Amazon ECR and provisioned through modular Terraform, with an optional Amazon EKS and IRSA path.

  20. OpenRouter Announcements58

    Self-Hosted LLM vs API: When Does Self-Hosting Pay Off

    At October 8, 2026 prices, a 27B model on one rented RTX 3090 breaks even against API pricing at roughly 6–12% load, while DeepSeek V4.1 Flash on four rented H200s never beats the cheapest zero-data-retention API endpoint. The post computes break-even load as GPU hourly rent divided by the API cost of the same hour of tokens, using live per-provider prices and benchmark throughput, and notes that published self-hosting costs near a cent per million tokens mostly count cached input tokens that are also nearly free via API. It also covers privacy options such as provider.zdr and EU/US in-region domains, and suggests self-hosting a steady base load while sending peaks to the API.

  21. OpenRouter Announcements58

    How to Stop an AI Agent Stuck in an Infinite Loop

    OpenRouter describes four guards against runaway agent loops, tested on six models with its Agent SDK (@openrouter/agent 0.11.0): doom-loop detection, a loopKey that normalizes tool arguments, stopWhen caps on steps and cost, and a credit limit on the API key. With doomLoop: true, all six models were blocked on their third identical tool call, and across 18 runs detection cut tool calls from 314 to 64 and spend from $0.29 to $0.05. The article notes that loops vary between runs and that only the key-level limit caps total spend when agent code is buggy or caps are missing.

  22. AWS Machine Learning Blog58

    Introducing the Web Search API on Amazon Bedrock AgentCore

    AWS announced the Web Search API on Amazon Bedrock AgentCore, which lets developers call the InvokeWebSearch operation directly from AWS SDKs or the AWS CLI with SigV4-signed IAM credentials, without creating a gateway or other resources. It returns up to 25 ranked results from an Amazon-operated web index, each with a text extract and, when available, title, URL, and publication time, and supports domain and publication-date filtering. It is available in six Regions and billed at $7 per 1,000 queries, complementing the existing AgentCore Gateway path.

  23. AWS Machine Learning Blog46

    Detecting and recovering from silent data corruption on Amazon SageMaker HyperPod

    This post describes adding three checks to a PyTorch DDP training loop to detect silent data corruption (SDC), where hardware such as a GPU returns a wrong but plausible number without raising an error: a non-finite gradient check, a ring replay audit that recomputes another node's micro-batch and compares loss bits and gradient fingerprints, and a weight fingerprint comparison after the optimizer step. When a check fires, the suspect rank is mapped to its node via the Kubernetes node name, the node is cordoned, and SageMaker HyperPod replaces it, with training resuming from a checkpoint saved before the suspect window. The checks were tested with software-injected faults on a HyperPod cluster with 4 ml.p5.48xlarge instances (32 NVIDIA H100 GPUs) and repeated on three instances, with full code in an accompanying GitHub repository.

  24. AWS Machine Learning Blog38

    OpenAI Codex on Amazon Bedrock

    This AWS post explains how developers can run OpenAI Codex on the workstation while routing model inference through Amazon Bedrock using supported OpenAI models such as GPT-5.6 Sol, Terra, and Luna. It compares three access paths—Native AWS Access with IAM Identity Center, AgentCore Gateway, and an LLM Gateway—and recommends starting with a small, least-privilege pilot before expanding. It also covers validation steps, identity-isolation testing, OpenTelemetry and CloudWatch observability, cost allocation, plugins, hooks, MCP servers, phased rollout, and cleanup.

  25. Hacker News AI42

    Composing data pipelines in an AI-native workflow

    Fivetran describes its CLI as a terminal-native interface that lets engineers and AI coding harnesses (Claude Code, Codex, Gemini CLI, dbt Wizard) create connections, configure schemas, trigger syncs, and build custom connectors, with MCP servers supplying context from task trackers and observability stacks. The post walks through a session that lands Stripe data in Snowflake and ships an fct_mrr dbt model, then covers iterating on changed requirements and failed syncs, and offers guidance on scoped API keys, confirmation prompts, and prompt injection.

  26. AWS Machine Learning Blog38

    ICYMI: What landed for AI builders in October 2026

    AWS recaps its October 2026 releases for AI builders, including new Amazon Bedrock models such as Claude Haiku 5.5, OpenAI GPT-6.1 Terra, Amazon Nova 2.5 Sonic, GLM 5.3, and TwelveLabs Pegasus 1.5. Amazon Bedrock AgentCore gains a generally available CLI 1.0, model fallback and InvokeModel support in Gateway, Step Functions workflows as agent tools, and usage-based memory pricing, while Strands adds Bidi Agents, the Box local sandbox, red teaming in Strands Evals, and Decider on Gemma 4. The post also covers structured outputs for Claude models, Web Search domain filtering, a new Guardrails Standard tier for contextual grounding, and Amazon Bedrock cost breakdowns in AWS billing tools.

  27. Modal Blog58

    Modal becomes a gVisor maintainer

    Google is donating gVisor, including its name and trademarks, to the CNCF, and the project is moving to a maintainer-led governance model; Modal is one of three companies, alongside Ant Group and Tines, committing to join gVisor's maintainers, with OpenAI, Tencent and NVIDIA continuing their contributions. Modal says it has run gVisor as its major container runtime since the beginning, launching upwards of 40 million gVisor containers a day for GPU inference, multi-node training, AI coding agents and sandboxes, and has contributed upstream since 2023. The post details upstreamed work including nvproxy GPU support, an rdmaproxy device proxy for RDMA, snapshot/restore, and filesystem and memory performance improvements, and outlines future plans such as multi-GPU memory snapshots and GPUDirect Storage.

  28. Browser Use Blog34

    How to Use Custom Proxies with Browser Use

    This tutorial shows how to connect a third-party (bring-your-own) proxy to Browser Use Cloud by supplying the provider's host, port, protocol, and credentials when creating an agent run or cloud browser, then verifying the browser's exit IP and country via ipwho.is. It also demonstrates using the same credentials with Playwright both locally and against a Browser Use cloud browser over CDP, and compares managed proxy pricing ($5/GB) with BYO (provider rate plus $0.20/GB Browser Use egress). The guide includes setup steps, code samples, a troubleshooting table, and production tips such as preserving cookies alongside sticky sessions and stopping unused browsers.

  29. Pydantic AI Articles34

    What we found testing OpAMP clients against the spec

    Pydantic describes how its Logfire Fleet Management OpAMP clients for Rust, Go, Node.js, Python, Java and .NET share one Rust protocol core, run as WebAssembly or a native library, and are checked against roughly 300 normative spec statements, TLA+ models, Kani and Verus proofs, black-box conformance and fault testing. Running the same scenarios against upstream OpenTelemetry clients surfaced bugs in the Collector's OpAMP extension and Supervisor and in the Java, Python and .NET clients, including instance UID handling, reconnect and status reporting, capability declarations and startup panics, plus one critical security vulnerability that the core is not affected by.

  30. Hacker News AI60

    HuggingFace/Kernels: 200 WebGPU Kernels for Local AI

    Hugging Face released @huggingface/kernels, a minimal JavaScript library for loading and running optimized WebGPU kernels from the Hugging Face Hub, alongside an initial collection of 207 Apache-2.0 licensed kernels at huggingface.co/webgpu-kernels. Each kernel is published as a versioned repository containing a manifest, correctness and benchmark cases, and parameterized WGSL shader templates, and the team also launched Fleet, an in-browser GPU benchmarking suite that crowdsources correctness and performance evidence. In comparisons against ONNX Runtime WebGPU on an Apple M4 GPU across 809 matching cases, the kernels were 2.57x faster by geometric mean and 1.90x faster at the median.

  31. Hacker News AI22

    Show HN: Zumungo – AI-driven home automation

    Zumungo is a home automation tool accessed by pointing a browser at https://zumungo.local after installation; it advertises itself on the LAN via mDNS so the address resolves on Mac, Windows, iPhone, iPad, and Android, though older Linux may need Avahi installed. Because it uses a self-signed HTTPS certificate by default, browsers show a security warning that users dismiss via "Advanced → Proceed anyway." On first visit it offers to install a trusted certificate, or users can set up Cloudflare Tunnel for a real domain with a valid cert.

  32. AWS Machine Learning Blog12

    The attendee’s guide to the AWS re:Invent 2026 AI/ML track

    AWS will hold re:Invent from November 30 to December 4, offering over 2,000 learning sessions, with more than 140 in the AI/ML track spanning breakouts, chalk talks, builder sessions, workshops, code talks, and lightning talks. The guide organizes AI/ML sessions around the AWS AI stack—global infrastructure, AI chips (Trainium and NVIDIA GPUs), data foundation, models/training/inferencing (Amazon Bedrock and SageMaker AI), agent development and management (AgentCore), and agentic solutions—plus sessions on trust in agents, sustainability, and Local Zones and AI Factories. Breakout sessions are recorded and posted to the AWS Events YouTube channel a few days later, while other session types are live and not recorded.

  33. Hacker News AI20

    An AI-assisted RP2040 audio board that worked on first spin in 5 days

    Beyondex is a custom hardware mod that brings Valve Index audio to the Bigscreen Beyond VR headset, combining an RP2040-based DAC, battery management, and mechanical integration. After two failed designer attempts, the team delivered a production-ready design in five days, replacing the IP5310 power approach with TI's BQ25185 and fitting the board to a 24 mm by 50 mm envelope. From initial contact to shipping 200+ production units took weeks, not months.

  34. Simon Willison58

    aws-emulator

    AWS has released an official emulator for running tests against a local clone of its services without provisioning a paid API key. It is written in Rust and accumulated 29,684 commits in its first three weeks, with Swaminathan Sivasubramanian describing its origins in a guest post on Werner Vogels' blog. It currently requires Docker on macOS and Windows, and the author hopes a single downloadable binary will follow.

  35. MarkTechPost74

    Google Launches Gemini Decisions API With Gemini Decision 1 at $0.10/M Tokens

    Google launched the Gemini Decisions API, powered by the new Gemini Decision 1 model, which does not generate text but scores up to 1,000 typed questions against one shared input and returns calibrated probabilities for uses like routing, policy checks, tool selection and grading. It supports text, images, audio, video and PDFs with a 262,144-token context, bills $0.10 per 1M input tokens with zero output tokens, and is available only via the Google-hosted Gemini Developer API (v1beta). Google reports it leads 7 of 9 accuracy benchmarks in its table with a top-1 ECE of 0.0250, though it trails TypeSafe Jev 1.14 on When2Call (79.9% vs 82.0%) and costs more across the shared suite ($0.88 vs $0.68).

  36. Hacker News AI58

    I made an AI harness / orchestrator that *actually* gives you decent limits

    Scout is a Windows and Linux coding agent that pools the free tiers of five providers plus Kilo Code, OpenCode and OVH Cloud, falling back to the next model when one is rate limited, with free models limited to 10/min and 200/day without an account. It offers five permission modes, context pruning at 60k and compaction at 90k, self-maintaining memory in committable .scout/memory.md and ~/.scoutcode/memory.md files, and a Rust desktop app with a React WebView2 window shipping as an 18 MB executable. It also includes an issue tracker, remote control from a browser or phone, and an MCP bridge letting claude.ai, ChatGPT, Gemini and Grok use local file and shell tools.

  37. Hacker News AI22

    The role of natural scientists and hardware engineers in AI safety

    A physical scientist argues that natural scientists and hardware engineers are largely absent from AI safety work despite well-funded calls for their involvement, and that their "atoms" perspective could contribute physical-world defenses, physics-based cryptography, ecological analogies, and defense-in-depth approaches modeled on nuclear plant safety and airplane cockpit design. He attributes the gap partly to a culture difference between bits and atoms disciplines, and asks why the AI safety system of discourse, research, and funding excludes atoms people.