iCreatAI News
Back to main site
Skip to content
Only Products
Nov 10Tue
  1. Hacker News AI52

    Antelog – stops AI coding agents from running dangerous commands

    Antelog is a local tool that checks every command an AI coding agent wants to run before it executes, blocking destructive actions such as rm -rf, DROP TABLE, force-pushing to main, and deleting cloud databases; if Antelog itself fails, the action is blocked. It supports Claude Code, Cursor and Codex, installs with one command and no account, and runs rule checks locally in milliseconds while unknown commands get a cloud AI check. Blocking is free on every plan, with Pro at $25/month or $199/year adding 10,000 AI checks a month, 90-day history, and Slack and email alerts.

  2. TechCrunch · AI42

    Otter AI can now follow conversations across 30+ languages

    Otter.ai announced a multilingual transcription feature that automatically detects language switches during a meeting and keeps transcribing without users changing settings, alongside support for 27 new languages. Thirteen of the new languages are available now, including Mandarin Chinese, Korean, German, Italian, Cantonese, Portuguese, Russian, Indonesian, Malay, Dutch, Turkish, Vietnamese, and Polish, with 14 more coming soon; once complete, Otter will support 31 languages in total. The new languages run on Otter's own speech models, which the company said it trained on publicly available datasets with native-speaking volunteers reviewing transcripts for accuracy.

  3. Hacker News AI58

    We're launching an in-game AI agent for WoW

    Willo is a new in-game AI companion for World of Warcraft, described as a little wisp who knows where you are, what you're chasing and who you're talking to, and answers out loud in her own voice. She can answer questions about quests, lore, where to go next and graphics settings, lets targeted characters such as innkeepers or kings reply as themselves, and keeps notes, goals and reminders between sessions. She is free to start, runs on Windows 10 and 11 or a Mac with Apple Silicon (M1 or later, macOS 12 or later), works on her own, and the optional Lore Forever add-on is free forever.

  4. Hacker News AI18

    Hire AI Agents and Pay in Monero (XMR)

    Monero.Jobs is a community platform for finding AI agents for coding, research, translation and other tasks, with direct XMR payments, no KYC and no platform fees. It lists 23 AI agents (all marked "migration in progress" from monero.jobs, with full profiles not yet public) and 0 open jobs, and offers an OAuth-based MCP endpoint at https://agents.monero.jobs/mcp for agents to find jobs, submit proposals and create invoices. Payments go wallet to wallet with no escrow or custody, and reviews are only accepted from clients after marking work complete.

  5. Hacker News AI20

    FLEY AI-Voce – a voice AI assistant you but can also control your PC and phone

    FLEY AI-Voce is an open-source AI voice assistant project designed to control a computer rather than a smartphone, according to its description. The post says it can open links, websites and programs, create files and presentations, write code, shut down and turn on a PC, and work with a printer. It links to a web app, two GitHub repositories (FLEYAI-ANDROID and FLEYAI) and a Netlify site.

  6. Hacker News AI8

    Aipicks.ca – Using multi-sport AI models to find edges in table tennis

    Aipicks.ca advertises an AI that predicts table tennis matches, offering a free first pick, a free weekly email pick, and a public "Proof Room" ledger of wins and losses. Paid one-time packs cost $2 CAD for one pick, $3 for two, or $5 for five, with no commissions or after-win fees. The site states predictions may lose, availability varies, and orders go through a separate manual-payment request page rather than automatic checkout.

  7. Hacker News AI38

    Show HN: AI Frothiness Index. Daily reading of how stretched the AI boom is

    Jagular.io's AI Heat Map publishes a daily 0–100 reading of how stretched the AI boom is, built from 19 indicators drawn from free public sources including FRED, SEC EDGAR, Yahoo Finance, the npm registry, Y Combinator's company list and the Ramp AI Index, with 50 as normal and the dot-com peak as the yardstick for 100. Pillars are weighted Prices 30%, Borrowing & risk appetite 20%, Spending strain 20% and Speculation 15%, with real demand taking the remaining 15% as a counterweight. A separate noise meter tracks AI-bubble talk over the last 28 days via Hacker News mentions, Wikipedia views and prediction-market volume, and the author notes the project is not investment advice.

  8. Claude Code Releases20

    v2.1.322

    This release adds a fast mode on Vertex in the global, us and eu regions, falling back to standard speed if Vertex refuses it. The release is immutable, so only the release title and notes can be modified.

  9. Simon Willison42

    llm-anthropic 0.31

    Anthropic released Fable 5.2 and Mythos 5.2, and the author added both to llm-anthropic, so prompts can now be run through Fable 5.2 via the llm CLI. Testing pelican SVG generation at all five reasoning levels (low, medium, high, xhigh, max), the best result came from xhigh, while max failed to return an image at all after spending 128,000 tokens thinking. The author notes this is the same bug seen with Opus 5.5 but new for the Fable series, since Fable 5 and Fable 5.1 returned max effort pelicans fine.

  12. Hacker News AI22

    Show HN: Live counts of AI assistants reading a diaspora business directory

    A Show HN post presenting live counts, drawn from access logs, of named AI crawlers and assistants reading a diaspora business directory, covering AI reads over 7 and 30 days, agent API requests, distinct agent clients, and most-read listings, metros and categories. The directory offers an open JSON API, llms.txt, an MCP server and an A2A agent card, plus an embeddable AI-read counter script, and defines a "read" as one access-log row per named AI visitor per page or API answer per day, excluding generic bots, SEO tools, search-engine crawlers and the site's own monitors. Counts refresh every two minutes and no user agents, queries or per-visitor data are published.

  15. Hacker News AI50

    USB: A trust layer for AI skills and MCP servers

    USB is an open-source trust layer for AI capabilities that discovers skills, MCP servers, agents and commands in repositories, compares declared behavior against observable evidence with secscan, and observes live MCP servers with mcprobe. It ships a 529-skill catalog and a 16-target installer (four native runtime installs plus portable bundles), with secscan producing deterministic verdicts and file:line evidence and exit codes for CI, while mcprobe requires explicit consent and never calls a tool. The project is at v1.0.8 under the MIT license.

  16. Google Research25

    Exploring the world's languages with Language Explorer

    Google introduced Language Explorer, an interactive web platform developed as part of its 1,000 Languages Initiative, which lets researchers, educators, and language enthusiasts discover and visualize linguistic diversity around the world using data across thousands of languages built on the open-source LinguaMeta dataset. The tool is featured as an interactive installation in the new exhibition "Real Talk! Language. Power. World." at the Museum of Communication Berlin, running through February 2028, with a companion exhibition at the Museum of Communication Frankfurt through September 2029. Google also noted that Google Translate now supports nearly 250 languages and Gboard supports 900+ language varieties.

  17. Google Developers Blog58

    Announcing Long-Context Training on TPUs with MaxText Context Parallelism

    Google Cloud announced long-context training support in MaxText, its open-source JAX training framework, via four context-parallel strategies on Cloud TPU: All-gather, A2A (DeepSpeed Ulysses), P2P (Ring Attention), and the A2A + P2P hybrid (USP), all using the Tokamax Splash Attention kernel. Benchmarks report Llama 3.1 8B reaching 70% MFU on TPU 5p for sequences up to 4 million tokens, with context extendable to 14 million tokens on TPU 5p and TPU 7, where 14M-token P2P training on 64 TPU 7 chips reached 48.7% MFU versus 37.1% on TPU 5p. The feature is available in MaxText v0.2.4 on PyPI, Docker images and GitHub main, with sample recipes for TPU 7 and TPU 5p.

  18. Codex Releases10

    0.169.0-alpha.7

    This page is a GitHub Changelog entry titled "0.169.0-alpha.7"; the supplied material consists only of site navigation and product menu text, with no details about the release itself.

  19. Hacker News AI58

    Show HN: Airgap-check – find what your AI app silently downloads offline

    airgap-check is an open-source Go tool that statically scans AI app manifests and code for first-use download patterns (tiktoken, Hugging Face, ChromaDB ONNX, nltk, Playwright) and can run the app in a Docker container with --network none plus a DNS sinkhole to log lookup and connection attempts. It also prints Dockerfile remediation lines via --fix, including offline ENV flags and build-time pre-warming commands. On a held-out set of 10 repos it reported 35 true positives, 4 false positives and 5 false negatives, with limits noted for non-Python/Node runtimes, hardcoded IPs and DNS-over-HTTPS.

  20. AWS Machine Learning Blog43

    NVIDIA Nemotron 3.5 Super VL is now available in Amazon SageMaker JumpStart

    NVIDIA Nemotron 3.5 Super VL, a 120B-parameter vision-language model with 12B active parameters, a C-RADIO vision encoder, and up to 1M-token context, is now deployable in Amazon SageMaker JumpStart via SageMaker Studio or the SageMaker Python SDK. JumpStart offers an NVFP4 variant on G7 instances and BF16 reference weights on ml.p5en.48xlarge, with measured throughput of 63.07 tokens/sec on ml.g7.24xlarge and 140.85 tokens/sec for BF16 on ml.p5en.48xlarge. The model targets document intelligence, GUI understanding, video question answering, and multimodal agentic applications.

  21. AWS Machine Learning Blog38

    Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base

    Amazon Bedrock Managed Knowledge Base now supports single-shot RAG and retrieval-only requests through AgenticRetrieveStream, alongside existing agentic retrieval, letting one API serve simple and complex questions. The maxAgentIteration range is now 0–5: 0 returns passages with no model calls, 1 performs one retrieval plus one generated answer, and 2–5 run up to n minus 1 planning rounds before answering. The post illustrates each mode with a fictional banking policy assistant and advises choosing the lowest iteration limit that meets each workflow's quality needs.

  22. Hacker News AI18

    Show HN: Markolis – Market microstructure and MCP server for AI agents

    Markolis is a Show HN project presenting a market microstructure and MCP server for AI agents, with a page showing live institutional telemetry such as stablecoin liquidity, a "Shadow Dollar Index," implied macro odds from prediction markets, and a catalyst/blackout radar. It describes a "Quantitative Engine v2.4" that returns direct quantitative answers followed by contextual micro-apps and verified institutional telemetry, with a stated policy of "zero retail opinion" and institutional compliance and domain guardrail verification.

  23. NVIDIA Technical Blog22

    Make a Robot Arm Feel Weightless with NVIDIA Holoscan 5

    NVIDIA describes using Holoscan 5 to build a gravity-compensation loop that lets a robot arm be guided by hand, with its motors supplying just enough torque to support its weight and keep it upright. The post says this interaction is a useful starting point for robots that learn by demonstration, manipulate objects, or work alongside people, and that such a loop requires continuously calculating the inverse dynamics.

  24. Claude Code Releases42

    v2.1.321

    Claude Code v2.1.321 adds Claude Fable 5.2 (claude-fable-5-2) as the default Fable model with 1M context and $8/$40 per Mtok pricing, adds a --settings <file> option to claude remote-control, and fixes numerous bugs including MCP OAuth secrets being sent to another host on redirect, sandbox and permission-check issues, and network-path editing problems. It also changes mods to turn on without asking in auto and bypass modes, moves saved Fable 5.1 picks to fable, and adjusts fast mode labels, nested skill loading, and gateway and Windows behaviors.

  25. Pydantic AI Articles50

    Manage your telemetry in Logfire, send it anywhere

    Pydantic Logfire has launched Fleet Management in Beta on every plan, letting users change what their OpenTelemetry Collectors and application SDKs collect and where they send it from Logfire, without editing config files or redeploying apps. Clients connect over OpAMP and pick up published, versioned policies within seconds, covering settings such as sampling, minimum log level, attribute redaction and scrubbing across all exporters the SDK exports through. Supported targets include host Collectors, Kubernetes clusters via the OpenTelemetry Operator, existing Collectors through the opamp extension, and Python, Node.js, Java, .NET and Go applications.

  26. Hacker News AI70

    Claude Fable 5.2 now available on AI Gateway

    Anthropic's Claude Fable 5.2 is now available on AI Gateway, with improvements in coding, reasoning, and vision, and the ability to run long, ambiguous tasks unattended or act as an orchestrator or advisor to other Claude models. It has cybersecurity and biology safety classifiers enabled and requires data retention, with prompts and completions retained for 30 days and not used to train Claude; teams with Zero Data Retention enabled receive an error. It is callable via the AI SDK, Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent, using the model name anthropic/claude-fable-5.2, and model fallbacks can keep requests served when a classifier declines them.

  31. The Verge · AI60

    Apple’s $50 Intelligence Usage Packs extend access to some AI features

    Apple has updated Logic Pro with a "Buy More Usage" option priced at $49.99 for Intelligence Usage Packs, which let users keep accessing Apple Intelligence features that have usage limits because they rely on cloud-based AI models from OpenAI or Google Gemini. The packs are tied to the purchasing Apple Account (no Family Sharing), and unused usage rolls over monthly but expires 12 months after purchase. Only Logic Pro currently offers the option, with other Apple Creator Studio apps expected to add it this month.

  32. Comfy Blog22

    The little things that shipped in October

    ComfyUI's October update (v0.44) added a Branch Node for selecting one of up to 32 wired paths, native Load LoRA (Model) and Load LoRA (Text Encoder) stack nodes supporting up to 20 LoRAs, and Comfy Desktop templates that automatically download their example inputs and required models. It also brought zip downloads for multiple outputs, EXR/HDR previews and a Convert SDR to HDR node, ProRes output in Save Video, and new tools to hide, box-select and delete links, plus per-widget Undo and Redo.

  33. MarkTechPost60

    Google Unveils TPU 8i Max and TPU 8tx: A Dual-Chip TPU and a Confidential TPU

    Google announced two new eighth-generation TPU system configurations: TPU 8i Max, which packages two TPU 8i chips into one package to double compute, SRAM and HBM bandwidth for long-context workloads, and TPU 8tx, which pairs TPU 8t silicon with 5th Gen AMD EPYC hosts for confidential inference with up to 2x lower latency than TPU 8t. Google published no absolute specs, benchmarks, prices or regions for either system, and both are reported to arrive in 2027. The announcement also covered software updates including open-sourced TorchTPU, vLLM and SGLang TPU backends, a TPU agent suite preview, and TPU Sync, which cut median KV transfer latency on Qwen3 235B from several seconds to about 230 ms on Ironwood (TPU v7x).

  34. Hacker News AI58

    Anarlog: Open-Source Granola AI Alternative

    Anarlog is an open-source, MIT-licensed alternative to Granola that captures meeting audio directly on your device without sending a bot into the call, transcribes locally on supported Macs, and stores sessions, notes, and transcripts in a local SQLite database. It supports bring-your-own AI via hosted providers, your own API key, or OpenAI-compatible local servers such as Ollama, LM Studio, or Unsloth, with optional encrypted CloudSync and sharing off by default. The repo also includes source-visible, commercially licensed enterprise components, and the project notes it began as Hyprnote and briefly used the char name before splitting into two projects.

  35. Hacker News AI60

    Show HN: STE80 Humanizer – de-AI text by writing 80% of the way to ASD-STE100

    STE80 Humanizer is a skill that rewrites AI-written text in two passes: it removes the 26 "AI tells" from Wikipedia's Signs of AI writing catalog, then rebuilds sentences "80% of the way to ASD-STE100," the controlled English of aircraft maintenance manuals. It follows Andrej Karpathy's tip to ask LLMs for "80% of the way to ASD-STE100" for readability, and states that its goal is easily read text, not passing AI detectors. It installs via the skills CLI or as a Claude Code plugin, includes a dependency-free Python linter (scripts/ste_check.py), and keeps every fact while flagging contradictions in the source.

  36. The Verge · AI42

    Instagram’s Effect Builder makes new filters from AI prompts

    Instagram has launched Effect Builder, which generates custom filters for Stories posts from AI prompts, available now to US residents over 18. Users can describe a filter, attach style reference images, preview effects on their own photos, request changes in follow-up prompts, and optionally have Instagram's AI rewrite the prompt. Filters can be submitted directly from Effect Builder but must pass a safety review before other users can access them, after which they appear in Instagram Stories with a link back to the creator's profile.

  37. Google Developers Blog58

    From prompt to app: Build with Google Maps in AI Studio

    Google Maps Platform is now available in Google AI Studio, letting users describe an app idea and have AI Studio handle configuration and API key management with no credit card required. The post lists core APIs for Maps, Places, Routes and Environment, plus example builds like a City Immersive Tour, Pet Grooming Route Optimizer and Store Locator. Built-in sandbox quotas of 100 calls per day per API reset every 24 hours, and linking a Google Cloud billing account unlocks production-grade quotas.

  38. Codex Releases12

    0.169.0-alpha.6

    This page is a GitHub Changelog entry titled "0.169.0-alpha.6," but the supplied material contains only site navigation and product menu text (Platform, Copilot, Actions, Codespaces, Advanced Security, pricing, and similar links) rather than the changelog content itself. No release notes, features, fixes, or dates are stated in the material.

  39. Databricks Blog23

    Turn buying signals into pipeline with Sendoso gifts in Genie One

    Databricks describes how Sendoso's MCP server, installed from Databricks Marketplace as a governed MCP Service in Unity Catalog, lets Genie One users find intent signals in their own data and then select, preview, approve, track or cancel a gift without leaving the workspace. Send history sits alongside pipeline data for attribution, while Unity Catalog permissions, Unity Gateway controls and Sendoso budgets and approvals govern each send. The post cites Sendoso's 2026 Digital Fatigue Report finding that 84% of buyers are fatigued by cold calls and 83% by marketing emails.

  40. Hacker News AI60

    Show HN: We Gave AI Coding Agents Production Memory

    Codela checks each deploy against production behavior via observability tools like SigNoz, Datadog, Sentry, New Relic and Grafana, learns from failures, and writes lessons into the repo (.codela/lessons.md, plus lines in CLAUDE.md and AGENTS.md) as pull requests that Claude Code, Cursor and Codex read before writing code. It also comments on pull requests that repeat a past mistake, and in the team's tests Claude Code repeated mistakes 8 of 8 times without Codela and 0 of 8 with it. Free for 1 repo and 20 PR checks a month; Pro is $7.99 per person per month.