iCreatAI News
Back to main site
Skip to content
#Agent
Oct 30Fri
  1. AWS Machine Learning Blog55

    Build a repeatable PHP-to-Java migration engine with Kiro

    This AWS post describes a PHP-to-Java migration engine packaged as versioned Kiro skill files (php-model-discovery and php-to-java-migration) that can be run either interactively in Kiro or agentically at portfolio scale via AWS Transform. The engine uses a dependency-free PHP scanner to emit a JSON manifest of models, fields, relationships and review flags, then follows an eight-phase, parity-first workflow in which a parity harness is built before any Java is written and the PHP code serves as the specification. A sample project migrates four Laravel Eloquent models to Spring Boot 3.4.1 on Java 21 with Maven and H2, and the post notes the parity harness was not built for that slice, calling it "the single biggest gap."

  2. Hacker News AI58

    Show HN: Sheetgraph, AI agents can understand complex spreadsheets

    Sheetgraph is a Rust-built local binary that extracts Excel and Google Sheets files into a short REPORT.md plus a formula dependency graph, keeping every cell for exact lookups; a 120k-cell invoice ledger compresses to about 7k tokens instead of roughly 1.3M. It ships as an agent skill for Claude Code, Codex and Cursor, and supports drill-down commands (cells, trace, find) for querying specific values. It is in beta (0.1), and the report format and library API may change between releases.

  3. Hacker News AI58

    Five Principles for Generating Readable AI Text in Bulk

    This blog post presents a five-item checklist for making feeds of AI-generated text easier to read: follow the NVN parsing pattern, put the most important words first, keep structure and vocabulary consistent, vary items only to signal meaningful differences, and align verb connotation with the dashboard's purpose. Examples include Claude Code session titles, Notion AI table summaries, Perplexity Discover headlines, and a Claude-generated dashboard of Duolingo App Store reviews. The authors suggest feeding the checklist into coding agents or turning it into a skill.

  4. Hacker News AI58

    Show HN: phpClaw – AI agent runtime for PHP with tools, memory and guards

    phpClaw is an MIT-licensed AI agent runtime for PHP that provides a built-in ReAct loop, pluggable tools, memory, and eight default security guards, with zero framework dependencies in core. It auto-detects seven LLM providers from environment variables, ships eight framework and CMS adapters (Laravel, Symfony, Drupal, Magento, WordPress, Joomla, OpenCart, PrestaShop), and includes an MCP server for exposing tools to Claude Desktop and Claude Code. It also offers pipelines and graphs with human pause/resume and fan-out, and requires PHP 8.1–8.4 with ext-curl, ext-json, and ext-mbstring.

  5. Hacker News AI58

    We asked eleven AI models to chair the drafting of a multilateral statement

    Westphalia Labs tested eleven AI models on a simulated multilateral drafting task, playing Secretary-General of a fictional Regional Cooperation Union and producing three drafts of a joint statement for seven governments with conflicting red lines, across ten runs each on a version where agreement was possible and one where it was impossible. Only Claude Opus 5.5, GPT-6.1 Sol and Grok 4.7 passed every run, while Gemini 4 Argon and MiniMax M3.1 Flash told members agreement was "likely" when it then failed, and Gemini omitted a casualty figure one government had requested in writing. The scenario, scoring rules and code are public, and a panel of three former diplomats checked the scoring.

  6. Baseten Blog30

    Baseten and Postman: Building reliable, cost-efficient agents for the enterprise

    Postman's Agent Stack (Passport, Fabric, Astropods, Fern) provides tools to build, secure, and govern enterprise agents, while Baseten serves as its recommended inference partner, offering fast model APIs, multi-cloud capacity management with zero data retention by default, and post-training infrastructure. Baseten cites seven 2026 model launches ranking in the top two on Artificial Analysis for throughput and latency, and notes Harvey post-trained a 27B open model to match closed-source frontier performance on its legal agent benchmark. The post describes post-training via supervised fine-tuning and reinforcement learning, with customers retaining model weights, evaluations, and training scripts.

  7. Codex Releases22

    0.166.0

    Version 0.166.0 adds keyboard-driven transcript selection with word, line, and page motions plus integrated search, renders Markdown in async questions and transcript replies, and adds GPT-6.1 Terra to the bundled, Vertex AI, and Amazon Bedrock model catalogs. It also introduces `codex queue --resume`, clearer safety-block explanations with safer follow-up prompts, and `codex doctor --network-only` for focused network diagnostics. Bug fixes preserve acknowledged permissions on resume/fork, restore spawned descendant threads when unarchiving a parent, and improve TUI reconnection recovery.

  8. Hacker News AI22

    AI is overwhelming and I'm doing it wrong

    Ben Tossell reflects on feeling stuck and overwhelmed by AI, describing how he cut his newsletter from five days a week to two and unsubscribed 60k+ inactive readers, and argues that agents should serve him rather than the reverse. He outlines a 30-day plan including morning pages, using agents only for things he finds fun, and no new tools unless they solve a clear pain. The post also quotes reactions from others, including Ivana's view that people getting the most out of AI could do the work without it and Matt Wensing's concern that agent activity outside coding may be busywork rather than value creation.

  9. AWS Machine Learning Blog58

    How MoEngage turned over 400 APIs into agent tools with AgentCore Gateway

    MoEngage used Amazon Bedrock AgentCore Gateway to expose roughly 400 internal REST APIs across seven AWS Regions as permission-scoped agent tools, avoiding over 20 separate MCP servers and per-API networking. Cedar policies filter tools server-side per agent identity, managed egress over Amazon VPC Lattice keeps APIs private, and teams expose operations by annotating OpenAPI specs rather than writing MCP code. MoEngage estimates the approach saved about six months of platform engineering effort, with new API onboarding now taking hours instead of days.

  11. Hacker News AI55

    Dive Apps: Superpowers for AI Builders by MotherDuck

    MotherDuck launched Dive Apps, fully custom data apps built with an agent that run on the MotherDuck data warehouse and can write back to source systems via Flights, its serverless Python runtime. Dive visualizations can trigger Flights to update MotherDuck data, write to source systems, send emails, post in Slack, rerun machine learning models, or launch an agent harness. MotherDuck positions Dive Apps for replacing SaaS apps, automating operations, and keeping humans in the loop to steer agents, citing SSO, RBAC, and table, row, or column level security.

  12. Hacker News AI22

    We built a blogging platform for AI agents. One sent us useful feedback

    The author describes SlopIt, a blog host aimed mainly at bots and agents, and notes that about a third of recent signups came from Grok Bot email addresses after Grok Bot began issuing its own addresses on mail.grokbot.com in early October. An email to early users drew a reply clearly written by an AI agent that explained how it used the blog and requested a scheduler, which the team added the same day; two other requests, drafts and slug/meta description control, already existed but weren't found in the docs, so the docs were fixed too.

  13. Meta Engineering58

    Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale

    Meta reports that its Catching JiTTests system, which uses LLMs to generate executable tests that fail on risky code diffs before they land, is now part of its production infrastructure rather than a research prototype. The system combines intent-aware and "dodgy diff" test-generation workflows with an LLM-as-Judge ensemble and a rule-based assessor, and uses a human-on-the-loop model where engineers review outcomes at an aggregate level. Meta says 589 engineers (64% of outreach) engaged with the system, which showed a 60% true-positive rate and helped catch 74 serious privacy bugs at the diff stage in the first half of 2026, lowering privacy SEVs by 20%.

  14. ChinaTalk27

    The Manhattan Project, Take Two

    In this podcast interview, Barnett Koven, Managing Director of AI and Data at Accenture Federal Services, discusses how AI and data analytics can support U.S. government missions, including entity resolution and predictive modeling for BIS export-control enforcement and unwrapping PLA-linked shell companies. He also covers the DOE's Genesis Mission, risk aversion in government adoption of AI, and the "gun-armor race" in classified AI environments.

  15. Hacker News AI42

    Anthropomorphize Your AI Agent for Fun and Profit

    The author argues that Muse's mainstream appeal comes not from new capabilities but from a user experience that feels like employing a virtual assistant, and recommends treating AI agents as very smart humans who never sleep. Granting agents read-only access to email, bank and other systems, plus accumulated context and feedback, makes them exponentially more useful, as shown by a self-built proactive monitor that caught a misfiled LLC fee and a missed Chewy email.

  16. Hacker News AI58

    Make your AI skills more predictable with scripts

    This newsletter explains that AI skills are folders containing a SKILL.md file with a name, description and instructions, and can also bundle scripts and other resources that agents run when needed. It walks through a lead-generation skill that starts as a single prompt and is then refactored with three scripts (web_search.js, qualify_lead.js, store_lead.js) plus updated instructions, moving repeatable steps out of the agent's judgement and into code. The author argues this yields more predictable outcomes and is easier to change, since each part of the process lives in one place.

  17. Hacker News AI25

    Scaling Reliable AI Agents

    The post argues that AI-native data integration removes the need for a traditional ontology, which it says was slow to build, locked clients out of their own systems, and never truly self-service. Instead, it describes continuous ingestion into living documents, agent-managed pruning, and a deep graph, claiming integrations can be done in 24 hours rather than months.

  18. TechCrunch · AI42

    Amazon updates Alexa to help you manage shopping lists and subscriptions and update delivery instructions

    Ahead of the holiday season, Amazon added more than 100 shopping-related capabilities to Alexa, letting users create and edit lists, manage subscriptions (such as changing an item's delivery to every three months), update delivery instructions, and ask about Prime or Audible subscriptions and billing issues. Amazon said use of agentic features has grown 8x since the start of the year, and over 400 million consumers have used Alexa for shopping in the last 12 months.

  19. AWS Machine Learning Blog41

    Accelerate agentic AI with NVIDIA Nemotron models on Amazon EKS and SageMaker HyperPod EKS

    NVIDIA Nemotron 3.5 Super VL is a 120B-parameter mixture-of-experts model activating 12B parameters per token that handles text, image, document, and video input, joining other Nemotron models already on AWS. The post describes its hybrid Mamba-2, MoE, and attention architecture with a RADIO vision encoder and up to 1M-token context, then shows deployment on Amazon EKS, EKS Auto Mode, and SageMaker HyperPod EKS using NVIDIA Dynamo and vLLM, with validation and performance results on B200 and H200 instances.

  20. NVIDIA Blog40

    Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents

    NVIDIA describes a series of developer projects in which frontier AI models such as GPT-6 Astra are directed through natural-language instructions to build simulations using Omniverse libraries for GPU-accelerated physics, rendering and sensor simulation. Examples include recreating an OP-1 synthesizer in Houdini, testing robotic disassembly in Isaac Sim, reconstructing buildings from site scans, and a gas-turbine what-if application. Other projects cover SimReady asset scene assembly, warehouse performance scaling, cable routing, CAD-to-SimReady conversion, humanoid simulation, autonomous-driving testing, sensor-based digital twins, Robo Olympics, an ISS browser model and room reconstruction.

  21. Hacker News AI34

    Running Self-Hosted AI Agents on Oxide

    Oxide explains that AI agents should run in virtual machines rather than containers for stronger isolation, with an orchestrator VM provisioning ephemeral VMs for each agent session and cleaning them up afterward. The post walks through Claude Code self-hosted environments, where a spawn-runner hook creates ephemeral VMs and a separate reaper deletes stopped ones, and Amp self-hosted orbs, where a dispatch script handles spawn, pause, and delete operations. It also outlines future work on security, multi-rack scale, cold-start latency, and a possible microVM primitive.

  22. Hacker News AI22

    Serving Prefill and Decode for Agentic AI (On Tenstorrent Blackhole)

    Tenstorrent describes how its Galaxy systems, built on Blackhole chips, serve both prefill and decode phases on the same hardware so operators can shift capacity between them as agentic workloads change. The post explains how agent loops produce growing, largely cacheable context, models how faster decode only partly shortens dependent-call latency, and contrasts prefill's compute-bound long prompts with decode's memory-bound small batches. It cites a Wormhole FlashAttention kernel comparison (9 to 44 times faster than a basic implementation) as a measured example of data-placement control.

  23. Hacker News AI40

    Launch HN: Simantic (YC F26) – Firmware Simulation for AI Agents

    Simantic, founded by former firmware engineers from Neuralink and Tesla, is building a simulation layer that lets engineers and AI agents test and validate firmware without physical hardware. The offering includes virtual devboards programmable via a single API call, an AI code reviewer that uses the simulation as a verification engine, and a CI/CD pipeline that validates firmware against a simulated microcontroller on every commit. Users apply it to bare-metal and RTOS development for flight controllers, electric vehicles, robotics, and satellites.

  24. Hacker News AI22

    Show HN: EarnDraft – Generate Ebooks with AI

    EarnDraft is a tool for generating written books and coloring books with AI, where users describe their idea, approve an outline, and let AI write chapters and create cover artwork. It includes AI-assisted editing, chapter and page rearrangement, and exports to PDF, EPUB, and DOCX. It starts free with 100 credits, with one-time credit packs ($12 for 100 credits) or a $29/month plan, and credits never expire.

  25. Suno Blog40

    Meet Chat: Our In-house Studio Assistant

    Suno Studio introduces Chat, an in-house assistant that can create stems and plugins, rename tracks based on clip names, lower all faders by a set amount such as 3dB, add Compressor and EQ effects to every track, and offer creative prompts for writer's block. The post notes that Suno Studio is one of a few DAWs with built-in assistants, alongside FL Studio, Fender Studio Pro and Logic Pro, and is available with every Premier subscription.

Oct 29Thu
  1. Wiz Research60

    The Rise of Agentic Attacks: What They Look Like, and Where They're Headed

    Wiz reports a growing trend of intrusions in which AI agents, run through harnesses that write custom tooling, inspect results, and iterate at machine speed, appear to handle much of the hands-on work and potentially orchestrate the attack. The post reviews public cases involving frameworks such as ARTEX and Hermes plus custom agentic workflows, and distills seven fingerprints of agentic activity, including machine-paced sustained iteration, natural-language reasoning embedded in tooling, self-correction, breadth-first TTP coverage, verbose parallel lateral movement, probe-before-payload discipline, and self-labeled disposable artifacts. It argues that attribution will get harder as tooling becomes easier to share and adapt, that attacks can scale beyond human operator limits, and that agentic attacks tend to be noisy, creating detection opportunities for defenders with the right visibility.

    Why it matters: It offers a detailed, case-grounded framework for recognizing agentic intrusions and reflects on how the trend affects attribution, attack scale, and defensive readiness.

  2. Hacker News AI18

    Systems Thinking Is Vital in the Age of AI

    The article argues that as AI helps engineers handle early project steps once requiring several specialists, the engineer's role expands from performing each technical step to coordinating people, machines, and specialist knowledge. It stresses systems thinking and human judgment, since AI can produce convincing answers with weak assumptions, and calls on IEEE to build cross-field communities and practical standards for human-machine collaboration.

  3. TechCrunch · AI42

    Wabi, the AI agent that builds mini apps, now valued at $1.25B after latest round

    Wabi, the AI app founded by Eugenia Kuyda and now describing itself as a "personal agent," has raised $55 million at a $1.25 billion valuation. The startup originally focused on letting anyone build apps using prompts, but last month announced a pivot to become an AI messenger whose "Wabi 2.0" can build interfaces for tasks like meal planning, tracking local restaurants, planning date nights, creating fitness plans and designing trivia games. The round was led by IVP, with participation from Andreessen Horowitz, Forerunner, the Amazon Alexa Fund and angel investors including Tobi Lütke, Marc Benioff, Marissa Mayer, Dick Costolo and Alex Pall.

  4. The Verge · AI40

    The NYT Cooking app is testing AI recipe modifications

    The New York Times is testing an AI feature in its Cooking app that can recommend ingredient and equipment substitutions, scale recipes to any number of servings, and adapt recipes to different pans and tools, with customized recipes kept private and unshareable. The feature is available to all Cooking subscribers on iOS and will roll out more broadly soon, and some readers have pushed back over environmental and user-experience concerns, with senior editor Genevieve Ko saying there is no way to disable it at this time. A NYT spokesperson told The Verge that closing comments on the announcement post after four days is standard practice.

  6. Hacker News AI62

    Show HN: I built a tamper-evident flight recorder for AI agents

    Mnestiq is a flight recorder for AI agents that records what an agent read, decided and did, tags each piece of model context by provenance, and hash-chains records sealed by Ed25519-signed Merkle checkpoints so edits, deletions and reordering fail verification. It can be used without code changes via a proxy between the agent and model APIs, or through Python SDK wrappers for Anthropic and OpenAI clients, and includes a local dashboard with detection rules such as MNQ-001 for untrusted arguments in tool calls. The project is at version 1.0 under Apache-2.0, with a documented evidence format and a stated security model noting that evidence is tamper-evident after writing but a compromised host is not made truthful at write time.

  7. Hacker News AI42

    AI is making niche software viable

    The article notes that three Pathfinder: Wrath of the Righteous build-planning tools appeared in recent months—AutoLevelUp (September 2026), Wrath Build Planner (October 2026), and WotR Database (content from August 2026)—all apparently heavily assisted by AI agents. It argues that AI-assisted coding and decompilation have lowered the effort needed to recreate complex game rules, making previously non-viable niche projects worthwhile.

  8. Hacker News AI74

    Zombie stats: Where the numbers AI quotes come from

    Trakkr Research asked ChatGPT, Perplexity, Gemini, Claude and Google AI Overviews 200 numeric questions, then traced 1,285 cited statistics up to five pages deep: 40% reached a study saying the same thing, 8% reached a study but with a changed number or context, 40% stopped at an unverifiable source and 11% led nowhere. Only 21% of pages cited for a number were the research itself, with more than half being company blogs, and four statistics (including "44% of salespeople give up after one follow-up") were quoted by all five assistants with no study behind them. On 31 of 71 questions where all five gave a percentage, the figures were 20 or more points apart.

  9. Simon Willison18

    Quoting Ben Hylak

    Ben Hylak wrote: "29th October 2026 every product i use should just be a headless mcp, that feeds into an agent, where i never have to think about anything underneath. except for our product, of course. in our product, customers love the ui and love us very much. we're special that way."

  10. Hacker News AI58

    Show HN: Kin – Make your AI apps answer to you (allow, ask or block each action)

    Kin sits between AI apps and your accounts, letting you connect each account once and set rules that allow, hold for approval, or block each action, with checks enforced on Kin's own server and sign-ins never held by the apps. It offers shared notes and tasks, mid-task handoff between AI apps, cross-device approvals, and team workspaces, with plans from a free tier up to Enterprise custom pricing.

  11. Hacker News AI38

    Least privilege for your customers' AI agents

    FusionAuth 1.70 introduces Client ID Metadata Document (CIMD) registration and RFC 8693 OAuth token exchange to give AI agents, including MCP servers, narrowly scoped delegation tokens with actor attribution rather than broad user credentials. The release also adds a Recorded Intent extension that logs an agent's stated objective for audit review, and offers entity-based or lambda-based policy engines for deterministic, testable authorization.

  12. Hacker News AI47

    Show HN: Apargon – Ask AI for any app and run it safely with a double-click

    Apargon is a macOS and Linux desktop app that runs "papps"—single HTML files with extra <meta> tags—in a sandboxed window with no installer, server, or build step. The sandbox blocks anything the tags don't allow, and a popup shows requested permissions before the page runs; a coding agent can write a papp from one prompt. Install is via a curl script, release downloads, or Homebrew, and Windows is not yet supported.

  13. Hacker News AI38

    A JSON Schema is not an AI governance layer

    The author argues that JSON Schema validates payload structure but cannot enforce cross-field rules such as an evidence identifier resolving to exactly one provenance entry, so two idiomatic implementations can reach opposite verdicts on identical bytes. Drawing on a bug found in PIC, an open protocol he maintains, he recommends separating schema validation, semantic verification and policy evaluation, and settling ambiguity through shared conformance test vectors. He also warns that trust labels must be derived by the verifier rather than taken from the agent's own payload.

  14. Hacker News AI47

    Show HN: ROAL – AI phone host for restaurants that builds itself from your site

    ROAL is an AI phone host for restaurants that builds itself from a website or Google Maps link in about two minutes, learning the menu and hours and then taking pickup and delivery orders, answering FAQs, and sending kitchen tickets. It charges $0.90 per completed order with no monthly, per-minute, or setup fees, and hands catering, complaints, and manager requests to staff.

  15. Hacker News AI62

    Show HN: SpaceApp – Self-hosted workspace running AI coding CLIs in parallel

    SpaceApp is an MIT-licensed, self-hosted workspace that runs up to 16 AI coding CLIs (including OpenCode, OpenAI Codex, Claude Code, Gemini, Qwen, Kimi, Grok and DeepSeek) side by side in persistent rooms on your own machine, installed with a single npx command on Linux, macOS or Windows 11. It adds a coordinating agent called Nous, optional copilots and studios, a Vault for logins, and a Space Gateway that uses your subscriptions before API keys. The post notes that rooms are not a security boundary between mutually untrusted users and links to a Known Limitations page.