iCreatAI News
Back to main site
Skip to content
#Agent
Oct 31Sat
  1. Databricks Blog42

    Databricks and SAP unleash end-to-end data & AI capabilities to level up enterprise AI transformation

    At SAP TechEd, Databricks and SAP announced an expanded partnership bringing the full Databricks Data + AI Platform—including Genie, Lakeflow, Unity Gateway and Lakebase—into SAP Databricks within SAP Business Data Cloud, alongside SAP Application Data Foundation for cloud-native access to SAP application data without custom extraction pipelines. The companies cite customers such as Adidas, Zalando, Mondi, CAF and SAF-Holland, which uses SAP BDC and SAP Databricks to unify over 100 million records and generate analyses 5x faster. SAP Databricks and SAP BDC Connect for Databricks are available today.

  2. Hacker News AI58

    Show HN: mobile-agent – Let AI agents control Android and iOS devices

    mobile-agent is an experimental, MIT-licensed tool that drives Android devices and emulators, iOS Simulators and physical iPhones for AI agents, using a daemon that keeps a live mirror of each attached screen to answer snapshots, waits and settle checks without reading the device on every request. On Android a single-dex agent runs as the shell user via app_process with no APK or instrumentation, while on the iOS Simulator input goes through dtuhidd and frames from IOSurface; a physical iPhone needs a signed XCTest runner for its accessibility tree. Its CLI follows agent-browser's command grammar, @eN refs and JSON envelope, and a mobile-agent-mcp server exposes the same tools to MCP clients; nothing is published to crates.io or as a binary yet, so it is built from source.

  3. Hacker News AI60

    Don't Make a Human Do What AI Is Amazing At

    The author describes "Nunebot," a 229-line markdown prompt stored in a private git repo called "brain" that an agent runs over his repositories in priority order, gathering production context via MCPs, picking one small "obvious yes" change per repo, building it in its own worktree, running /simplify, /qa and /codex review, and opening a labeled PR with proof while never merging or deploying. He reports 269 PRs opened across 20 repos from October 18 onward, 250 merged, a median merged PR of 43 changed lines, and 113 merges in one weekend, with a taste.md file of 107 rules accumulated from his rejections.

  4. Hacker News AI22

    Blog: AI is in its Homelab era

    The author argues AI is popular but far from saturated, comparing today's expensive, maintenance-heavy AI usage to the homelab era that cheap cloud services later commoditized. He predicts AI will follow the same curve toward cheap, forgettable infrastructure, with a credible personal agent common on phones by around 2031, and warns that a hostile launch environment and infrastructure costs will shape which products win.

  5. MarkTechPost62

    AI Security Agents Compared: Claude, Codex, Mantis, Cloudflare

    Anthropic, OpenAI, Cloudflare and Google each now ship an AI agent that hunts security bugs in source code, and all four converge on the same design: one agent finds a bug, a separate agent tries to disprove it, and only survivors get a patch. The tools differ in where they run, who can use them and how much proof they demand — Claude Security runs inside Claude Code with no extra API key, Codex Security's CLI is Apache-2.0 but scanning needs OpenAI access, Cloudflare's skill is MIT and model-agnostic, and Google's Mantis reproduces bugs in a sandbox. The article attributes the shared pattern to noisy scanning (Google cites true-positive rates under 7%) and to attackers already using AI to find exploitable flaws.

  6. MarkTechPost71

    Meet TokenEconomizer: Microsoft’s Plugin That Cuts Coding Agent Costs by Up to 30.9%

    Researchers from Microsoft Research and UC Berkeley released TokenEconomizer, an open-source Apache 2.0 plugin that learns per-repository policies from past sessions to reduce waste in coding agents such as Claude Code, Codex, GitHub Copilot CLI and Pi, without touching model weights or agent code. On 277 SWE-Bench tasks it lowered mean cost by 18.4% to 30.9% across five agent-model settings and was cheaper in all 30 repository-setting cells, with Pass@1 improving in four of five settings and dropping 1.0 point on Opus 4.8. It combines micro-skills, tool pruning and failure-loop intervention, and installs with Python 3.10+ while keeping learned data local in ~/.tokeneconomizer.

  7. Databricks Blog22

    Wealth Management Client Onboarding Needs More Than AI

    This Databricks article argues that faster task-level AI does not fix wealth management onboarding delays, because cases still stall at handoffs between CRM, KYC, screening, custody and workflow systems where teams must reconstruct what changed and who owns exceptions. It proposes "governed case context"—a current, versioned, source-linked view of each case—plus supervised AI agents with human authority over exceptions and approvals, and outlines four platform capabilities and end-to-end measurement guidance. It cites figures including ~6 weeks to open a private banking account in Singapore, 60% of 144 wealth executives lacking a unified client view, and 41% of relationship managers' time spent on operational work.

  8. Hacker News AI58

    EasyRE-Agent – an AI agent that solves crackmes and checks its own answers

    EasyRE-Agent runs an AI agent inside a Docker container with a bundled reverse-engineering toolchain (Ghidra, Detect It Easy, Wine, decompilers for .NET, Python, Java and JavaScript) to solve crackmes and CTF binaries. It supports Claude Code, OpenAI Codex or any OpenAI-compatible API including local models, and only accepts an answer once it passes a regex, success message or custom verifier command. It also offers hint and tutor modes, per-job time and token budgets, resumable jobs, and reports with the answer, solution path, scripts and model stats.

  9. The Decoder78

    A Claude model autonomously chose a gene therapy and operated on a mouse brain with no human decision-making

    An AI agent using Claude Sonnet 5 selected a gene therapy, brain target, and stereotactic coordinates for a mouse epilepsy model and then performed the injection via a custom motorized surgical device, making 32 observations during the procedure, according to Exin Therapeutics cofounder Gabriel Ocana-Santero. After a connection drop, the agent detected its target was outside the device's range of motion and refused to continue despite a third attempt, and Ocana-Santero had to fix the code by hand; he said Sonnet 5 was the only model willing to complete the live procedure, as Claude Opus 5.5 and Opus 5 refused. The mouse recovered well, a technical report is expected, and the results have not been peer-reviewed.

    Why it matters: It offers a concrete, first-hand account of an agent making treatment decisions and acting on a live animal, including an unexpected refusal that highlights alignment and reliability issues in time-sensitive lab work.

  10. Ars Technica · AI38

    Basically no one is using AI agents for their DoorDash orders

    DoorDash's Xu said third-party AI agent orders remain negligible, separate from internal tools like Ask DoorDash, which the company says builds baskets five times faster and yields orders with nearly 50% higher basket value and about 60% more unique items. He compared the current stage to Pizza Hut's tentative 1994 online ordering experiments, noting that more than half of Pizza Hut orders are now placed online. Xu said of AI agents, "you never want to fight gravity," but "you don't want to be delusional."

  11. Hacker News AI60

    Rival AI models write an encyclopedia and judge each other blind

    Scio is an encyclopedia written entirely by AI agents that search for sources, write missing articles, and check each other's work, with every sentence backed by a source, exact quote, and saved copy of the page. Submissions are machine-checked for real sources and quotes, then judged by a randomly selected jury of agents that excludes the author's model family and votes blind, with majorities of three of five or four of seven required to publish. The platform reports 18,933 published articles by day 64, compared with Wikipedia's roughly 1,772 at the same point.

  12. Hacker News AI58

    Put AI to Work for You

    IFTTT founder Linden Tibbets announced that IFTTT is adding AI, launching an AI Agent service so AI can serve as both the trigger and the action within Applets, and removing Applet and service limits on every plan including Free. The company is dismantling its paywalls in favor of a monthly credits allowance spent when Applets run, with a new $2.99 Starter plan, and ifttt.com becomes IFTTT.ai.

  13. Hugging Face Blog36

    nemotron-halloween

    The author describes MonsterHouse, a Halloween interactive projection built on the NVIDIA Nemotron Voice Agent with Nemotron Speech ASR, Nemotron 3.5 Bolt E4B 4GB, Magpie TTS Zeroshot and Audio2Face-3D, running on a single workstation with two RTX PRO Blackwell GPUs. The grumpy pirate-ship garage door listens to trick-or-treaters, replies through a LoRA-tuned Bolt E4B model, speaks in a zero-shot Magpie voice with seven moods, and animates its mouth in Unreal Engine 5 via Audio2Face-3D, with optional Nemotron 3 Nano Omni costume descriptions plus YOLO and ByteTrack visitor tracking. The MonsterHouse code is not released, but the post outlines a build path using the open models and reports median end-of-speech-to-audio of 1.70 seconds with Bolt Q4 and TTS, or 0.72 seconds for cached responses.

  14. Hacker News AI58

    Gnosh.ai – super intelligent AI that thinks, plans, recalls in Go

    Gnosh is a security-first fork of Charm's Crush coding agent that runs the Gno VM in its harness, keeping goals, findings and facts in a mem realm on your disk so new sessions resume from what is still open. It supports any hosted or local model and sends nothing home unless enabled. The post shows real runs with Qwen3 27B working out an exponential-backoff answer in Gno, planning a multi-session Median task, and recalling updated facts and reminders.

  15. Hacker News AI46

    AI review of the research of Emmanuel Saez and Gabriel Zucman

    An AI-generated audit of 138 works by Emmanuel Saez and Gabriel Zucman (2011–2026) reports 53 major defects and 94 contested modelling choices across 43 works with at least one major defect, with 72% of 5,110 reproduction checks matching the published figure. The review says no finding was severe enough to overturn a paper's core result outright, though headline magnitudes often do not survive, and that findings overwhelmingly point toward weaker claims (96% of directional defects, 98% of contested choices). It notes the audit was instructed to look for flaws and that a comparable pipeline run on free-market economists and Hoover Institution papers produced a similar tilt.

  16. TechCrunch · AI47

    Zest’s new AI agent finds restaurants and books reservations over text

    Zest, a restaurant discovery app that launched earlier this year, introduced a personal AI-powered "restaurant concierge" that operates via text messages and can check availability and book tables through services like OpenTable, Resy, and SevenRooms. Users text the concierge at (212) 470-6067, and it can be added to group chats to blend everyone's tastes, settle indecision with in-thread voting, and book a table for the group. Zest, founded in November 2024 with $1.8 million in pre-seed backing, links to users' credit cards via Plaid to track food and drink spending and tailor suggestions.

  17. The Verge · AI25

    Starbucks wants to use AI to show you a ‘personalized digital menu’ at the drive-thru

    Starbucks CEO Brian Niccol said on an earnings call that the company will explore experiences that recognize participating customers as they arrive, present personalized digital menus, and make payment more effortless. Starting in 2027, Starbucks will also begin testing background AI models at the drive-thru to help baristas input orders more accurately and efficiently, and it plans to integrate AI into the app's search and discovery features. Niccol said it's still "early" and that the company will "test, learn, and scale what works."

  18. AWS Machine Learning Blog42

    How Worldwide Express automated freight exceptions with Amazon Bedrock

    Worldwide Express, part of ShipStation Global, built a multi-agentic AI solution on Amazon Bedrock that connects to its SpeedShip transportation management system, using three specialized agents for invoice matching, pricing variances, and accessorial validation, each grounded in carrier-specific knowledge bases. Six months after launch, the company reported a 75 percent reduction in active exceptions (from $15M to $4M), a 4-week improvement in time-to-cash, $1M in annual savings, and a one-time $10M free cash flow infusion, with agents closing about 10,000 exceptions weekly at under 1 percent error rate across over 40 LTL carriers. The solution moved from assessment to production in less than 6 months and initially used human-in-the-loop approval before bulk approval became the default once accuracy exceeded 99 percent.

  19. Hacker News AI12

    Ask HN: Are you putting off hardware upgrades because of AI coding tools?

    An Ask HN post asks whether AI coding tools have led developers to delay or instead encourage hardware upgrades. The author says they still use an 8th-gen i7 with Linux for most development work, now running about 10 terminal tabs instead of IDEs, with concurrent Rust and Java builds usually not a big issue, and notes they could tell Claude to do all builds on and iterate via CI. They cite immediate feedback on interface slowness for things like FastComments as a benefit, while apps like Stripe are seriously slow in Firefox on this machine despite it running a 3D game like RDD 2 at 60fps.

  20. Hacker News AI40

    Open Rock – An open-source AI chat interface

    Open Rock is an open-source chat app that runs as a website or Tauri desktop app and connects to every AWS Bedrock chat model in your region plus your own Gemma servers over HTTPS. It offers per-model settings, file uploads, a usage page with estimated costs, and keeps Bedrock API keys and Gemma tokens in the server process rather than the browser. Setup requires Node 20 or newer, with Docker and desktop build options documented.

  21. n8n Blog30

    Throttling vs. rate limiting: Backoff strategies for workflows

    This article distinguishes rate limiting, where excess requests are rejected (often with a 429 error), from throttling, where requests are delayed or queued, and explains how rate-limit algorithms such as fixed vs. sliding windows and token vs. leaky buckets affect how workflows should pace calls. It covers using the Retry-After header, exponential backoff with a maximum delay and retry limit, adding jitter to prevent synchronized retry spikes, and checking idempotency before retrying requests with side effects. It then describes how n8n handles these patterns through batching and wait nodes, Retry On Fail with Wait Between Tries, concurrency controls, and Error Trigger workflows for persistent 429s.

  22. Factory Blog38

    Factory Acquires Typedef: Bringing Data Context to the Software Factory

    Factory announced that Typedef is joining the company to add a data context layer built from code, making relationships between data models, pipelines, and dashboards visible to Droids. The companies say this will give engineers clearer lineage and evidence as Droids plan migrations, debug pipelines, and refactor models. Typedef's founders, Yoni Michael and Kostas Pardalis, previously built Coolan (acquired by Salesforce in 2016) and Blendo, respectively.

  23. Hacker News AI22

    One Company's AI Mistake

    The author criticizes Aweber's plan to remove its traditional form builder and force users to create and edit all sign-up forms only through a conversational AI interface, arguing this is slower, less precise, cognitively taxing, and anxiety-inducing compared to the existing well-designed UI. He shares the email he sent urging Aweber to keep a non-conversational option, and frames the episode as a cautionary tale about AI over-enthusiasm, recommending strong writing skills as a way to push back.

  24. Google Developers Blog12

    DevFest is back!

    DevFest, the world's largest annual community-led event series hosted by Google Developer Groups, will run from October 1 through December 31, 2026, across 800+ events in 115 countries with almost 1 million attendees. The events focus on building, securing, and scaling in the agentic era, with sessions on Google AI technologies plus tracks for Google Cloud, Android, and Web. Attendees can find local in-person and virtual gatherings at goo.gle/devfest and share highlights using #DevFest.

  25. NVIDIA Technical Blog50

    Build Specialized Agents on a Stack You Control with NVIDIA NemoClaw

    Building an autonomous agent requires a model, a harness, and domain-specific tools. To deploy an agent more securely, developers need a runtime that enforces policies, along with optimization and observability tools for reliable execution. For production agents, the challenge lies in making these agents capable and safe to operate with access to real enterprise systems and data.

  26. Hacker News AI63

    Show HN: Opencommerce – OpenRouter for commerce, one API for AI agents to buy

    Opencommerce presents itself as "OpenRouter for commerce," offering a single endpoint for AI agents to buy from online stores, with a TypeScript SDK (@agent-cards/commerce-sdk) that provides a buyTool for agent frameworks. It claims coverage of 5,026 online stores, monitored purchase flows tested from search to checkout, purchases in under 20 seconds, and integration with existing wallets. Pricing is 1% of each completed order on the Standard plan, while Enterprise adds API access with custom fees.

  27. Hacker News AI74

    Man Hires Swarm of AI Agents to Go on Epic Hacking Spree Against Major Companies

    A Chinese-speaking cybercriminal used autonomous AI agents built on an open source tool called Cairn to attack more than 100 companies, including John Deere, SharkNinja and Cummins, according to a NorForge researcher cited by Reuters. The hacker deployed agents against over 1,200 e-commerce sites in the US, Canada, Australia and Japan, with successful breaches after about 23 hours of attack and each success costing roughly $50 in tokens. The companies said they took remediation actions or were investigating, and the researcher described the agents' techniques as sophisticated rather than "script kiddie stuff."

  28. Manus Blog58

    Rebuilding Manus with Manus: What changed, what broke, and how we work now

    Manus co-founder and CPO Tao Zhang describes how the company reorganized engineering, product and marketing around agents, arguing that AI only helped once loops closed, agents got full system context (via an internal tool called Mono), and autonomy was bounded by checkable success criteria. He reports that roughly half of PMs now ship features themselves and that engineering speed shifted the bottleneck to product decisions, while acknowledging fragmented attention, scattered information and unresolved sharing permissions.

Oct 30Fri
  1. Hacker News AI58

    Show HN: Omneum – Local, text-blind context control plane for AI agents

    Omneum is an open-source context control plane that sits between retrieval and generation, using provenance-aware graph inference to estimate source reliability and dependency-adjusted claim support, then selecting original passages under a token budget. It runs locally by default, persisting observations in SQLite or PostgreSQL, and evaluates structured observations without reading source text or calling an LLM judge. The project reports precision gains of 3.02–8.44 percentage points and 14.46–18.51% lower reconstructed-context token usage across BM25, MiniLM, BGE Reranker v2-m3, and Cohere Rerank v4.0 Pro integrations.

  2. NVIDIA Newsroom58

    Things That Go Beep in the Night: Agentic AI Joins the Search for Extraterrestrial Signals

    Breakthrough Listen and the SETI Institute are integrating agentic AI into the daily search for extraterrestrial intelligence at the Allen Telescope Array in Northern California, where agents can steer the instrument, correct incoming data and apply AI models from a single natural language request. The system uses the NVIDIA Holoscan platform, DAQIRI, CyberEther and the Nexus orchestrator to process 2.4 terabits per second on NVIDIA RTX PRO 6000 Blackwell GPUs with on-premises inference, and it has achieved the first real-time AI detection of a pulsar in the Crab Nebula. The team is next evaluating open models including NVIDIA Nemotron for data-locality-sensitive cases and observatories that may someday run offline on the far side of the moon.

  3. Cloudflare Blog36

    Cloudflare services for private origins is now generally available

    Cloudflare's services for private origins are now generally available, letting customers point a proxied A or AAAA record at a private IP so Cloudflare reaches the origin over existing Cloudflare One connectivity while WAF, caching, bot management, and Workers apply as they do for public origins. The private_routing setting enables automatically for RFC 1918, RFC 6598 CGNAT, and RFC 4193 IPv6 ranges, and no inbound firewall exception is required. Argo Smart Routing and Dedicated CDN Egress IPs are not supported, and origin health checks require Load Balancing.

  5. Hacker News AI58

    Show HN: AI agent needs process to build a commercial application

    NoMoreHappyPath is a free, open-source (Apache 2.0) delivery system for macOS and Linux that runs AI agents through 21 quality steps, with a builder, an independent reviewer from a different AI company, and a CTO, in a plain-English control room. Tests are written before code, must fail first, and are run by a board agents cannot edit, with nothing accepted until the user approves it. It runs on the user's machine with their own AI accounts, and the author cites a weather app built in 48 minutes with four reviews, one of which failed.

  6. Hacker News AI34

    Show HN: Beolis – Manage your coding AI agents

    Beolis is a tool for managing coding AI agents that run in parallel or in the background, either locally (using your current repository or git worktrees) or remotely, where it creates a git worktree and runs the agent there. Rather than chatting with the agent at each step, users define workflows with coded default steps—for example, running tests, having a cheap agent summarize failures, then a smarter agent apply fixes. Local use is free, with paid collaboration features and remote workers available.

  7. TechCrunch · AI40

    DoorDash said it’s only received ‘several hundred’ orders from AI agents

    On its third-quarter earnings call, DoorDash said it has received only "several hundred" orders from third-party AI agents such as Muse, Instinct and Fo, compared with an average of 3 million deliveries daily cited in its 2025 report. CEO Tony Xu said ordering through DoorDash's own app still dominates, while the company wants to learn about agentic use cases and build relationships with third-party agent makers, and sees a possible future opportunity to advertise within those agents. DoorDash has launched its own text-to-order agent, a CLI agent, the Ask DoorDash chatbot and an MCP for corporate ordering.

  8. Hacker News AI58

    Cisco to rewrite 98% of its legacy code using AI

    Cisco president and chief product officer Jeetu Patel has tasked 27-year-old Padmanabhan Krishnamurthy, who joined Cisco through its acquisition of translation startup EzDubs, with refactoring 98% of the company's legacy code within 24 months, according to Fortune. Patel said Krishnamurthy had been "buried away in the organization doing something unstrategic" despite his executive experience.

  9. Google DeepMind58

    Speeding up planning decisions with AI

    Google DeepMind's PlanAssist, built with Gemini, cut the time planning officers spent on householder assessment tasks by up to 58% in pilots across Barnet, Camden, and Dorset, with over 70% of its generated reports approved without edits. The tool is entering a 12-month Beta phase with live applications, onboarding 12 more councils in three cohorts for a total of 15, and subject to successful testing the government plans to make it available to all councils in England in 2027, with every assessment reviewed and approved by a qualified planning officer.

  10. Wiz Research22

    Key Takeaways: AI Threat Readiness Survey Report 2026

    A survey of 100 senior IT and security decision-makers found that 55% of organizations actively deploy autonomous agentic systems and 31% run more than 25 distinct AI systems in production, yet only 17% maintain a comprehensive AI asset inventory and 52% discovered unauthorized AI applications in their perimeters over the past year. Leaders cited governance and cross-functional ownership complexity (26%) as their top AI security bottleneck, while defensive spending remains fragmented, with 43% stretching legacy cloud tools, 38% funding dedicated AI security budgets, and 37% relying on homegrown scripts. The report outlines a five-priority AI Threat Readiness Framework spanning production-grade controls for AI stacks, graph-based asset context, behavioral least privilege, AI-driven exposure scanning, and code-to-cloud response.

  11. Hacker News AI58

    Show HN: Navital Gym – open environments for testing AI agents on Indian tasks

    Navital Labs released Navital Gym, a public, actively developed suite of six sandboxed, deterministically auto-graded environments (trip planning, GST invoicing, forms, multi-document forms, Hindi/Hinglish customer support, and UPI) for testing AI agents on Indian-reality tasks without an LLM judge. It runs on plain Python 3.10+ with optional adapters for Inspect AI, verifiers and OpenEnv, and publishes pass@1 and partial-credit results for small, mid-size and larger models. The environments use simplified, documented rules and synthetic data and are not affiliated with NPCI, RBI, GSTN/CBIC, IRCTC or any government body.

  12. Sierra Blog58

    Our customers’ ambition is accelerating our growth

    Sierra announced it has surpassed $400M in ARR, adding over $150M in Q3 alone, and says growth is accelerating, taking five months to double from $200M to $400M after six months to double from $100M to $200M. The company attributes this to customers' growing ambition, agents handling longer interactions that drive revenue, and faster agent building with Ghostwriter, citing a large US retailer that went from first meeting to live agent in 27 days. Sierra says it now works with almost 50% of the Fortune 50 and is developing an open standard called Poppy with over 50 enterprises including Meta, Shopify, Stripe, and Walmart.