iCreatAI News
Back to main site
Skip to content
#Agent
Oct 28Wed
  1. Latent Space58

    How Anthropic ships Claude with Claude: Separating the Brain from the Hands

    This episode interviews Katelyn Lesse and Angela Jiang, Anthropic's heads of Engineering and Product, about the Opus 5.5 launch, covering pricing and intelligence-per-dollar tradeoffs, efforts to make the API harder to distill (including preserving thinking blocks across turns), and the Managed Agents architecture that separates the session log and harness from the sandbox executing code. The guests explain that this separation keeps credentials out of sandboxes and lets the harness persist when an execution environment fails, and they describe "dreaming" as one agent inspecting another agent's prior work and writing memories back. They also discuss evaluation work, safety attention as launches have become harder, and keeping the base harness simple while developers experiment with verifiers and parallel agents on top.

  2. AWS Machine Learning Blog18

    AWS named a Leader in the 2026 Gartner Magic Quadrant for Contact Center as a Service

    AWS announced that Amazon Connect was named a Leader in the 2026 Gartner Magic Quadrant for Contact Center as a Service (CCaaS) for the fourth consecutive year. The post describes Connect Customer as combining customer context, generative and agentic AI, and auditable actions with human handoffs, and contrasts its focus on full resolution with industry emphasis on deflection. Gartner's Magic Quadrant for CCaaS was published 19 October 2026 by Drew Kraus et al.

  3. Google Developers Blog34

    Building Conversational Commerce with Multi-Agent Swarms on GCP: A Working Prototype

    The post presents HappyDelivery, a working prototype of the previously described three-layer conversational commerce architecture built with LangGraph, Gemini, FastAPI, and Google Cloud. It details an omni-channel ingress service that verifies platform-specific signatures and normalizes payloads before queuing them to Pub/Sub, a Redis session and cart layer, and a LangGraph agent swarm with supervisor, profile, inventory, and transaction specialists using deterministic pricing tools. Live benchmarks and a three-turn simulated shopping flow, plus a five-test automated suite, are reported as verification.

  4. Pragmatic Engineer58

    AI SRE: what is it, how could it change on-call – and does it work?

    This Pragmatic Engineer article examines the rise of "AI SRE" incident tooling, driven by rising deploy frequency and pager volume, drawing on interviews with Rootly, incident.io and ResolveAI. It describes how these agents mostly speed up incident investigation inside Slack using context layers, knowledge graphs and memory, while whether they should make code changes remains debated. It also covers accuracy tactics like adversarial verifier agents and backtesting, latency/cost tradeoffs, in-house builds at OpenAI, Stripe, Google and Monzo, and the limits of fully autonomous remediation.

  6. Hacker News AI34

    Who needs AI psychosis? I gave myself VR psychosis

    The author describes building and auto-deploying web-based VR games by voice-prompting coding agents from the pub, using tools like Wispr Flow, Claude's /remote-control, Git, Vercel and Cloudflare, with games playable via Three.js and WebXR on a Quest 2. He walks through several prototypes, especially Star Crusader, and argues that iterating on primary gameplay loops is the fastest way to develop taste. He also recounts a scaled-back drawing-and-deploying game activity with his daughter.

  7. Hacker News AI60

    Show HN: AgenticBench, 9 security tests run on 25 AI coding agents

    AgenticBench publishes a security leaderboard running 9 defined tests on 25 AI coding agent harnesses, each in a fresh container with the harness's default settings, scoring results as pass, fail, missing control (MC) or N/A, with N/A and MC never counted as passes. Results include Codex 0.163.0 at 10/11, GitHub Copilot CLI 1.0.103 at 25/11 and Cline 3.0.73 at 11/11, while Auggie 0.36.0 scored 5/11; failures are disclosed privately to makers first, with 14 disclosures raised so far (6 published, 8 held). The board states it is not a penetration test or certification and measures nine tests using planted, fake secrets, with full materials available to tested harness makers under an NDA.

  9. Hacker News AI47

    Show HN: Search2o Simplifies AI Agents

    Search2o is an agent server that handles the infrastructure behind building, discovering and running AI agents, letting developers focus on business logic. Agents are described in English, discovered via search requests, and can build on each other within a conversation, with managed state, encrypted conversations and memories, multi-user roles, and stateless horizontally scalable servers. It offers integration via Python expressions, a REST API, and hooks, and its agent server and UI are source available.

  10. Hacker News AI58

    I benchmarked 4 web search APIs for AI agents on 30 live queries

    Pallavi Singla benchmarked You.com, Tavily, Exa and Parallel on 30 agent-style queries across GTM, insurance and finance, with 3 runs per query (90 calls per API), and published the results, harness and data. Parallel led accuracy (67%) with You.com close behind (63%) and tied on fully correct queries, while You.com was fastest (593 ms p50) and freshest (4.1 h median newest relevant result) and never returned empty. The final run was Oct 8, 2026, and the author notes 10 queries per use case is a focused test rather than a leaderboard.

  11. Hacker News AI58

    Show HN: Make your AI agent think before it codes

    SpecOps is an open-source tool that adds a structured four-phase workflow to AI coding assistants: understanding the codebase, writing requirements and design, implementing ordered tasks from the spec, and verifying acceptance criteria. It works with Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Google Antigravity, storing git-tracked markdown specs, and adds features like EARS-notation requirements, drift checks, dependency gates, adversarial evaluation, and a production learnings layer.

  12. The Decoder71

    Google Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs

    Google Deepmind introduced Genie 4, a real-time world model that renders scenes frame by frame in response to keyboard and text-prompt input, generates its own background audio, and simulates talking characters. Gemini models plan the simulation in the background to keep it coherent, with Gemini 3.8 Flash checking multistep goals and Gemini 4 Argon tested in a demo where Genie 4 simulates Apptronik's Apollo robot playing checkers. Deepmind calls Genie 4 an early experimental model that stays consistent over short sessions but can drift in longer ones; it is available to select testers as a research preview, with SynthID watermarking on all output.

  13. AWS Machine Learning Blog50

    Exowatt beats frontier models on accuracy with SageMaker serverless model customization

    Exowatt used Amazon SageMaker AI serverless model customization to fine-tune Qwen3-1.7B for edge alarm triage (0.911 macro-F1 vs 0.698 for Claude Sonnet 4.6) and Qwen3-14B for cloud energy-market analysis (0.975 macro-F1 vs 0.625 for Claude Opus 4.7, at about 49× lower cost per 1,000 answers). The pipeline spans seven AWS serverless services, with the edge model quantized to GGUF and run offline via llama.cpp on existing CPUs, and the cloud model served through Amazon Bedrock Custom Model Import. Exowatt moved from experimentation to production in nine days and plans to reuse the pipeline across fleet tasks.

  15. The Verge · AI40

    Firefox’s Smart Window adds AI form filling and webpage monitoring

    Mozilla is updating Firefox's AI-powered Smart Window with a feature that fills online forms using information from your open tabs, such as an online portfolio or LinkedIn page, and shares source-page data with Google's Gemini 3.1 Flash Lite. Users can also type "/watch" in the Smart Window chat to have Firefox check specified webpages daily or weekly for sales, job listings and other updates, notifying them when a change is detected. Both features are rolling out to the Smart Window beta on desktop in the US and Canada, with other countries to follow in the "coming months."

  16. Google DeepMind82

    Genie 4: A new generation of world simulation

    Google announced Genie 4, a natively multimodal world model that generates photorealistic, real-time interactive simulations with native audio, including ambient sound and interactive dialogue, and builds on Gemini models for reasoning and coherence. It is rolling out as a research preview to trusted testers, with plans to reach Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and Google AI Studio. Google notes limitations such as drift in visual details and object permanence over longer sessions, and says all generated video and audio include SynthID watermarking.

    Why it matters: Useful for readers tracking frontier world models, as it details Genie 4's capabilities, staged rollout, and acknowledged limitations.

  17. Google Developers Blog67

    Fast, reliable A2UI, with swappable inference formats

    A2UI now supports swappable inference formats, with A2UI Express as the new default that requires up to 3x fewer tokens than Direct JSON and can cut latency by up to 3x, while decision models like Jev can reduce latency by up to 80x for layouts defined in advance. Express is available in the Python agent SDK (a2ui-agent-sdk 0.9.0), the TypeScript agent SDK (@a2ui/agent) and the Dart SDK (a2ui_agent 0.0.1-wip004), and the SDK compiles the model's reply into validated A2UI messages. The post also describes the Apparite (jev2ui) example, where Jev answers layout questions and code builds the component tree, with screens complete in 0.8 to 1.7 s across 11 prompts in a small first-look sample.

    Why it matters: It gives concrete latency and token figures plus working SDK versions for teams weighing Express against decision-model-driven layouts.

  18. Replit Blog72

    Anyone can now bring their ideas into the company codebase

    Replit launched Cloud Agents for existing repositories, letting anyone on a team describe a change in plain language and have an agent find the code, test it in cloud sandboxes, and open a tested pull request in GitHub or GitLab with screenshots and video. The feature includes shared environments set up once by an admin, review feedback that agents turn into proposed team skills for engineer approval, and a Slack integration for starting changes from threads; it is available to all Pro and Enterprise customers.

    Why it matters: Announces a notable shift in how non-engineers can contribute tested code changes to production repositories, with concrete details on testing, review, and setup.

  19. Meta Engineering38

    PrivacyLib: Privacy Controls at the Data Access Boundary

    Meta details PrivacyLib, a common library embedded in the clients of hundreds of its data and processing systems that enforces privacy requirements at the point of data access, performing billions of checks per second. Systems integrate once and new requirements arrive as plug-in modules, with changes simulated before release and rolled out per module; for internal AI agents, tool calls carry agent context to PrivacyLib so modules can observe data use and block disallowed operations.

  20. Hacker News AI22

    Show HN: EveryGen AI – AI images, short videos and copy rewrites in one tab

    EveryGen AI is a browser-based tool that combines image generation (defaulting to GPT Image 2), video generation (defaulting to MiniMax H3 Max Turbo), browser image utilities, and a Gemini 2.5 Flash text-rewriting tool called Humanize AI. It offers annual credit plans from Lite ($179/year for 7,200 credits) to Max ($1,199/year for 96,000 credits), and states it is an independent tool, not an official MiniMax or fal website.

  21. Hacker News AI36

    Show HN: Agent Referee – signed, checkable reviews and tie-breaks for AI agents

    Agent Referee is a paid HTTP service that lets AI agents from different owners settle tie-breaks (weighted coin flip, draw, rock-paper-scissors) or have a single agent's output checked by independent AI reviewers, returning Ed25519-signed receipts each side can verify. It charges per match or per review in USDC on Base via x402 with no accounts or API keys, and offers judge tiers using panels of models from Anthropic, Google and OpenAI. The author reports 300+ self-play paid matches and 18 paid reviews on Base mainnet, and notes the service is run by one person, that AI verdicts can be wrong, and that some guarantees (accepted-but-unrecorded requests, step ordering) still depend on trusting the operator.

  22. Hacker News AI71

    AI review optimized for recall (catches more defects than Codex or Claude)

    QuickReview is a self-hosted GitHub PR reviewer that fans each change out to many narrow, read-only lens passes, merges duplicate findings, and re-validates every candidate against the code before posting one review. On 185 real PRs with 520 verified defects it finds 97% of high-severity, 93% of medium and 84% of low defects, versus 90%, 82% and 52% for the best of six other reviewers, at about $2 and 17.5 minutes per PR. It is in beta, runs as a deterministic TypeScript daemon with no LLM in its decision path, and ships with dry_run = true so a fresh install posts nothing.

  23. Hacker News AI23

    Leaf PHP: looking back at 740k installs and our crazy AI plan

    Leaf PHP's packages have passed 740,000 combined installs on Packagist since the framework's first release in October 2019. The author traces major turning points to v3, which introduced modules, and v5, an AI-native rebuild with a new route parser, AI-readable docs and a .leaf/CONTEXT.md file, noting installs have roughly doubled since v5 shipped in August. He also says Leaf MVC's share of installs fell from about one in two at the start of 2025 to about one in three today as more projects are started by agents.

  24. Hacker News AI38

    Kechup – a simple CLI task tracker for AI agents

    Kechup is a command-line task tracker for a single project folder that stores tasks, claims, notes and history in the project folder and in git so a new agent session can read what the last session did. It requires only Python 3.12+ and git (Linux or macOS, not Windows), commits every write with the agent ID as author, and closes a task only when its REPORT.md is committed and clean. It also detects plain git reverts of accepted work, marking the task as reverted and re-blocking dependent tasks.

  25. Hacker News AI60

    Show HN: Snippet – An Always-On AI Agent

    Snippet is a code-first terminal agent distributed as a single Rust binary that provides a terminal UI plus a serve daemon for remote control from Android, macOS, Linux and Windows apps. It offers durable sessions with checkpoints, rewind and searchable compacted history, per-repository markdown memory shared across worktrees, a small tool set, and configurable model profiles including Anthropic, OpenAI, Gemini, OpenRouter, OpenAI-compatible endpoints and local models. Remote access requires a token and works with user-set-up tunnels such as Tailscale or Cloudflare, and the project is licensed under AGPL-3.0-or-later.

  26. Hacker News AI58

    Show HN: Sectr – Serverless backend platform for easy deployment of AI agents

    Sectr is a serverless backend platform that lets you register agents built with any framework and deploy them to the cloud with one command, exposing each as an AG-UI endpoint for CopilotKit frontends. It offers local development via `sectr dev`, serverless human-in-the-loop approvals that suspend and scale to zero while waiting, and persisted streaming with a session journal and dashboard replay. Sectr is free during beta and supports sign-up with GitHub, Google, Vercel or email.

  27. Hacker News AI36

    Show HN: ChemX – Architectural AST linter for LLM context bloat, AI slop

    ChemX is a CLI and MCP gateway that runs AST audits, TypeScript typechecks, and tests, claiming to compress roughly 17,000 tokens of raw command output into about 45 tokens by exiting silently on success and surfacing diagnostics only on failure. It also offers a SQLite WAL symbol index for sub-100ms symbol lookups, AI-slop detection for chat residue and truncation placeholders, and file leases for multi-agent concurrency. A free `npx chemx audit` is available, with paid licenses ($27 solo, $97 team) and advisory sessions.

  28. Hacker News AI40

    AI Slop, Vibe-Coded Clones and Indie Plugins

    A nearly 25-year-old music software company describes four AI-driven pressures: near-identical clones of its AD-202 released within two weeks (one reportedly modeled from its web demo code), 10–20 AI-generated "collaboration" requests per day that have led it to stop reading them, and large tech firms devoting product cycles to replacing plugin businesses. The author argues the company's value lies in deep DAW and music-making expertise and a long-term relationship with customers, and urges buyers to be skeptical of new companies that suddenly offer six products.

  29. Hacker News AI33

    Feynman's wobbling plate and Threshold Concepts behind modern AI

    Luis, who has studied AI for about 10 years, argues that curiosity-driven play at the edge of one's knowledge, as with Feynman's wobbling plate, is the engine of real learning, and outlines eight "threshold concepts" that explain modern AI: learning from data, representations and embeddings, next-token prediction, attention, evals, post-training and RL fine-tuning, harnesses and agents, and recursive self-improvement. He cites Vygotsky's zone of proximal development, Meyer and Land's threshold concepts, and Bruner's spiral learning, and includes a study prompt usable with any LLM. The post ends with a paragraph promoting his AI coach, Zairai.

  30. Hacker News AI58

    Can You Make a 3D Game with AI, If You Don't Know How to Do Anything?

    The author describes building a browser-based 3D game intro inspired by Mass Effect using mostly free tools plus Codex from a $20 ChatGPT subscription, spending about $15 and roughly 10 days. The workflow combined ChatGPT for prompts and character images, Hunyuan3D for models, Mixamo for animation, and Freesound for audio, with the author rewriting dialogues and fixing bugs himself. He concludes that AI now lets beginners experiment with game development without deep technical knowledge.

  31. Hacker News AI38

    The Duality of the AI Build-Out

    Tech companies are simultaneously embedding specialized AI agents into their own products and building MCP plugins so those products work inside general-purpose chat apps like ChatGPT and Claude, since no one knows which paradigm will win. The post weighs specialized agents (better task performance, UI control, but users bear inference costs and context fragments across products) against MCP plugins (no inference cost, access to a large installed base, but less control and a separate experience). It notes OpenAI's "Sign in with ChatGPT" hybrid as potentially the most user-friendly model if broadly available, and flags local-first on-device inference via something like the Prompt API as a possible long-term winner.

  32. Hacker News AI58

    Show HN: Snippet – An Always-On AI Agent

    Snippet is a coding agent team that runs on your own computer and can be prompted from a phone, desktop, or terminal, with a Mission Control layer that assigns work to agents, checks results, and returns finished changes. It runs on the model you already pay for, moving background work to the next model when one hits its limit, and each agent has its own memory stored as plain files in your repo. It supports scheduled jobs, quiet hours, and sessions shared between the terminal app and phone, and installs via a curl script from snippet.wacht.dev.

  33. Amp Chronicle42

    Amp on Android

    Amp now has an Android app, available for download and install from ampcode.com/app or via a QR code. The post shows the Amp design talk thread, the slide deck in the Portals tab, and the present.js diff in the Changes tab, all within the Android app.

Oct 27Tue
  1. TechCrunch · AI38

    Meta AI director Rohit Patel leaves to take on Microsoft Office and Google Workspace

    TechCrunch reports that Rohit Patel, a former director at Meta Superintelligence Labs, has left Meta after eight years to launch Ndoc, an AI-native workspace pitched as a replacement for Microsoft Office and Google Workspace. Ndoc combines a Stage tab for presentations and dashboards, a Narrative tab for analyses and citations, and a Model tab housing datasets and Python scripts, and is built on a mixture of open source models. Patel plans to open-source the ".ndoc.html" export format, and Ndoc is now running an enterprise pilot with a limited alpha and a beta planned for the coming weeks.

  2. Latent Space38

    Coding From the Himalayas With an Offline AI Agent

    A Thomson Reuters principal engineer describes running the OpenCode coding agent with Ollama and Qwen3.5 9B entirely on a laptop, then disconnecting the internet to fix a bug in an expense calculator and run its tests. The article covers model size and memory considerations, published benchmark scores, setup steps, and the limits of what can be done offline.

  3. NVIDIA Blog38

    How AI Is Changing the Pace of Discovery for Millions Living With Dementia

    C-BRAIN, a consortium of 18 institutions led by Dr. Randall Bateman and working with NVIDIA, launched in November 2025 to use AI to speed Alzheimer's research by drawing on previously inaccessible "dark data" through a hybrid centralized and federated approach. Its two tools, OpenScientist and InsightEngine, have completed analyses in minutes that scientists estimated would take weeks to months, at under $10 per run. The consortium aims to build a multimodal biological foundation model and, by year three, discover new causal mechanisms of brain aging and Alzheimer's disease.

  4. The Verge · AI62

    Apple is adding an AI chatbot to Pages, Keynote, and Numbers

    Apple is bringing an AI assistant built on Apple and OpenAI models to Keynote, Pages, and Numbers, where it can design and animate slides, draft and restructure text, and calculate and visualize data. The apps now support the Model Context Protocol on macOS 27 or later for third-party AI agents, and the assistant is rolling out in beta to devices compatible with Apple Intelligence running iOS 27, iPadOS 27, or macOS 27 or later. Other updates include Generate Fill in Pixelmator Pro, a Liquid Glass redesign and AI assistant for Logic Pro, and MotionVFX templates plus a Content Hub in Final Cut Pro, available free to existing Creator's Studio subscribers in November.

  5. Hacker News AI50

    A Salesforce AI agent that can't publish a hallucination

    Deal Rescue is an LLM agent that gathers a stalled Salesforce opportunity's CRM record, web signals and latest meeting transcript, then has Claude draft a scored timeline, deal read and email. A deterministic grounding gate re-checks every date, amount, contact and citation against what was fetched, rejecting invented output with reasons, retrying at most twice, and failing closed by publishing nothing. The deal score is a deterministic rubric that Claude may adjust by ±15 only with a cited signal, and no email is ever sent from the codebase—publishing writes a draft with an approval flag for a human to approve in Salesforce.

  6. Hacker News AI58

    Show HN: AGBoss Dependency injection and static validation for AI agents

    AGBoss is an open-source TypeScript framework built on LangGraph that provides strictly typed decorator components for agents, actions, routers, tools, MCP servers, A2A services and knowledge bases, assembled in an @Application container with constructor dependency injection and compile-time Path Scope verification via `agboss check`. Version 0.1.0 publishes @agboss/core (production runtime) and @agboss/cli (static workflow compiler and code generator) on npm, with features including action compensation with LIFO rollback, human-in-the-loop pauses, FinOps budgets, PII masking, SQLite WAL leases, signed Agent Mesh envelopes and a five-loop evaluation pipeline. Projects are scaffolded with `agboss create`, which also writes AGENTS.md, CLAUDE.md and version-matched skills for AI coding agents.

  7. Hacker News AI60

    Show HN: Hashling, an open-source Mac security agent your own AI can talk to

    Hashling is a free, MIT-licensed macOS security agent for Apple silicon Macs running macOS 14 or newer that monitors internet connections, AI coding agents, malware, startup items, privacy permissions, trackers, downloads, uploads, data breaches, texts, ransomware and Mac settings. It can be connected to Claude Code, Cursor, Codex or any MCP client so an AI agent can query its findings and propose fixes, but every change requires Touch ID approval. It runs locally, requires no account, and offers an optional fully local AI model so questions never leave the Mac.