iCreatAI News
Back to main site
Skip to content
#Agent
Nov 11Wed
  1. Hugging Face Blog55

    BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model

    Tether AI Research introduces BotPsy, a 0.8B-parameter model built on Qwen3.5-0.8B for function calling and agentic workflows, suitable for on-device deployment. It roughly doubles its base model's tool-use scores (BFCL v4 23.4 to 44.0, ACEBench 30.1 to 58.7, τ-bench 23.2 to 51.5) and outperforms every model up to 1.2B parameters tested on all six agentic benchmarks, while also beating Qwen3.5-2B-Think on five of the six. It will be released with open weights under Apache 2.0 in bf16, Q8 and Q4 as safetensors and GGUF files, and is intended for low- to medium-difficulty tasks, not high-stakes use.

  2. Hacker News AI42

    The Unexpected AI Stack: C# + .NET

    This post argues that C# and .NET are underrated foundations for agentic software development, citing build- and run-time type checks, Roslyn analyzers and source generators, EF Core schema checks, and a mature toolchain as guardrails for agent-written code. It highlights Aspire as a programmable runtime orchestration layer with isolated networking for worktrees and a queryable OpenTelemetry sink, and CSharpRepl as a way for agents to connect to a running application and wrap or replace functions at runtime. The piece is Part 1 of a five-part series and links the full repo at https://github.com/zeeq-ai/zeeq-tmpl.

  3. Hacker News AI20

    Controlling your AI agents from a game handheld

    The author describes using a Retroid Pocket 5 Android gaming handheld, paired with a portable OLED screen, power bank and foldable keyboard, to control personal AI agents on a mini PC during business trips. Software includes Termius, Tailscale, pi/opencode, herdr for multiplexing, and a web-based VS Code server for editing files and viewing diffs. The setup has so far been used in hotels and airports, and the author notes most Android terminal apps also support Mosh.

  4. NVIDIA Newsroom22

    How AI Helps Recyclers Turn Mixed Waste Into Reusable Material

    NVIDIA describes how four Inception startups apply AI and robotics to waste sorting: AIRECO uses vision AI and Jetson Orin NX modules to finely sort plastics, EverestLabs AI deploys computer vision-guided robots on recycling lines, Greyparrot's Analyzer platform identifies objects on conveyor belts, and reverse.fashion automates textile sorting with high-resolution computer vision. The article cites figures including less than 7% of materials entering the economy coming from recycled or reused sources and over 2 billion tons of municipal solid waste generated per year. It also notes company-reported results such as AIRECO's 95% recognition accuracy on its test line and EverestLabs' estimate of about 25,000 tons of material recycled.

  5. Hacker News AI63

    Show HN: A company running in an AI harness

    The author presents Restless, a system for running a small "company" of AI agents inside a persistent Linux machine, where human users set direction and agents handle routine work such as research, builds, QA and scheduling. The post walks through an illustrative day at a fictional game studio, describing roles for people and agents, approval gates for external actions, model choice per agent, and pricing tiers. It also cites FrankenSurf, an open-source project with 100 GitHub stars, as a real example of a Restless company writing its code, shipping releases and marketing it.

  6. AWS Machine Learning Blog58

    Introducing Kimi K3.1 Pro on Amazon Bedrock

    Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock, described as a post-trained version of Kimi K3 with the same 3T-class open-weight architecture and 1-million-token context window, trained with more post-training compute for long-horizon agentic work and fewer factual errors. It generates output tokens at a higher rate, with Moonshot AI reporting 2–3 times the speed of Kimi K3.1 Pro, and uses the same endpoint, APIs, and features as Kimi K3, so existing code can switch by changing the model ID. The post covers getting started via the Chat Completions, Responses, and Converse APIs, lowering costs with the Flex tier, explicit prompt caching, and using the model in OpenCode.

  7. Hacker News AI38

    AI proved your code correct. What did it actually prove?

    Keller AI explains how formal verification works, using a sorting example and Euclid's equilateral-triangle construction to show how proofs combine definitions, assumptions and prior results, then applies the approach to a document-download authorization handler. The article stresses that a checked proof only establishes a result within a mathematical model, so its value depends on whether the model's assumptions match reality and whether the specification captures the intended requirement, citing a revocation-versus-session example and timing side channels. It also reports an unreproduced synthetic experiment in which the best of seven automated reviewer setups approved 1 of 88 sealed rule-breaking changes.

  8. AWS Machine Learning Blog40

    Build a daily dependency watcher with LangGraph and Amazon Bedrock AgentCore web search

    The Web Search API in Amazon Bedrock AgentCore is now available, returning current web results with title, URL, publication date and query-relevant extract, signed with existing AWS credentials and served from an Amazon-operated index. The post walks through building a LangGraph dependency watch that researches npm, PyPI and container base images in parallel, keeping the date window, domain blocklist and search budget in code and checking each finding against its cited sources. In the test run, three branches made 12 searches and finished in 36 seconds versus 99 seconds sequentially, and the watch can be hosted on AgentCore runtime or offered through AgentCore Gateway.

  9. Microsoft Research78

    Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents

    Microsoft researchers describe "Lazarus," a backdoor technique that reprograms fewer than 10 dormant neurons in an LLM, without training, so an agent built on it behaves normally and passes standard evals until a trigger—such as a date change—causes it to download and run attacker code with whatever access it has. The attack needs only write access to a checkpoint, so internally developed models are equally exposed, and reliable detection requires diffing against original weights, making provenance and weight integrity critical. Microsoft Foundry ties open-weight models to their publishers and scans surrounding containers, and Microsoft is developing AI-powered weight scanning, a red-teaming harness, and cryptographic model signing.

    Why it matters: It offers a concrete, researcher-first account of a low-cost weight-space backdoor and the provenance and weight-auditing practices it implies for anyone deploying agents.

  10. Cursor Blog71

    Cursor Projects is now multiplayer

    Cursor announced that Projects, its multi-agent workspace introduced in September, now supports multiplayer so teammates can plan, build and ship together alongside their agents. Projects adds a shared context system holding requirements docs, diagrams, tech specs and mockups, plus a shared task board showing who and which agents are working on what and the PR behind each task. The feature also enables agent-to-agent communication across teammates, and is rolling out in beta to all Cursor users starting today.

    Why it matters: Useful for teams evaluating collaborative AI coding tools, as it describes a shared-context multi-agent workspace and its beta availability.

  11. AWS Machine Learning Blog40

    The agent evaluation playbook: Built-in, DeepEval, and AutoEval on Amazon Bedrock AgentCore Evaluations

    This AWS post explains how to evaluate production agents on Amazon Bedrock AgentCore by starting from business outcomes, breaking them into observable behaviors, and mapping each to a trace- or session-level evaluator. It covers the built-in AWS evaluators, managed third-party metrics from DeepEval and AutoEval, custom and multi-dimension LLM-as-a-judge evaluators, and suggested evaluator stacks for customer support, research, and domain-content agents. It also describes three evaluation modes—on-demand, online, and batch—that share the same evaluator IDs, plus the ListEvaluators API for retrieving the full catalog.

  12. Pydantic AI Articles60

    Code mode is not a sandbox

    This post distinguishes code mode, where the model writes a short Python program calling your tools as functions via a single run_code tool, from a sandbox, which is an isolated environment where code runs. It describes three places a sandbox boundary can go (the whole agent, only the tools, or only the model-written code) and how Pydantic AI workspaces let you move that boundary without rewriting tools. It also covers Monty, a Rust-written Python interpreter that runs run_code next to the agent with no filesystem, network, or environment variables.

    Why it matters: Useful for teams deciding where to place isolation boundaries when combining code mode with sandboxed tool execution.

  13. Hacker News AI60

    AgentGuard – Transaction guardrails for AI agents that hold wallets

    AgentGuard is an open-source (Apache 2.0) transaction guardrail layer for AI agents holding crypto wallets: before signing or broadcasting, an agent submits the proposed transaction to AgentGuard, which simulates it against live chain state, evaluates the effects against an operator-defined policy, and returns allow, block or escalate with an explanation, a 0–100 risk score and an immutable audit record. It supports EVM chains and Solana, decodes common drain vectors (unlimited approvals, setApprovalForAll, permits, zero-minimum-output swaps, SetAuthority, never-seen contracts), and ships a conservative default policy plus a TypeScript SDK that wraps any signer so signTransaction/sendTransaction are checked transparently. An optional separately licensed @agentguard/behavior package adds per-agent behavioral anomaly scoring, and both it and the reputation layer fail closed on outages or unreadable profiles.

  14. Ars Technica · AI78

    Grok Build coding agent leaks oodles of confidential info, some belonging to SpaceXSI

    Research from security firm Claroc shows that Grok Build, the vibe-coding agent from SpaceXSI, exposes proprietary business information and other sensitive secrets from thousands of users through shareable app links, because a design decision lets anyone enumerate live projects despite randomized URLs. The exposed data includes internal business plans, ad proposals, medical exam results, cruise-line galley checklists, and employee names and ID numbers, with some coming from two-dozen apps built by SpaceXSI itself, including a confidential onboarding plan, a sales territory map of 594 accounts, and internal system addresses.

    Why it matters: It documents a concrete URL-enumeration flaw in a widely used coding agent and shows the leak reaching the vendor's own confidential material.

  15. Hacker News AI48

    Show HN: AI agents that barter your stuff for things you want

    This Show HN post introduces a service where users list items they no longer want and instruct an AI agent, via a "mandate" with categories, trade radius and credit limits, to negotiate with other people's agents for desired items. Deals return for user approval unless auto-accept is enabled, credits (one cent each) are held until handoff is confirmed, and agents can arrange multi-party trades. The free plan allows up to 3 trips a day and 20 negotiations a month, with paid plans starting at $8 a month.

  16. Hacker News AI58

    Show HN: CodeLens AI-Augmented Code Review Tool

    CodeLens is a code review tool that turns a pull request or local branch into a guided review: a brief of what changed and why, a queue of changes ordered by risk, and per-change context including callers, entry points, and external effects. It parses 15 languages with Tree-sitter (with TypeScript compiler type info for TS/JS), supports Claude, any OpenAI-compatible API, or local Ollama models, and caches results by content hash in SQLite or Postgres. It also offers codebase exploration, GitHub PR review with inline comments, a GitHub Action, and a heuristic offline mode; it requires Node.js 22.13+ and git and is Apache-2.0 licensed.

  17. Hacker News AI58

    An AI agent said the code was verified. The evidence said otherwise

    A blog post argues that when an AI agent implements, tests, reviews and reports on its own code, its claim of "verified" is untrustworthy, and proposes binding evidence (review, tests, human approval) to a specific Git tree hash so that changing the tree invalidates the evidence. It introduces Uncle (github.com/unclehq/uncle), an open-source tool that runs checks itself, records exit codes and tree identities, and distinguishes "verified," "signed" and "human looked at it" rather than blurring them. The author notes the tool does not establish correctness, is young, and is partly defeated by a hostile agent with unsandboxed shell access.

  18. Hacker News AI58

    My AI Agents Found an Unmapped Maya Site in Mexico

    The author describes using AI agents to analyze NASA lidar data covering about 1,200 km² of jungle, where the agents flagged structures including a hilltop site with a plaza, an oval pyramid at least 8–12 m tall, a raised courtyard and a possible water reservoir. After checking the literature and archives, the author sent a report to Mexico's INAH, which replied that no registered archaeological site was identified at the location. The author, who states he is not an archaeologist, offers to help with an INAH-led field check and notes the site's identification remains unofficial.

  19. Hacker News AI58

    Show HN: Aisync, advisory file claims so two AI agents don't edit one repo

    aisync is a local hub (~/.ai-sync/, a git repo) that lets Claude Code, Codex and Cursor share rules, a hash-chained journal and file claims, with an overlapping claim exiting with code 3 so an agent stops before colliding. Hooks inject what other tools just did into running sessions, and version 0.2.0 adds layered When/Do/Not rules, a progress_file for stable prompt caching, and an optional MCP server. It requires Python 3.11+ and git on macOS or Linux, uses only the standard library, and is MIT licensed.

  20. n8n Blog15

    Microservices best practices every automation engineer should know

    This article outlines microservices best practices, including defining clear service boundaries via domain-driven design and the single responsibility principle, and building resilience into service-to-service calls with circuit breakers, retries with exponential backoff, and bulkheads. It also covers routing traffic through an API gateway and making failures observable with distributed tracing and centralized logging, noting how n8n workflows can orchestrate and monitor service calls.

  21. Hacker News AI48

    Tim O'Reilly – The New Knowledge Artifacts of the AI Economy

    Tim O'Reilly argues that as AI makes code cheap to generate, source code is being displaced as the key shareable knowledge artifact, with "context bundles"—prompts, specs, Agent Skills, MCP servers, agent traces and evals—taking its place. Drawing on the history of open source, the web and Chicago's grain trade, he contends the community must identify these new artifacts and build the mechanisms and institutions to share and trust them. He cites emerging efforts including Common Fabric, Cursor Origin, Entire and Anthropic's internal Scion system.

  22. The Decoder70

    OpenAI turns ChatGPT into a business directory with AI agents that handle customer questions

    OpenAI is launching a beta feature called "Businesses in ChatGPT" that lets companies register and manage business profiles through a Business Hub, update information, add product feeds with prices and availability, and track mentions and website clicks. Eligible US e-commerce and online service providers can create "Business Agents" that answer customer questions, help with product comparisons, and serve as targets for ChatGPT ads, and Shopify merchants can connect their store directly. OpenAI says user conversations aren't shared with businesses and that ChatGPT reaches 1.2 billion users per week, with plans to expand to more markets and industries over time.

  23. Latent Space50

    Designing for Agents — Zeno Rocha, Resend

    This podcast episode features Resend co-founder and CEO Zeno Rocha discussing Agent Experience Optimization, including an AEO study in which Claude Code picked Resend first in 64 of 102 email recommendations, and how React Email templates and a pricing page readable via a .md URL helped Resend reach developers before models. Rocha describes growing Resend's MCP server from roughly 20 tools at launch to more than 80, weighing that against Cloudflare's two-tool Code Mode server, and explains why Resend introduced custom tracking domains to keep one customer's blocklisting from affecting others. He says Resend had 4.3 million users and 120,000 paying customers at recording time.

  25. Mastra Blog31

    $25 Starter Plan on Mastra Platform

    Mastra introduced a $25 Starter plan that raises monthly allowances for compute, data, and observability events and includes one Small dedicated server whose compute is covered by the $25, with usage beyond the allowances billed on top. Compute measurement is changing and allowances are being updated on every plan, while a serverless agent remains free to run on all plans including Free. Projects run serverless or on Small, Medium, or Large servers, and Mastra Connect now has a connection allowance on each plan (5 on Free, 10 on Starter, 50 on Team, $0.50 each additional) with egress from those connections counting toward plan egress usage.

  26. Hacker News AI58

    Show HN: Zeus – Claude Code for AI voice agents

    ThunderPhone v3 introduces Zeus, a fully agentic harness that configures, tests and tunes voice agents for a business's use case, replacing the retired Spark, Bolt and Storm pre-baked stacks with one unified architecture. ThunderPhone says its multi-model architecture, which runs multiple transcription models and combines faster and slower LLMs turn by turn, scores 99.4% on Big Bench Audio. Zeus is free for now, and ThunderPhone uses cost-plus pricing with margins from 17% to 25%.

  27. Artificial Analysis Articles60

    Multimodal Knowledge Agent (MKA) benchmark: testing knowledge work capabilities with complex visual files

    Artificial Analysis partnered with Google DeepMind to launch the Multimodal Knowledge Agent (MKA) benchmark, comprising 200 private real-world visual tasks across 10 industries in which agents work from dense visual files like architectural drawings, engineering schematics, and clinical scans to produce deliverables such as slide decks, spreadsheets, PDFs, Word documents, and marked-up images. Tasks are graded against expert rubrics averaging ~70 weighted criteria split into Regression and Climb checks, with the headline Climb WSR score, run in the open-source Stirrup agent harness with up to 250 turns and graded by GPT-6 Luna (medium) as an agentic judge. Claude Fable 5.2 (max) leads with 57% Climb WSR, followed by Gemini 4 Carbon (high) at 54% and Claude Opus 5.5 (max) at 53%, while Claude Fable 5.2 averages $31.97 per task versus $6.29 for Gemini 4 Carbon and $1.11 for GPT-6.1 Sol.

    Why it matters: The results offer a useful cost-performance and per-vertical breakdown for anyone choosing models for agentic knowledge work over complex visual files.

  28. TechCrunch · AI58

    Oura to acquire AI-native primary care startup Counsel Health for $625M

    Oura announced it will acquire AI-native primary care company Counsel Health for $625 million, expanding the partnership that integrated Counsel's chat-based medical AI and physician access into the Oura app in June. Counsel CEO Muthu Alagappan will join Oura as chief clinical AI officer with the company's 70 employees, and Counsel will continue serving enterprise partners. The deal is expected to close before the end of 2027, and Oura also reported quarterly revenue of $533 million, up 153% year-over-year.

  29. Hacker News AI45

    Doc2Harness: Benchmarking how well AI builds agent harnesses

    The authors propose Doc2Harness, a two-stage benchmark that evaluates long-horizon harness engineering: a build model constructs a candidate harness from an interface-only contract skeleton and a development document consolidating behavior across twelve frontier harnesses, and the frozen harness is then run per test case by a scripted mock model and scored via four observable channels. Across nineteen frontier models, each with three independent builds on 328 test cases, GPT-6 Astra achieves the highest pass rate at 53.05% while the weakest model reaches 27.44%, and failures cluster around how cross-cutting functionality is split across modules. The authors describe it as the first deterministic benchmark for measuring long-horizon harness engineering.

  30. The Decoder73

    Anthropic turns Claude into a full workspace with Plugins, spreadsheets, whiteboards, and soon Meeting notes

    Anthropic is adding collaboration features to the Claude app: Claude Sheets for creating and editing spreadsheets with AI assistance, Claude Whiteboards for brainstorming with Claude summaries, and Claude Data (formerly Dashboards) for connecting to tools like Snowflake and Salesforce to build dashboards and visualizations. It is also launching Interactive Connectors, letting partners such as Adobe, Atlassian, and Salesforce embed their apps into Claude, similar to ChatGPT's plugins, and says Claude Meetings, which can join calls and take notes, is launching "soon." Enterprise customers get security controls including audit logs, isolated virtual machines, and a compliance API.

  31. Hacker News AI18

    MAMIXcite is AI visibility+SEO+AEO+GEO+ Business improvement. is this useful?

    MAMIXcite is a platform that observes how answer engines such as ChatGPT, Gemini, Perplexity, Claude and Google AI describe, compare and recommend a business, then diagnoses competitive gaps, prioritizes improvements, supports owner-approved execution and measures before-and-after change. It adds a "Business Excellence Intelligence" layer aimed at the business itself — service quality, customer experience, operations and credibility — and states it cannot guarantee AI recommendations. It is positioned for businesses in the UAE, starting with dental and healthcare clinics, property maintenance and home services, real estate, and agencies.

  32. Hacker News AI58

    Woolly, a local memory shared by all your AI tools

    Woolly is a local, private memory layer that runs on your computer and gives MCP apps like Claude Code, Claude Desktop and Cursor one shared memory stored as plain Markdown files. It also adds memory to Ollama and OpenAI/Anthropic-compatible apps via `woolly proxy`, keeps facts current by replacing outdated ones, and lets you review, edit or delete memories through `woolly ui`. Installation is via a curl script, Homebrew, Windows PowerShell, or `go install`, with a Python SDK available as `pip install woolly-ai`.

  33. Google Blog AI55

    Gemini Intelligence: New features, on more devices

    Google announced that Gemini Intelligence is expanding to more devices, including the motorola signature 27 (pre-order in the U.S. from November 19) and Pixel 10, Pixel 10 Pro XL and Pixel 10 Pro Fold via today's Pixel Drop. New and expanded features include Create My Widget for building custom widgets from a prompt, Device Assistance for controlling and fixing your device by asking, Rambler on additional devices, and task automation expanding to the UK, India and Japan. Gemini Intelligence is also coming to Android Auto for proactive suggestions and to Pixel Watch for Create My Widget in the coming weeks.

  34. TechCrunch · AI48

    OpenAI rolls out new business profiles, making ChatGPT just a little bit more like Google

    OpenAI launched a beta Business Hub where companies can create verified business profiles and, if eligible, a specialized business agent that ChatGPT users can ask about the business and its products. The hub also offers limited business insights such as profile views, business mentions and website clicks, and businesses must verify their profiles through a process OpenAI did not detail. The move follows the company's earlier e-commerce effort, which it retired in March.

  35. Hacker News AI36

    Show HN: Uplumo – See which pages AI answers cite

    Uplumo is an SEO and AI search platform that tracks Google rankings, audits sites, shows where AI assistants mention a brand, and measures AI referral traffic via a cookie-free tracker. Its AI Visibility feature inspects brand mentions and cited sources across supported models, while plans range from a free tier to Business at $69/month with white-label reports. The post states that AI Visibility does not cover every answer and that Uplumo does not guarantee rankings or sales.

  36. The Verge · AI58

    ChatGPT is getting verified AI ‘Business Agents’

    OpenAI is launching verified “Business Agents” in ChatGPT in beta, initially for eligible US e-commerce and online service businesses, letting users chat with brand-representing agents for tasks like comparison shopping. Businesses can set agent instructions and context, and can claim and verify their organization through Business Hub, which also shows insights like ChatGPT mentions and top discovery topics. OpenAI says chats with Business Agents will be clearly labeled and separate from the main ChatGPT conversation.

  37. The Decoder82

    Gemini 4 Carbon arrives just in time to feel like yesterday's news in the fastest model cycle yet

    Google has released Gemini 4 Carbon, which it says complements rather than replaces Gemini 4 Argon, targeting complex multi-step coding, debugging and open-ended scientific research. Anthropic's newly unveiled Fable 5.2 outperforms Carbon in the Artificial Analysis test even at lower reasoning intensity, though Carbon costs far less per task. Google also previewed a "/swarm" feature in Antigravity and reported that Carbon achieved a zero percent prompt injection success rate on the Gray Swan IPI benchmark.

    Why it matters: It captures a fast-moving model race and pairs benchmark claims with cost and safety caveats worth weighing.

  38. Baseten Blog69

    How Baseten and Genspark trained a deep research model to outperform Opus 5.5

    Genspark worked with Baseten Applied Research to post-train Qwen3.5-397B into a specialized Deep Research model that scores 0.759 on Genspark's quality grader, up from 0.612 for the base model and above Opus 5.5 (0.738), Sonnet 5.5 (0.742), GPT-5.6 Sol (0.637), Kimi K3 (0.724) and DeepSeek V4 Pro (0.675). The recipe splits the task into research, trained with reinforcement learning against a shaped semi-verifiable reward, and synthesis, trained mainly with supervised fine-tuning on high-quality reports written from the model's own research trajectories, followed by end-to-end RL. The model crawls 5× more sources per query than the base model and runs with NVFP4 weights on 2×B200 GPUs per replica, now serving as the default for Genspark's Deep Research agent in production.

    Why it matters: A detailed, reproducible account of post-training an open model for a judged production workload, useful for teams weighing RL versus SFT and reward shaping.

  39. AWS Machine Learning Blog34

    Autonomous treasury agents: How Trovata built an AI-native solution on Amazon Bedrock and AgentCore

    Trovata, an AI-native cash and liquidity management platform connected to over 10,000 banks, describes how it built autonomous treasury agents on Amazon Bedrock and Amazon Bedrock AgentCore, using role-based access control and a verified API layer within a bank-branded deployment model. The post outlines use cases such as cash forecasting, natural language querying, anomaly detection, automated reconciliation and persistent agentic workflows, and cites customer results including $1M+ in annualized cost savings, 5+ hours per day saved per accounting team, a 77 percent reduction in annual TMS costs, and reporting reduced from hours or days to under a minute. It also notes a library of ten agent patterns from real customer deployments and Trovata's plans to expand agent patterns, ERP integrations and global bank connectivity.

  40. Hacker News AI50

    Show HN: Qitt – A proactive AI chief of staff built on T3 Code

    Qitt is a proactive chief of staff built from T3 Code threads and scheduled tasks that watches incoming requests, triages them, and starts research worker threads ahead of time, but never sends anything—every output is proposed text for the owner to review. It is vendor-agnostic, customizable via Markdown charters and a local context file, and extendable through input-source folders, with Slack and JIRA shipping as examples; it has run on Claude only so far. It requires a T3 Code server and Node.js 22.19 or later, and runs on one always-on machine, losing events that arrive while it is down by design.