iCreatAI News
Back to main site
Skip to content
#Deployment
Nov 7Sat
  1. AWS Machine Learning Blog36

    Taxbit Assist: A grounded, role-aware AI agent on Amazon Bedrock AgentCore

    Taxbit built Taxbit Assist, an embedded AI assistant for its digital-asset tax compliance dashboard, on Amazon Bedrock AgentCore using the Strands Agents SDK, with grounded and cited answers, role and organization awareness, no tax advice, and regional data residency. The post details the architecture, a curated knowledge base with semantic chunking and reranking, identity bound in code rather than by the model, guardrails-based PII handling, and continuous production quality measurement. Taxbit reports the assistant has run in the US and EU since May 2026, with model cost averaging under 20 cents per conversation and about three-quarters of input tokens served from prompt cache.

  2. AWS Machine Learning Blog50

    How Greenlight Financial built an autonomous SOC solution on Amazon Bedrock AgentCore

    Greenlight Financial's Luna, built on Amazon Bedrock AgentCore runtime and memory, autonomously resolves more than 90 percent of its 3,000–4,000 monthly security and risk cases, using a tiered supervisor architecture with over 30 specialized agents and episodic memory for continuous learning. The system triages dark web breach-card alerts, identity anomalies, and financial-risk events in seconds, escalating complex cases to a Tier 2 supervisor and human analysts. Greenlight later extended Luna into financial risk triage within two months by adding new specialized agents and a risk-domain supervisor to the existing infrastructure.

  3. AWS Machine Learning Blog50

    Govern AI agent access with Okta Cross App Access and Amazon Bedrock AgentCore – Part 1

    This AWS post describes using Okta Cross App Access (XAA) as the governance plane and Amazon Bedrock AgentCore Identity as the execution plane so an AI agent can act on behalf of signed-in users, with Okta deciding which agent may act for which user and AgentCore redeeming Okta's single-use ID-JAG for a short-lived access token. It walks through registering the agent in Okta, configuring the credential provider and workload identity, enforcing per-user authority via the groups claim in MCP servers, and reports measured results such as revocation taking effect in about 1 second and AgentCore Identity adding about 0.6 seconds to a roughly 30-second request.

  4. AWS Machine Learning Blog36

    Govern AI agent access with Okta Cross App Access and Amazon Bedrock AgentCore – Part 2

    Part 2 of this AWS post moves the Part 1 Okta Cross App Access solution from one agent and two MCP servers to a topology with Amazon Bedrock AgentCore Gateway as a single front door that redeems Okta's ID-JAG for each target, default-deny Cedar policies in AgentCore Policy binding tools to agents and delegated scopes, and a second agent on Amazon EKS under its own Okta identity. It also describes tracing decisions with AgentCore Observability and CloudWatch Omni alongside Okta's System Log, reports validation results and latency figures, and compares XAA with per-user OAuth consent for applications that cannot accept an ID-JAG.

  6. Hacker News AI30

    AI companies should own their metering, not the billing stack

    The author argues that "billing" bundles distinct jobs—usage metering, pricing, balances, invoicing, revenue recognition, and contracting—and that AI companies should own the customer-facing fast loop (event collection, aggregation, pricing, and balance pools) while buying specialist software for invoicing and revenue recognition. End-to-end billing vendors often require customers to run their own collection infrastructure, manage enterprise agreements in parallel systems, and rely on spreadsheets for ASC 606 revenue recognition, and replacing one outgrown component can force changes across a monolithic stack. The recommended architecture connects metering and back-office systems through a single shared model of commercial agreements owned by the back office.

  7. Google Developers Blog60

    Agent Distraction

    The post reports that 13% of agent file-reading sessions expose the agent to inline TODO(bug/...) or FIXME(bug/...) references, and in 6% of encounters the agent takes follow-up action on that bug ID, 83% of which are unprompted by the developer. Cross-referencing these detours against live bug status, it finds 41% chase already-closed or obsolete tickets while 57% involve still-open bugs where the agent expanded scope, and a fixed-effects regression shows unprompted bug detours add 70% more steps, 77% more tokens and 105% more wait time per session. The authors built agents that scan codebases and remove confirmed-obsolete bug references, reporting thousands removed over six months with over 95% acceptance from human reviewers.

    Why it matters: Offers a quantified, data-backed look at how stale code comments misdirect coding agents, plus a concrete remediation approach.

  8. NVIDIA Newsroom40

    How NVIDIA Open Source Tools Are Helping Researchers Build Next-Generation 6G Networks

    NVIDIA's open source Aerial and Sionna tools, whose adoption has grown 10x in a year with over 1 million downloads of its open source 5G/6G tools and use by more than 8,000 research and academic institutions, are being used by researchers on projects including goal-oriented semantic communications for robots at King's College London, a neural receiver tested by SoftBank, demand-predicting base station sleep at the University of Leeds, and GPU-accelerated channel models in CTTC's 5G-LENA simulator.

  9. Factory Blog36

    Extending the Factory Organization Model with User Groups

    Factory introduced User Groups, which sync from an identity provider via Directory Sync and let admins set usage limits and model access per group, mapped into chosen organizations. Settings resolve per request in a hierarchy where an individual override wins, then the user's group settings in that organization, then the organization default; for limits the highest group limit applies, and for model access a model is allowed if any of the user's groups allows it. Groups are configured in the Enterprise Admin Console, group limits can be managed through the Organization API up to 100 groups per request, and changes are recorded in the audit log.

  10. Hacker News AI58

    Show HN: Infinity – Git-style branching for AI chats

    Infinity is a free macOS app (version 0.1.5, macOS 14+, Apple silicon and Intel, early testing) that lets every AI answer branch, with forks from any phrase, a Canvas view mapping all branches, and side-pane or inline continuation. It supports local models via Ollama, LM Studio and Apple Intelligence plus cloud providers including OpenAI, Anthropic, Google and OpenRouter, can send one message to up to four models at once, and adds Code and Assistant modes with shared projects. The app requires no account and includes no ads or analytics, keeping chats, settings and the file index on the Mac and API keys in the Keychain.

  11. Hacker News AI65

    AI agent can move money in Stripe

    Stripe's MCP server lets AI agents build checkout pages, run financial reports, automate refunds or price adjustments, and now send money to others via Stripe Treasury. Agents can connect on your behalf via OAuth with human confirmation required for sensitive live-mode actions, or get their own identity through agent-tagged API keys governed by Approval rules that require designated reviewers for sensitive actions. Approval requests can be reviewed in the Dashboard, expire after 14 days if unapproved, and agents can listen for outcomes via webhook events such as v2.core.approval_request.approved.

  12. Hacker News AI73

    AI coding agent setups from 663 Hacker News comments

    An analysis of an Ask HN thread from November 4, 2026, in which 424 of 530 commenters named at least one AI tool, found Claude Code leading with 180 users, followed by Codex with 103, while 148 people named open-weight or local models such as DeepSeek, Qwen and GLM. The piece distills nine detailed setups into seven patterns, including running parallel agents in separate git worktrees, fresh-context reviewers on every change, cheap builder models behind strong planners, and sandboxing agents that run without permission prompts. Counts are self-reported and drawn from three readers' notes on every comment, so the article treats them as close rather than exact.

  13. Baseten Blog70

    Introducing Serverless Loops: frontier RL training for everyone

    Baseten announced the general availability of Serverless Loops, a Tinker-compatible training SDK for supervised fine-tuning and reinforcement learning on frontier open models at 256k context length, with one-click deployment to Baseten Dedicated Inference or weight download in Hugging Face Safetensors format. The release cites early users including NVIDIA, Datadog, LangChain Labs and Ambience Healthcare, and reports NVIDIA's post-trained Nemotron Super 3.5 VL improving intent classification accuracy from 76.8% to 94% and reaching 87% validation F1 on receipt extraction.

    Why it matters: Useful for readers weighing managed post-training options, as it pairs a GA launch with named early adopters and concrete reported results.

  14. The Decoder60

    Frontier Radar #5: If AGI is so close, why is everyone leaving? The neolabs and their bets

    This newsletter surveys 27 independently founded, research-driven "neolabs" in the US and Europe, grouped by their primary technical bet, and contrasts their founders' doubts about today's recipe of ever-larger language models with claims from Jensen Huang and Greg Brockman that AGI has arrived. The first group targets continual learning and learning from few examples (Adaption, Core Automation, Flapping Airplanes, Ineffable Intelligence, Ndea, Safe Superintelligence), while the second bets language alone is insufficient and pursues spatial and physical intelligence (AMI, Black Forest Labs, General Intuition, Physical Intelligence, World Labs). It notes the funding behind these labs, including Nvidia's reported five billion dollar investment in SSI and AMD's planned acquisition of World Labs for about 8.2 billion dollars, and asks whether they can deliver something the big players lack.

  15. Hacker News AI58

    SpaceX launched Google AI chips to orbit with Planet Labs satellites

    SpaceX's Falcon 9 launched Planet Labs satellites on the Transporter-18 mission, including a solar-powered prototype carrying Google tensor processing units, marking the first in-orbit test for Alphabet's Project Suncatcher. Alphabet said its team confirmed contact with the satellite and that it is operating as expected, calling the launch a first step in research into whether space could host scalable machine learning infrastructure. Alphabet, which holds a SpaceX stake valued at over $82 billion, said satellites in low Earth orbit can access near-constant sunlight and generate up to eight times more solar power than on Earth.

Nov 6Fri
  1. Modal Blog27

    How Snorkel runs realistic agent simulations with Modal

    Snorkel uses Modal to power inference for open-weight models it evaluates and to provide GPU and CPU sandboxes for millions of agent simulations per month, peaking at tens of thousands of sandboxes an hour. Modal's VM sandboxes let Snorkel recreate production-like environments, including multi-service systems and GPU-enabled workloads, and its memory bursting feature cut total sandbox costs by around 20% by avoiding over-provisioning. Snorkel also uses Modal's Shared and Dedicated Endpoints to stand up inference for new and fine-tuned models, and plans to evaluate Modal as a training solution.

  2. ElevenLabs Blog55

    Give your Unity NPCs a voice with ElevenAgents

    ElevenLabs released an ElevenAgents Unity SDK that connects a Unity scene to an ElevenLabs voice agent, listening through the player's microphone, playing the agent's voice through an AudioSource, and running the session via the Conversation API. The same code runs in the Editor, desktop builds, and WebGL, with iOS, Android, and XR in beta. The SDK supports dynamic variables, overrides, contextual updates, client tools, and main-thread events, and is installed via the git URL https://github.com/elevenlabs/unity.git#v0.1.0.

  3. OpenRouter Announcements67

    Introducing the New Auto and Auto Code Routers

    OpenRouter launched a rebuilt Auto Router on a new technical foundation that it says outperforms the previous version by up to 4× on benchmarks, with a routing step 3× faster at p90 (0.65s vs 1.96s), alongside a new coding-specialized Auto Code router (openrouter/auto-code) that scores in line with Claude Opus 5.5 across five benchmarks while costing 74% less per task. The new routers weigh eleven factors per request combined with live pricing, provider health, and cache status, and work within governance policies such as guardrails, zero data retention, provider restrictions, allowed model lists, and BYOK keys. The slug openrouter/auto is unchanged, and the cost_tier, allowed_models, and excluded_models settings still work.

    Why it matters: Useful for readers tracking model-routing products, since it details concrete latency and cost claims and explains how routing differs from provider routing.

  4. Browser Use Blog25

    Best Proxy Providers for AI Agents (2026)

    The article compares seven rotating residential proxy providers (Decodo, Oxylabs, FloppyData, Roundproxies, Byteful, DataImpulse, Webshare) on IP pool size, location targeting, sticky session length, entry pricing, trials and traffic expiry, and reports results from browser-agent benchmark tasks such as product research, text extraction, form filling and session continuity. It also covers built-in versus bring-your-own proxies on browser platforms, setup guidance for custom proxies, and advice on checking session continuity, location coverage, target-site access and cost per completed task. The author notes the samples are small and differently timed and do not establish a universal reliability or speed ranking.

  5. Hacker News AI58

    Show HN: Current – Change control for AI agents (Elixir)

    Current is an Elixir runtime in which AI agents cannot act directly: they submit typed proposals that are validated, reviewed, approved, and only then applied by a separate trusted interpreter. Every step, from the request and the files the model read to approvals and effect outputs, is recorded in a hash-chained, event-sourced log that can be replayed to rebuild state. It is early-stage, single-node, and explicitly not a sandbox or authentication system.

  6. Cloudflare Blog34

    The post-quantum future of web privacy

    Cloudflare explains how Privacy Pass, which relies on classical cryptography like RSA and elliptic curves, will need post-quantum replacements, and explores MOLE (Moderation Of unLinkable Endorsements), a design whose endorsements hide the issuer's identity. The post describes how the VOLE-in-the-Head proof system combined with multivariate signatures such as UOV and MAYO yields blind signatures like PoMFRIT (6.7KB, reducible to about 4.3KB with UOV), and how these building blocks can be reconfigured into MOLE endorsements and credentials. It also covers optimizations (fewer hashes, TurboSHAKE, smaller Keccak state, multivariate commitments and PRGs) and notes that multivariate cryptanalysis is still immature, so parameter changes and further study are expected.

  7. Trail of Bits Blog40

    After Binance, check what your signing systems can approve

    This article examines the October 2026 Binance security incident, in which attackers who compromised a DevOps laptop obtained valid signatures from Binance's wallet-signing service and used an EIP-7702 delegation to authorize repeated transfers without further signatures. It argues that transaction execution and monitoring systems must understand newer Ethereum execution paths such as EIP-7702 delegations, session keys, Safe modules and ERC-4337 UserOperations, and offers a four-step checklist covering reduced signing access, treating delegation as an administrative privilege, limiting damage if signing is compromised, and detecting changes in wallet authority.

  8. Hacker News AI65

    Baton – Keep long coding goals moving across AI coding agents

    Baton is a tool that keeps a single long coding goal running for days by rotating it between coding agents, ending each agent's turn at 5 hours or USD 50 and excluding Claude from a goal after USD 150 spent. It works with Codex and Antigravity alone, with Claude as an optional pay-per-use third agent that joins only once an API key is saved, and it finishes a goal only when a verification command exits 0. Each goal cycles through plan, build and review phases, with context passed between agents via the repository, commits and a handoff file, and Superpowers is required for every round.

  9. Hacker News AI18

    Smooth Outdoor-Indoor Mapping, JWT Auth and AI Analytics

    Navigine's autumn 2026 platform update adds raster map tile support, flicker-free zooming, turn-by-turn guidance with pedestrian ETA and a built-in route simulator to its mobile SDKs. It also completes a full migration to JWT authentication across API, Web Portal, QR Navigation and Emulator, deprecating legacy hash and API key methods, and introduces API rate limiting and configurable track history retention. AI-powered analysis is added to Heatmap and Workday picture reports, alongside interactive zone-level notification overlays and targeted email and Telegram alerts sent to individual tracked assets.

  11. Hacker News AI58

    Lowvram: A CLI tool to run large AI models in low VRAM GPUs

    Henrique Soares introduces lowvram, a Linux CLI tool that intercepts CUDA calls via LD_PRELOAD, replacing cuMemAlloc with cuMemAllocManaged so applications can use system RAM when VRAM is insufficient. On a 6 GB RTX 3060, YuE2 under lowvram generated 43.1 tokens per second versus 1.9 for Accelerate and 6.8 for CPU, and Llama-TTS with Qwen3-TTS ran after a standard run failed with an out-of-memory error. The author notes trade-offs: PCIe paging slows computation, system RAM can be exhausted, and the tool requires CUDA knowledge.

  12. Amp Chronicle60

    Spaces

    Amp launched spaces, a new way to interact with agents and your team in which a space is a conversation with a single agent whose job is to spawn and coordinate agents for you, so you no longer have to create and organize threads yourself. The post describes internal uses, including building Spaces v1 itself, running a service-accounts launch with monitoring and user refunds, and a security review that split the codebase into 16 areas. To start a space, use the + in the Spaces section of the sidebar, set a title and a project, and tell your agent what to work on.

    Why it matters: It offers a concrete look at a higher-level agent-orchestration workflow, illustrated with the team's own day-to-day examples.

  13. Amp Chronicle50

    Close the Loop

    Amp now offers a feedback widget that lets users send change requests directly from their website: enable it in project settings, add a script to the site's <head>, and allow the site's origin. Visiting the site with ?amp shows the annotation widget, where clicking page elements and writing instructions sends feedback that starts a new thread in the project, and the change is shipped from that thread like any other. After the first use, the widget appears on the site without ?amp until hidden.

  14. Manus Blog34

    How to Build Your First Game with AI: A Step-by-Step Guide

    This guide compares three no-code routes to a first game—AI game builders like Manus, visual event-sheet engines GDevelop and Construct 3, and block-based Scratch—and stresses that game design, not tooling, is the hard part. It provides a fill-in-the-blanks game brief template and a walkthrough of building a 2D robot platformer in Manus, from prompt and Game Blueprint through playtesting, tuning, and publishing a shareable link.

  15. Hacker News AI58

    You Had Me at "Hello": A Chinese‑Language Framework Targeting AI Infrastructure

    Era researchers observed a Chinese-language exploitation framework they named Greeter attacking seven Flowise honeypots across four regions from July to October 2026, using the overrideConfig code injection flaw CVE-2024-58351 to execute commands via chat messages that each read only "hello". The 12-step chain included host reconnaissance, cloud metadata probing, credential discovery, persistence attempts and fileless execution staging, with commands arriving 3.5 seconds apart. A Shodan query found 4,372 internet-exposed Flowise instances, of which 703 of 3,277 version-identifiable hosts had no authentication enabled and 46 appeared to share the vulnerable conditions recreated in the honeypots.

  16. Hacker News AI20

    Open AI Cellular: Open platform for prototyping and testing AI based 6G

    Open AI Cellular (OAIC) describes its mission as providing an open platform for prototyping and testing artificial intelligence-based controllers enabling 6G research. The page announces the OAIC-T v2.0.0 release, which adds RANFusion, a simulator of 5G core network component behaviors and performances, with InfluxDB support, KPI metrics, AI fuzzing using genetic algorithms to generate UE traffic for testing traffic balancing methods, and example test scripts. It also lists past workshops, tutorials and talks, and notes NSF sponsorship under fund numbers 2120442 and 2120411.

  17. Hacker News AI48

    Axiom – blocks AI agents from inventing limits your code never defined

    Axiom is a zero-dependency local guardrail that runs as a pre-write hook in Claude Code and Cursor, or as a stdin/stdout filter for other agents, blocking tool calls before writes occur. It uses regex and AST-pattern detection across three components (Noema, Lemma, Manam) to catch hardcoded numeric bounds, auth bypasses, dangerous Bash, secrets, dependency confusion and invented rate limits, with a tri-state TRUE/FALSE/UNKNOWN logic that halts on UNKNOWN. The author states detection is not semantic and can be bypassed with minor obfuscation, positioning it as a first line of defense alongside container isolation, branch protection and secret scanning.

  18. vLLM Blog42

    VeRL-Omni v0.3.0: Async Training and Broader Multimodal Post-Training

    VeRL-Omni v0.3.0 adds asynchronous and decoupled RL execution paths across multimodal workloads, makes the TransferQueue/ReplayBuffer-based V1 trainer the default, and moves the rollout stack to vLLM 0.30.0 and vLLM-Omni 0.30.0. It includes end-to-end recipes for MiniMax H3 audio-video post-training with DiffusionNFT and MiniCPM-o 4.5 AVQA GSPO, where a 4×H800 experiment found separate-async about 9% slower per prompt at natural response lengths but roughly 6.7% faster at 1024 tokens. The release also expands model and algorithm coverage, adds Ascend and AMD ROCm Dockerfiles, and notes upgrade changes including V1 as default, named diffusion media artifacts, and fail-closed attention backends.

  19. Codex Releases22

    0.167.0

    Codex 0.167.0 adds an agent command center opened with `codex agents --no-daemon`, unread-result markers in the command center and session picker, cross-backend session switching from the terminal picker, local image attachment previews, and a Google Cloud Vertex AI setup wizard. Bug fixes keep saved chats visible across model provider changes, preserve transcript history when Ctrl+L clears the terminal, and resolve network approval prompts when their requests end. Documentation and chores cover managed network constraints under [permissions.network], DotSlash manifest updates, and reduced jemalloc arena counts for Linux musl builds.

  20. Hacker News AI36

    The Sweet Spot: How One Brain and Thousands of Micro-Adapters Could Save Open AI

    The article argues that open models are bottlenecked by hardware because Mixture of Experts architectures must keep all total parameters in memory even though only a fraction are active per token. It proposes a frozen, quantized base model paired with thousands of 2–5 MB low-rank adapters selected by a two-step hierarchical router, plus Multi-Head Latent Attention to compress the context cache by roughly ninety percent. Because small adapters can be streamed from system RAM or SSD in a millisecond or two, the design lets capable AI run locally on accessible hardware instead of multi-GPU clusters.

  21. The Verge · AI58

    Perplexity launches its own take on AI agents for work

    Perplexity has launched always-on "Teammates" that can take on multiple roles within a workspace, pulling existing projects, skills, and memory from Perplexity tools, and building on Perplexity Computer to support collaboration and ongoing, large-scale work. Each Teammate can be assigned different jobs that run simultaneously, with progress tracked through individual threads in the Perplexity app and interaction available in Slack, but the feature requires the $200/month Max plan. CEO Aravind Srinivas said on X that the company envisions "every org having hundreds of teammates working for each person."

  22. Hacker News AI71

    AgentSight: System-wide AI agent profiling and monitoring with eBPF

    AgentSight is a local-first, top/strace-like observability tool for AI agents that uses eBPF and TLS traffic tracing to connect prompts, model calls, and tool decisions to their real effects on the machine, without requiring an SDK, proxy, or vendor integration. It works with existing agents such as Claude Code, Codex, Gemini CLI, OpenCode, and OpenClaw, offering live session views, process/file/network tracking, saved SQLite session reports, a web UI, and OpenTelemetry export. The project is MIT-licensed and installable via Homebrew, Cargo, release binaries, or Docker, with eBPF requiring Linux kernel 4.1+ and sudo access for live capture.

  23. Sierra Blog40

    Accelerators take care of the basics

    Sierra describes Accelerators, prebuilt packages for high-volume workflows such as order tracking, appointment scheduling, claims intake and ID verification, which come with basic integrations and guardrails and are customized for a business using Ghostwriter. Accelerators are maintained by Sierra but track customer changes separately so updates can be reviewed before being applied, and they connect to a company's existing software systems. The first Accelerators are available today in Agent Studio, with user-built and shareable Accelerators planned.

  24. MarkTechPost67

    Baidu Releases ERNIE 5.5 Flash Base: A 280B MoE Base Model With 14B Active Parameters

    Baidu has released ERNIE 5.5 Flash Base, a 280B-parameter text-only sparse MoE pre-training checkpoint that activates 14B parameters per token, with 128K training context and up to 1M for fine-tuning and inference. It uses hybrid attention (37 HCA layers caching 1 entry per 128 tokens plus 6 MLA+DSA layers), 512 routed experts with top-10 plus one shared expert, and ECHO in place of MTP, and was pre-trained from scratch on 33.5T tokens with the Muon optimizer. Baidu reports best scores on 24 of 30 base-model benchmarks in its unified pipeline, including MMLU-Pro 78.4 versus 69.2 for DeepSeek-V4-Flash-Base, with weights on Hugging Face and ModelScope in FP8 and BF16 and serving documented for SGLang and vLLM.

  25. AWS Machine Learning Blog53

    Getting started with Web Answer on Amazon Bedrock AgentCore

    Amazon announced the general availability of Web Answer on Amazon Bedrock AgentCore, a managed Gateway tool that takes a natural-language question and returns a synthesized answer with source citations in seconds, replacing a self-built search, retrieve, synthesize, and citation pipeline. The post contrasts it with Web Search (which returns ranked URLs and lets you keep your own model), then walks through granting the Gateway service role bedrock-agentcore:InvokeWebAnswer, creating a Web Answer target, and calling it from a Strands agent. It is available in us-east-1 at $10 per 1,000 tool calls, with a 10 transactions per second per account rate limit.