AllyshipContent Radar

News 2877

Chủ đề cộng đồng đang thảo luận

Crawl live-1795119300000 · 03:15 20 thg 11, 2026 · Xuất bản 03:31 20 thg 11, 2026

203 / 2877 chủ đề đạt ngưỡng 55 trong khoảng này.

1

Ask HN: Who Is Hiring? (November 2026 – We Give a Shit Edition)

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 5 tương tác đã đo · Nguồn crawl

k_sze 1 bài viết · HN: AI agent
Nguyên văn nguồn
Chi tiết nguồn

This is a bit of a tongue-in-cheek. Since reading the "We need smart people who give a shit" story (https://news.ycombinator.com/item?id=50554045), and the comments underneath it, I realise that there is a good deal of engineers who are disgruntled by how AI is incompatible with smart people who give a shit, how it is turning us into meat proxies and Letzter Mensch. So this is a call for companies and employers with smart management who still give a shit, who do not demand that engineers replace their workflow with 5 parallel agent sessions, who appreciate the craftsmanship of humans, to step forward and post their job openings.

3

Knowledge factories! (They call it Knowledge engine but same thing)

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

hwchase17 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Knowledge factories! (They call it Knowledge engine but same thing) Hex is one of the best agent building companies I know! We did a pod with them a year ago where we chatted a bit on an earlier version of this https://m.youtube.com/watch?v=Xyh1EqcjGME

5

Build your own custom index in the Artificial Analysis Data Playground

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

artificialanlys 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Build your own custom index in the Artificial Analysis Data Playground Add any Artificial Analysis benchmarks, customize their weights, and plot the results with other chart axis. Models receive a score only if they have results for every evaluation in your index, consistent with the Intelligence Index methodology. Also in the Data Playground: ➤ Formula metrics: combine any metrics with +, -, *, / and functions such as log and sqrt ➤ Playback: play a scatter chart forward by launch date, with the frontier drawn as it stood at each date ➤ Heat maps across many evaluations, and box plot distributions by group, such as open weights vs proprietary ➤ A workbench with sheets, Columns/Rows shelves and a dashboard view The Data Playground is available with Artificial Analysis Pro. Media

6

Optimize AI economics on Amazon Bedrock with Accenture’s sequenced approach

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Ilan Geller 1 bài viết · AWS Machine Learning Blog
Nguyên văn nguồn
Chi tiết nguồn

<p>As enterprises scale AI on <a href="https://aws.amazon.com/bedrock/" target="_blank" rel="noopener">Amazon Bedrock</a>, token spend often grows even as per-token prices fall. Without cost allocation tags in place, your cloud invoice shows AI spend as a single line item rather than by team, workload, agent, or model. Cheaper tokens expand adoption, and agentic workloads multiply invocations. As successful AI use cases scale, consumption can rise faster than unit prices drop. The economic question is whether the business value generated grows faster than the cost of the intelligence required to produce it. The Linux Foundation has launched the <a href="https://www.linuxfoundation.org/press/linux-foundation-launches-the-tokenomics-foundation-to-define-the-economics-and-roi-of-ai-value" target="_blank" rel="noopener">Tokenomics Foundation</a> to develop open standards for AI cost economics, a sign that managing the economics of AI is now an industry discipline.</p> <p>In this post, you will learn about six levers for optimizing token spend, how Accenture applied them in production, and how to apply them using Amazon Bedrock.</p> <p>Accenture applied these levers in four client engagements across telecom, insurance, mining, and a large enterprise deployment. The same levers are available natively on Amazon Bedrock as described in this post. Where savings were measured, token spend fell by about 40–85 percent. Results are specific to each client’s workload and may vary. Client names are withheld by Accenture to protect client confidentiality.</p> <h2 id="attribution-first-measuring-cost-at-the-business-level">Attribution first: Measuring cost at the business level</h2> <p>Before you optimize anything, you need to see where consumption is occurring, who owns it, and what business value it produces. Cost allocation tags at the team, workload, and agent level are the prerequisite for connecting consumption to accountable owners and, ultimately, to business outcomes. You apply them through <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cost-mgmt-application-inference-profiles.html" target="_blank" rel="noopener">Amazon Bedrock application inference profiles</a>, one profile per application or workload, tagged by team, cost center, and environment. After you activate them as cost allocation tags in the <a href="https://aws.amazon.com/aws-cost-management/billing-and-cost-management-console-home/" target="_blank" rel="noopener">AWS Billing and Cost Management console</a>, you can use these tags to trace which teams, applications, and agents are driving spend. They also make it possible to measure the impact of each change you introduce.</p> <p>Three AWS services provide the underlying telemetry. <a href="https://aws.amazon.com/aws-cost-management/aws-cost-and-usage-reporting/" target="_blank" rel="noopener">AWS Cost and Usage Reports</a> (CUR 2.0), delivered through <a href="https://docs.aws.amazon.com/cur/latest/userguide/what-is-data-exports.html" target="_blank" rel="noopener">AWS Data Exports</a>, handle financial attribution, breaking down billed inference cost by workload and team after your cost allocation tags are active. <a href="https://aws.amazon.com/cloudwatch/" target="_blank" rel="noopener">Amazon CloudWatch</a> captures operational signals such as invocation counts and latency. <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-invocation-logging.html" target="_blank" rel="noopener">Amazon Bedrock model invocation logging</a> records request-level detail, including the model used and the input and output token counts for each call.</p> <p>Telemetry alone isn’t enough. Engineers can read cost per invocation on a dashboard, but product owners and program leaders need a metric expressed in business terms. Accenture’s Cost per Business Transaction (CpBT) framework bridges this gap. CpBT aggregates all the model invocations, retries, tool calls, and agent handoffs that contribute to one successful business output into a single fully loaded cost figure. It surfaces the true cost of producing a result, including the failed attempts that raw token pricing hides. Tracked against the business value each workflow delivers, CpBT distinguishes a growing bill that reflects scaling success from one that reflects waste.</p> <h2 id="the-six-optimization-levers">The six optimization levers</h2> <p>The goal of these six levers isn’t to minimize tokens at all costs. It’s to use the right amount and level of intelligence to deliver each business outcome at the appropriate cost, quality, and risk. The levers are organized into three phases based on the complexity of the change and the investment it requires. AWS and Accenture recommend working through the phases in order, and you can apply each phase independently to the workloads where it will have the most impact.</p> <h3 id="phase-1-configuration-only-no-infrastructure-change">Phase 1: Configuration only, no infrastructure change</h3> <p>With <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html" target="_blank" rel="noopener">Amazon Bedrock prompt caching</a>, the model reuses the parts of a prompt that repeat across requests, such as system instructions, tool definitions, and reference documents, so you stop paying full price to process the same content again. Amazon Bedrock stores the key-value state of previously computed prompt prefixes and is designed to skip recomputation on later requests. This is designed to reduce cached input token costs by up to 90 percent for supported models (see <a href="https://aws.amazon.com/bedrock/prompt-caching/" target="_blank" rel="noopener">Amazon Bedrock Prompt Caching</a>).</p> <p><a href="https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference.html" target="_blank" rel="noopener">Amazon Bedrock batch inference</a> processes non-urgent workloads asynchronously as a group at 50 percent lower cost than on-demand pricing for select models (s

7

Une note markdown globale qui vous suit dans chaque workspace ?

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

cloudinnantes 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Une note markdown globale qui vous suit dans chaque workspace ? Salut tout le monde ! Je viens de publier le plugin Human Scratchpad; maintenant listé dans le répertoire Community @orca_build Orca donne à chaque workspace ses propres fichiers, terminaux et agents. Ce qui me manquait, c'est un endroit pour tout ce qui n'appartient à aucun d'entre eux : une commande pour demain, une tâche pour cet après-midi, un snippet à coller ailleurs. Scratchpad ajoute un panneau dans la barre latérale droite qui édite un seul fichier markdown, le même quel que soit le workspace ouvert. https://orca.dev/plugins/erom/orca-plugin-human-scratchpad

8

Orca - chạy một đội các coding agents bằng subscription của bạn

71

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

stablyai, orca_build 0 bài viết · GitHub discovery: AI agents, X
Biên tập tiếng Việt
Chi tiết nguồn

Orca được mô tả là cho phép chạy một “fleet of coding agents” (ví dụ Claude Code, Codex) với subscription của riêng bạn. Nền tảng có sẵn trên desktop, mobile và remote runtime.

Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.

  • Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription.
  • Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription.
  • Available on desktop, mobile and remote runtime.
9

Archify - biến ý tưởng/plan/codebase thành sơ đồ tương tác

71

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

tt-a1i, tom_doerr 0 bài viết · GitHub discovery: LLM, X
Biên tập tiếng Việt
Chi tiết nguồn

Archify được mô tả là chuyển mọi ý tưởng, kế hoạch hoặc codebase thành một sơ đồ tương tác “đẹp”. Nó là một agent skill cho Claude Code, Codex và nhiều nền tảng khác.

Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

  • Turn any idea, plan, or codebase into a beautiful interactive diagram.
  • Turn any idea, plan, or codebase into a beautiful interactive diagram.
  • An agent skill for Claude Code, Codex, and more.
11

From learning to leaderboard: How Cisco upskilled 1,200 engineers in agentic AI with AWS AI League

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Rakesh Vangari 1 bài viết · AWS Machine Learning Blog
Nguyên văn nguồn
Chi tiết nguồn

<p>Cisco, like many large engineering organizations, is adopting generative and agentic AI to change how its engineers build software. The hard part is no longer access to the technology. It’s helping thousands of engineers move from watching a demo to confidently building with it. Recorded sessions and slide decks rarely close that gap. Engineers learn fastest when they build something real, see it fail, fix it, and try again.</p> <p>AWS designed <a href="https://aws.amazon.com/ai/aileague/" target="_blank" rel="noopener">AWS AI League</a> for exactly that. It turns hands-on AI learning into a gamified competition, where participants customize models and build agents on AWS, get instant feedback on a live leaderboard, and compete in a game-show-style finale.</p> <p>Cisco is one of the clearest examples of what this looks like at scale. In 2025, Hemanth V, a Cisco software engineer, went from an internal Cisco event to being crowned the first AWS AI League Champion at AWS re:Invent 2025. In 2026, 1,200 Cisco engineers competed in an AWS AI League tournament at Cisco Transformation Fest 4.0. The winner, Nishanth Aluhonnu, earned a full event pass to AWS re:Invent 2026 in Las Vegas.</p> <p>In this post, we share how Cisco and AWS used Cisco Transformation Fest and AWS AI League to build a lasting culture of learning by doing. We previously covered this program in <a href="https://aws.amazon.com/blogs/machine-learning/from-theory-to-delivery-how-atos-upskilled-400-engineers-in-agentic-ai/" target="_blank" rel="noopener">From theory to delivery: How Atos upskilled 400 engineers in agentic AI</a>, and here we look at Cisco’s experience. We walk through Cisco’s journey, share technical lessons from the 2026 winning agent, and explain how your organization can host its own AWS AI League.</p> <h1>What is AWS AI League?</h1> <p>AWS AI League helps organizations build advanced AI skills through competition. Each league follows three steps:</p> <ol type="1"> <li><strong>Learn –</strong>&nbsp;A hands-on, 2-hour workshop led by AWS experts introduces the tools and the challenge.</li> <li><strong>Build –</strong>&nbsp;Participants experiment at their own pace and submit to a live leaderboard, with an automated evaluator giving real-time feedback after each submission.</li> <li><strong>Compete –</strong>&nbsp;Top finalists take the stage in a live, game-show-style grand finale.</li> </ol> <p>Although AWS AI League offers multiple use cases, at Cisco it offered the following two challenges:</p> <ul> <li><strong>Agentic AI challenge –</strong>&nbsp;Participants build agents with <a href="https://aws.amazon.com/bedrock/agentcore/" target="_blank" rel="noopener">Amazon Bedrock AgentCore</a>, a platform to build, connect, and optimize agents at scale with any framework or model. The agents move through a maze-like grid, solving challenges on the way to a treasure chest. The challenges map to real-world tasks such as handling inappropriate content, running code, retrieving information from the web, and extracting structured data. Builders can choose models for supervisor and sub-agents and add tools such as <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/memory.html" target="_blank" rel="noopener">AgentCore memory, a capability of Amazon Bedrock AgentCore</a>, and <a href="https://aws.amazon.com/lambda/lambda-functions/" target="_blank" rel="noopener">AWS Lambda Event Functions</a>. Builders use <a href="https://aws.amazon.com/bedrock/guardrails/" target="_blank" rel="noopener">Amazon Bedrock Guardrails</a> to apply safety controls to their agents.</li> <li><strong>Model customization challenge –</strong>&nbsp;Participants fine-tune models in <a href="https://aws.amazon.com/sagemaker/ai/studio/" target="_blank" rel="noopener">Amazon SageMaker Studio</a> using the latest training recipes. The challenge awards points when an automated evaluator rates a participant’s customized model as more accurate and comprehensive than a reference model on the specific tasks in the competition.</li> </ul> <p>Finalists are scored on time efficiency, accuracy, agent planning, and token consumption efficiency.</p> <div style="width: 810px" class="wp-caption alignnone"> <a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/03/ML-22161-1.png" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/03/ML-22161-1.png" alt="AWS AI League champion on stage at AWS re:Invent 2025" width="800"></a> <p class="wp-caption-text">Figure 1: AWS AI League champion at AWS re:Invent 2025</p> </div> <div style="width: 810px" class="wp-caption alignnone"> <a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/03/ML-22161-2.png" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/03/ML-22161-2.png" alt="2026 AWS AI League winner at the Cisco campus" width="800"></a> <p class="wp-caption-text">Figure 2: 2026 AWS AI League winner at Cisco campus</p> </div> <h1>The Cisco and AWS partnership</h1> <p>The AWS AI League story at Cisco grows out of a deep engineering partnership. Cisco and AWS bring together networking, cloud, security, and observability for shared customers, and many Cisco business units have chosen to build their next-generation applications natively on AWS. These include:</p> <ul> <li><strong>Cisco SD-WAN</strong>, whose controller architecture runs on AWS and serves customers globally as a software as a service (SaaS) application.</li> <li><strong>Cisco Meraki</strong>, <strong>Cisco Spaces</strong>, and Cisco’s IoT and smart buildings group.</li> <li><strong>Cisco Cloud Control</strong>, a cloud-native, AI-powered application integrated with AWS services that brings together security, networking, observability, and collaboration.</li> <li><strong>Cisco AI Defense</strong>, where Cisco

12

LangChain Raises $300M Series C at $3B Valuation

80

3 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

langchain, hwchase17 và 1 nguồn khác 1 bài viết · LangChain Blog, X
Biên tập tiếng Việt
Chi tiết nguồn

LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.

LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.

  • LangChain raises $300M Series C at a $3B valuation, led by CapitalG, to help every company own its intelligence with LangSmith, the agent engineering platform.
  • LangChain raises $300M Series C at a $3B valuation, led by CapitalG
  • to help every company own its intelligence with LangSmith, the agent engineering platform.
13

Keep inference running through regional capacity shortfalls with cross-Region inference routing in Amazon SageMaker AI

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Dmitry Soldatkin 1 bài viết · AWS Machine Learning Blog
Nguyên văn nguồn
Chi tiết nguồn

<p>Serving a model from more than one AWS Region is a well-established pattern for highly available inference: when one Region runs short of GPU capacity, requests move to another. The pattern is simple to describe and hard to operate. Until now, if you served models on Amazon SageMaker AI managed endpoints, cross-Region routing was a piece you still had to build yourself.</p> <p>Today, we’re introducing cross-Region inference routing in Amazon SageMaker AI. It uses a new resource, the inference router, that gives your application one invocation path across the endpoints and inference components you already run, in one or more AWS Regions and AWS accounts. You register the destinations that serve a model, and your application invokes the router instead of a specific endpoint. The router keeps requests in its own Region while the local destination is healthy, shifts new requests to another registered destination when it isn’t, and returns traffic gradually after recovery.</p> <p>In this post, we explain how cross-Region inference routing decides where each request runs, walk through an example with one model in two Regions, and cover monitoring, limits, and what you pay. For a cross-account deployment that serves several models, see <a href="https://aws.amazon.com/blogs/machine-learning/how-salesforce-is-advancing-global-scale-model-serving-with-cross-region-inference-routing-in-amazon-sagemaker-ai/">How Salesforce is advancing global-scale model serving with cross-Region inference routing in Amazon SageMaker AI</a>.</p> <h2 id="when-one-region-runs-short-of-capacity">When one Region runs short of capacity</h2> <p>A SageMaker AI endpoint runs in one AWS Region and one account. When autoscaling can’t add instances of the type your endpoint needs, requests throttle and time out, even when the same model has spare capacity in another Region. To use that capacity, your application must detect a struggling endpoint and switch Regions, decide which errors are safe to retry without running the model twice, move traffic back after recovery without flapping, and manage access to endpoints in other accounts. That code sits on the critical path of every request, and every team serving models across Regions maintains its own version of it.</p> <h2 id="how-cross-region-inference-routing-works">How cross-Region inference routing works</h2> <p>Cross-Region inference routing is based on a few core ideas:</p> <ul> <li><strong>You decide where your model might run –</strong> For each model, you choose which endpoints and inference components the router might use.</li> <li><strong>SageMaker AI decides which destination serves each request –</strong>&nbsp;The router prefers its own Region and shifts new requests to another destination only when the local one can’t serve reliably.</li> <li><strong>Your endpoints stay the same –</strong>&nbsp;You deploy endpoints as you do today, with the same models, configurations, instance pools, and autoscaling. Direct <code>InvokeEndpoint</code> calls keep working, and the router passes <code>InferenceId</code> and <code>CustomAttributes</code> through, as <code>InvokeEndpoint</code> does.</li> <li><strong>You can see every decision –</strong>&nbsp;Each real-time response tells you which destination served the request and why.</li> </ul> <p>A few terms describe the pieces:</p> <ul> <li><strong>Inference router</strong> – A Regional SageMaker AI resource in your account that your application invokes.</li> <li><strong>Routing target</strong> – A name for one logical model on a router, such as <code>fraud-model</code>. A router can hold many routing targets, and each fails over independently of the others.</li> <li><strong>Destination</strong> – A real-time endpoint, inference component, or asynchronous endpoint registered under a routing target, identified by its full Amazon Resource Name (ARN), which tells the router its Region and account. A routing target holds either real-time destinations, which can mix endpoints and inference components across Regions and accounts, or asynchronous endpoints only.</li> <li><strong>Local destination</strong> – A destination in the router’s Region, preferred while it’s healthy.</li> <li><strong>Routing reason</strong> – A value returned with each real-time response that explains where the request went and why.</li> </ul> <p>The Region you create the router in is its local Region. To prefer a different Region, create a router there. The router doesn’t create capacity, scale your endpoints, deploy models, or copy model artifacts and container images. Each destination must already be running in its Region.</p> <div style="width: 810px" class="wp-caption alignnone"> <a href="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/17/ML-22377-1-1.png" target="_blank" rel="noopener"><img src="https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/17/ML-22377-1-1.png" alt="Inference router architecture: a client invokes a router in Region A, which sends requests to a local destination and falls back to destinations in Region B in the same account and in another account" width="800"></a> <p class="wp-caption-text">Figure 1: Each request goes to a healthy destination, with the router preferring destinations in its own Region</p> </div> <h3 id="how-routing-decisions-are-made">How routing decisions are made</h3> <p>The router considers only destinations that are registered on the routing target and that it’s authorized to invoke. Among those, it prefers destinations in its own Region, and when more than one local destination is healthy, it spreads requests across them evenly. Requests leave the Region only when local destinations can’t serve reliably. To detect that, SageMaker AI calculates a health score for each destination from its recent requests, measured in the destination’s own Region. Server errors (5xx), throttles, and timeouts lower the score. Errors from the SageMaker AI plat

14

Protect agent tool calls with Skyflow and Amazon Bedrock AgentCore Gateway

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Joe McCarron 1 bài viết · AWS Machine Learning Blog
Nguyên văn nguồn
Chi tiết nguồn

<p>In this post, we show how <a href="https://www.skyflow.com/" target="_blank" rel="noopener">Skyflow</a> and Amazon Bedrock <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway.html" target="_blank" rel="noopener">AgentCore Gateway</a> keep sensitive data out of the tools your AI agents call, and out of the model context those tools feed. We add Skyflow Detect to Amazon Bedrock AgentCore Gateway as a request and response <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-interceptors.html" target="_blank" rel="noopener">interceptor</a>. The Skyflow interceptor de-identifies data before it reaches a tool, restores it before the agent reads the result, and replaces documents with clean copies before the agent opens them. Your agents and tools don’t change.</p> <p>Skyflow is available in AWS Marketplace, and the interceptor is open source on GitHub.</p> <h2 id="agents-act-through-tools-and-tools-move-data">Agents act through tools, and tools move data</h2> <p>Agents have moved from answering questions to taking action, and they take action through tools: Model Context Protocol (MCP) servers, SaaS APIs, document stores, and web search. Every agent tool call is a data flow. Most enterprise controls cover what goes into and comes out of the model. Far fewer cover what an agent sends to its tools or what those tools send back.</p> <p>That gap shows up in three ways:</p> <ul> <li><strong>Sensitive data leaves through tool arguments.</strong> The model writes the arguments from everything in its context, including details the tool doesn’t need. Ask an agent about a customer, and the customer’s name, account number, or email goes straight into a query to a third-party server. That server sits outside your AWS account and your compliance scope.</li> <li><strong>Sensitive data comes back in tool results.</strong> Scraped web pages, CRM records, and case notes land in the model’s context, memory, traces, and logs. This happens even when the task never needed them.</li> <li><strong>Documents bypass text inspection.</strong> Document tools such as Amazon Simple Storage Service (Amazon S3), Box, and Google Drive return a signed URL, not text. A filter that inspects strings sees a link and lets it through, and the agent then opens the original file.</li> </ul> <p>Patching each agent doesn’t scale across teams and frameworks, and it can’t reach third-party tools. The controls need to sit where every tool call passes, so authorization, content safety, and data protection apply the same way to every agent and tool.</p> <p>AgentCore Gateway is that place. It fronts every tool an agent uses, whatever framework or model the agent runs on. It does more than route that traffic. With AgentCore Gateway interceptors, you can run your own code, as an AWS Lambda function, on every call that passes through it. A request interceptor sees each call before it reaches a tool, and a response interceptor sees each result before it reaches the agent. Either one can inspect the payload, rewrite it, or block the call. That makes the gateway a natural place to add data protection alongside Policy and Guardrails. This single control, attached once, covers every agent and every tool behind the gateway, without any change to agent or tool code.</p> <h3 id="example-a-dispute-resolution-agent-at-a-large-european-bank">Example: A dispute-resolution agent at a large European bank</h3> <p>Consider a large European bank with retail and corporate banking operations and strict data-residency obligations. Its operations teams are adopting agents to investigate card disputes.</p> <p>An analyst asks the agent to look into a disputed transaction. The agent searches the web for the merchant, then pulls the dispute case note from Amazon S3 to summarize it. Without protection, three things happen:</p> <ul> <li>The model builds the search query from everything in context. The search provider receives ‘Mateo Jackson dispute AnyCompany Electronics London’. That’s the customer’s name, sent to a third party, for a search that only needed the merchant.</li> <li>Scraped merchant pages bring unrelated personal data into the model’s context.</li> <li>The agent reads the original case note, with the customer’s full name, email, phone number, and card details.</li> </ul> <p>With the Skyflow interceptor on the gateway, the same workflow plays out differently:</p> <ul> <li>The search provider receives ‘[NAME_AJbrIud] dispute AnyCompany Electronics London’, where [NAME_AJbrIud] is a reversible vault token. The merchant results come back the same, the provider never learns who the customer is, and the analyst still sees the real name in the agent’s answer.</li> <li>Web content reaches the model already de-identified.</li> <li>The agent only ever receives a link to a de-identified copy of the case note.</li> </ul> <h2 id="solution-overview">Solution overview</h2> <p>The Skyflow interceptor is a single AWS Lambda function attached to both of the AgentCore Gateway interception points:</p> <ul> <li><code>REQUEST</code> runs before the gateway calls a tool.</li> <li><code>RESPONSE</code> runs after the tool answers and before the agent sees the result.</li> </ul> <p>At each point, it calls Skyflow Detect to find sensitive entities such as names, email addresses, phone numbers, government IDs, card numbers, dates of birth, and locations. It replaces them with tokens, or restores the originals. Skyflow Vault stores the original values so authorized systems can reverse the tokens.</p> <p>The Skyflow gateway configuration decides, for each tool, which of three protection modes applies: Shield the tool, Shield the model, and Shield the document.</p> <table border="1px" width="100%" cellpadding="10px"> <tbody> <tr> <td><strong>Mode</strong></td> <td><strong>What happens</strong></td> <td><strong>Who sees real data</strong></td> <td><strong>How it works</strong></td> <td><strong>Typical use</strong></td> </tr> <tr> <

15

LangSmith Tool Gateway: Secure, governed tool use for agents

63

1 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

langchain 1 bài viết · LangChain Blog, X
Nguyên văn nguồn
Chi tiết nguồn

LangSmith Tool Gateway, now in Public Beta, handles credentials, identity, and access for every agent tool call, with policies, approvals, and traces.

17

b12549

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

github-actions[bot] 1 bài viết · ggml-org/llama.cpp releases
Nguyên văn nguồn
Chi tiết nguồn

<details open=""> <p>llama: fixes for Inkling 2 attention mask (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6428533227" data-permission-text="Title is private" data-url="https://github.com/ggml-org/llama.cpp/issues/32429" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/32429/hovercard" href="https://github.com/ggml-org/llama.cpp/pull/32429">#32429</a>)</p> <ul> <li>llama : give Inkling2 its own relative-position attention input</li> </ul> <p>The Inkling2 graph built its flash attention mask from the hybrid iswa<br> input and passed it to build_attn through a new kq_mask argument. That<br> argument let a caller pair its own dense mask with the kv_rows of<br> llm_graph_input_attn_kv_iswa, whose mask follows the per-sequence cell<br> lists whenever kv_rows is enabled.</p> <p>Add llm_graph_input_attn_rel_pos instead. It owns dense KQ masks and the<br> query-to-cell distances, fills both from the same cells, and its<br> build_attn overload adds the per-head bias to its own mask and never<br> passes kv_rows. The iswa build_attn is back to its previous signature;<br> its body moves to build_attn_iswa_impl, which both overloads call.</p> <p>Inkling2 now folds the per-query sink into the bias with and without<br> flash attention, so build_attn_mha no longer needs the per-query sink<br> path.</p> <p>Assisted-By: Claude Opus 5.5 <a href="mailto:noreply@anthropic.com">noreply@anthropic.com</a></p> <ul> <li>inkling2 : make the expert weight scale and final logit softcap optional</li> </ul> <p>Load both keys as optional and skip them when they are zero, as other<br> models do, instead of rejecting zero at load.</p> <p>Assisted-By: Claude Opus 5.5 <a href="mailto:noreply@anthropic.com">noreply@anthropic.com</a></p> <ul> <li>llama : build kv_rows masks for the hybrid iswa memory</li> </ul> <p>llm_graph_input_mem_hybrid_iswa checked its masks with<br> can_reuse_attn_mask, which expects kv_rows whenever they are enabled,<br> but built them dense. With a unified cache and flash attention the<br> check always failed, and hybrid iswa models (LFM2, LFM3, Inkling2)<br> never reused a graph. Build the masks with build_attn_inp_attn_mask,<br> like the plain iswa input.</p> <p>Assisted-By: Claude Opus 5.5 <a href="mailto:noreply@anthropic.com">noreply@anthropic.com</a></p> <ul> <li>llama : make the relative-position input a hybrid iswa input</li> </ul> <p>Address review: llm_graph_input_mem_hybrid_iswa_rel derives from<br> llm_graph_input_mem_hybrid_iswa and owns the attention and recurrent<br> inputs, so Inkling2 builds one memory input instead of two. Its<br> attention input is built with dense masks, can_reuse checks them as<br> dense, and its build_attn asserts that the mask has no kv_rows (TODO:<br> a kv_rows variant). build_attn_iswa_impl is now a static helper.</p> <p>Assisted-By: Claude Opus 5.5 <a href="mailto:noreply@anthropic.com">noreply@anthropic.com</a></p> <ul> <li>llama : compose the hybrid iswa rel input, format inkling2</li> </ul> <p>Address review: llm_graph_input_mem_hybrid_iswa_rel owns its attention<br> and recurrent inputs like the other composite inputs instead of deriving<br> from llm_graph_input_mem_hybrid_iswa.</p> <p>Format src/models/inkling2.cpp like the other model sources: grouped<br> and aligned key and tensor loading, descriptive per-layer names, blank<br> lines and section comments between the steps, and cb() names for the<br> intermediate tensors. The graph is unchanged.</p> <p>Assisted-By: Claude Opus 5.5 <a href="mailto:noreply@anthropic.com">noreply@anthropic.com</a></p> </details> <p><strong>Website:</strong></p> <ul> <li><a href="https://llama.app" rel="nofollow">https://llama.app</a></li> </ul> <p><strong>Attestations:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/attestations/69772952">https://github.com/ggml-org/llama.cpp/attestations/69772952</a></li> </ul> <p><strong>macOS/iOS:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-macos-arm64.tar.gz">macOS Apple Silicon (arm64)</a></li> <li>macOS Apple Silicon (arm64, KleidiAI enabled) <a href="https://github.com/ggml-org/llama.cpp/pull/23780" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/23780/hovercard">DISABLED</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-macos-x64.tar.gz">macOS Intel (x64)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-xcframework.zip">iOS XCFramework</a></li> </ul> <p><strong>Linux:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-x64.tar.gz">Ubuntu x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-arm64.tar.gz">Ubuntu arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-s390x.tar.gz">Ubuntu 24.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-26.04-s390x.tar.gz">Ubuntu 26.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-zdnn-s390x.tar.gz">Ubuntu 26.04 s390x (zDNN)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-vulkan-x64.tar.gz">Ubuntu x64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-vulkan-arm64.tar.gz">Ubuntu arm64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/llama-b12549-bin-ubuntu-cuda-12.8-x64.tar.gz">Ubuntu x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12549/cudart-llama-b12549-bin-ubuntu-cuda-12.8-x64.tar.gz">CUDA 12.8 libraries</a>

  • b12549 ggml-org/llama.cpp releases · 20 thg 11, 2026
18

b12548

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

github-actions[bot] 1 bài viết · ggml-org/llama.cpp releases
Nguyên văn nguồn
Chi tiết nguồn

<details open=""> <p>metal : fix the second argument of NSMakeRange (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6488409917" data-permission-text="Title is private" data-url="https://github.com/ggml-org/llama.cpp/issues/32602" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/32602/hovercard" href="https://github.com/ggml-org/llama.cpp/pull/32602">#32602</a>)</p> </details> <p><strong>Website:</strong></p> <ul> <li><a href="https://llama.app" rel="nofollow">https://llama.app</a></li> </ul> <p><strong>Attestations:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/attestations/69767057">https://github.com/ggml-org/llama.cpp/attestations/69767057</a></li> </ul> <p><strong>macOS/iOS:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-macos-arm64.tar.gz">macOS Apple Silicon (arm64)</a></li> <li>macOS Apple Silicon (arm64, KleidiAI enabled) <a href="https://github.com/ggml-org/llama.cpp/pull/23780" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/23780/hovercard">DISABLED</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-macos-x64.tar.gz">macOS Intel (x64)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-xcframework.zip">iOS XCFramework</a></li> </ul> <p><strong>Linux:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-x64.tar.gz">Ubuntu x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-arm64.tar.gz">Ubuntu arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-s390x.tar.gz">Ubuntu 24.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-26.04-s390x.tar.gz">Ubuntu 26.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-zdnn-s390x.tar.gz">Ubuntu 26.04 s390x (zDNN)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-vulkan-x64.tar.gz">Ubuntu x64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-vulkan-arm64.tar.gz">Ubuntu arm64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-cuda-12.8-x64.tar.gz">Ubuntu x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/cudart-llama-b12548-bin-ubuntu-cuda-12.8-x64.tar.gz">CUDA 12.8 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-cuda-13.5-x64.tar.gz">Ubuntu x64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/cudart-llama-b12548-bin-ubuntu-cuda-13.5-x64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-cuda-13.5-arm64.tar.gz">Ubuntu arm64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/cudart-llama-b12548-bin-ubuntu-cuda-13.5-arm64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-rocm-10.0-x64.tar.gz">Ubuntu x64 (ROCm 10.0)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-openvino-2026.4.1-x64.tar.gz">Ubuntu x64 (OpenVINO)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-sycl-fp32-x64.tar.gz">Ubuntu x64 (SYCL FP32)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-ubuntu-sycl-fp16-x64.tar.gz">Ubuntu x64 (SYCL FP16)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-linux-arm64-snapdragon.tar.gz">Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md">setup guide</a></li> </ul> <p><strong>Android:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-android-arm64.tar.gz">Android arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-android-arm64-snapdragon.tar.gz">Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md">setup guide</a></li> </ul> <p><strong>Windows:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-win-cpu-x64.zip">Windows x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-win-cpu-arm64.zip">Windows arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-win-opencl-adreno-arm64.zip">Windows arm64 (OpenCL Adreno)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-win-cuda-12.4-x64.zip">Windows x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/cudart-llama-bin-win-cuda-12.4-x64.zip">CUDA 12.4 DLLs</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-win-cuda-13.5-x64.zip">Windows x64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/cudart-llama-bin-win-cuda-13.5-x64.zip">CUDA 13.5 DLLs</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12548/llama-b12548-bin-win-cuda-13.5-arm

  • b12548 ggml-org/llama.cpp releases · 20 thg 11, 2026
19

Read the process and how we're thinking about it here: https://www.llamaindex.ai/blog/building-toward-a-perfect-document-parsing-benchmark?utm_source=socials&utm_medium=tw_channel&utm_campaign=blogpos

64

2 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

LlamaIndex, jerryjliu0 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Read the process and how we're thinking about it here: https://www.llamaindex.ai/blog/building-toward-a-perfect-document-parsing-benchmark?utm_source=socials&utm_medium=tw_channel&utm_campaign=blogpost&utm_content=blogperfectbenchmark

20

Claude solves two open problems in the physics of black holes

87

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 221 tương tác đã đo · Nguồn crawl

Handy-Man, cybermango 1 bài viết · HN: Claude, Anthropic Research (unofficial RSS mirror)
Nguyên văn nguồn
Chi tiết nguồn
1–20 / 203
Trang 1 / 11