AI/ML news, top picks, and generated innovation digests.
8391 matching items
The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. [...] Maybe the idealized form of MCP is just an auth gateway for the API and nothing else. That’d still be a win. — Sean Lynch , comment on Hacker News Tags: model-context-protocol , llms , ai , generative-ai , skills
By Adam Wolf Running production LLM inference on a new accelerator family is a layered problem. The model matters. The runtime that exists for the GPU you have matters at least as much. So does the precision mode that works without losing accuracy, the inference engine that hits your throughput targets, and the secure endpoint […]
Appearing at the Big Technology AI Summit Thursday, OpenAI president Greg Brockman indicated that winning the compute race could be the key to winning more broadly.
Large language models have moved out of the research lab and into engineers’ daily workflow. LLMs serve as reasoning engines that can orchestrate complex tasks including identifying vulnerabilities in source code and transforming fragmented project discussions into rigorous technical specifications. While the general public uses AI tools to write email and plan vacations, technical professionals use LLMs as core architectural elements that are fundamentally changing how digital infrastructures are built and maintained. As the AI models move into mainstream engineering practice, the demand for technical expertise is rising. The LLM technology market is expected to grow by about 33 percent every year through 2030 , according to MarketsandMarkets . The rapid expansion suggests that proficiency in implementing and securing the models is transitioning from a niche into a core requirement for technologists. More than just a better search engine To use LLMs effectively, technical professionals must move beyond treating them as conversational robots. At a fundamental level, the AI systems are built on the transformer architecture , a framework that replaced the older method of processing data in a fixed, sequential order. Unlike earlier models that analyzed information one step at a time, transformers use self-attention mechanisms to ingest vast datasets simultaneously. For technical professionals, LLMs are core architectural elements that are fundamentally changing how digital infr…
Qubot, our internal Copilot-powered analytics agent, allows any GitHub employee to ask questions about our data in plain language. Here's what we learned as we built it. The post How we built an internal data analytics agent appeared first on The GitHub Blog .
ML system design interviews test how well you can think beyond models. In these interviews, choosing an algorithm is only one part of the answer. You also need to explain how data is collected, how features are created, how predictions are served, and how the system improves over time. Most real ML systems are built […] The post System Design for ML Interviews: 10 Real Problems Walked Through appeared first on Analytics Vidhya .
Web Search on Amazon Bedrock AgentCore is now generally available. In this post, we walk through what makes Web Search on Amazon Bedrock AgentCore different, why it matters, and how to wire it in with a few lines of code.
❤️ Check out Weights & Biases and sign up for a free demo here: https://wandb.me/papers 📝 The paper is available here: https://recursivemas.github.io/ https://github.com/RecursiveMAS/RecursiveMAS Brain reading video: https://www.youtube.com/watch?v=IUg-t609byg 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Adam Bridges, Benji Rabhan, B Shang, Cameron Navor, Charles Ian Norman Venn, Christian Ahlin, Eric T, Fred R, Gordon Child, Juan Benet, Michael Tedder, Owen Skarpness, Richard Sundvall, Ryan Stankye, Shawn Becker, Steef, Taras Bobrovytsky, Tazaur Sagenclaw, Tybie Fitzhugh, Ueli Gallizzi
This post shows how to enable Adobe Marketing Agent for Amazon Quick using a Model Context Protocol (MCP). We walk you through how to configure the integration, authenticate using your Adobe credentials, and get the latest insights in Amazon Quick. The sample workflow returns audience rankings, loyalty segment summaries, journey usage, and conflict recommendations.
SAP and Google Cloud are deploying agentic commerce architecture to automate multi-agent marketing and retail operations at enterprise scale. SAP research indicates 78 percent of businesses consider AI essential for retaining customers in 2026. However, the same data reveals fewer than two in five companies share customer data across customer experience (37%) or CRM (39%) […] The post SAP and Google Cloud deploy agentic commerce architecture appeared first on AI News .
Token spend does not prove AI is creating value. Teams need cost-per-outcome metrics that connect AI usage to resolved tickets, accepted code, shipped features, and other business results. The post Why AI token costs don’t tell you if your AI is working appeared first on Arize AI .
Designing contract-bound AI agents for high-stakes execution.
I am building a production-grade recommendation system for a short-video platform (processing around 50k videos). The architecture utilizes a vector database ( Qdrant ) to store and query 768-dimensional video embeddings generated by a VideoCLIP model. To track user preferences in real-time, I implement an online learning mechanism that updates a single user_vector iteratively after each interaction based on a computed rating (bounded between [-1.0, 1.0] via tanh ). The Goal & The Problem I want my system to actively update the user vector on both positive and negative signals . Initially, I tried a standard linear combination: updated_vector = (alpha * u) + (beta * v * rating) Where u is the current user vector, v is the video vector, alpha is the decay, and beta is the learning rate. However, when a user gives a negative rating (e.g., -0.8 ), multiplying the VideoCLIP embedding by a negative scalar flips its direction entirely. In a 768-d multimodal space, adding this inverted vector creates massive noise across unrelated dimensions, causing aggressive vector drift instead of just moving away from that specific topic. On the other hand, simply clamping negative ratings to 0 fixes the geometry but creates a severe feedback loop/frozen vector issue where the profile stops evolving during consecutive negative interactions. What I Want to Achieve I need a mathematically sound way to update the vector during negative interactions so that the user profile actively flees from the…
In healthcare settings where patients use LLMs as a medical assistant, LLM performance differs between evaluation and deployment. (a) Bean et al. (2025) find a 61 percentage point difference between evaluation and deployment. (b) We argue this gap arises not from poorly designed benchmarks, but from implicit assumptions embedded in evaluation protocols that fail to hold at deployment. (c) We propose a taxonomy that categorizes assumptions into two types, task and outcome, to diagnose where the gap arises and what is required to close it. Closing the gap requires making assumptions explicit, testing which assumptions hold, and updating evaluation protocols accordingly. Healthcare LLM benchmarks are one of the main paradigms by which LLMs are evaluated prior to clinical settings. Benchmarks provide a stable goalpost that allow researchers to iterate quickly and measure progress consistently. However, in high-stakes domains like healthcare, that same abstraction becomes a liability. For example, a recent study found a 61 percentage point drop in accuracy when going from evaluation to deployment (see Figure). In this setting, patients use LLMs as a medical assistant to better understand their symptoms, identify the underlying condition, and take appropriate actions. Moreover, the results showed that patients given access to a […]
This post was originally an op-ed co-authored with Kevin Xu of Interconnected for a general, non-technical audience.
The moment an agent needs to deploy something, it slams face-first into a wall built for humans. Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds.
The Dutch East India company was among the first modern companies to receive legal personhood. Should we reconsider what personhood means in the age of AI?
“My ‘Skill’ is uploaded; my cubicle has been emptied.”
The Advisory Forum (the Forum) is a general advisory body to the European Commission and the AI Board, established to provide technical expertise, advise them, and to contribute to their tasks under the EU AI Act. It sits within the Act’s broader governance architecture, as one of the two advisory bodies, in addition to the […]
PLUS: A reasoning model helped doctors surface 18 confirmed rare-disease diagnoses.
In 2018, Amazon brought me in as the lead UX Sound Designer for Astro, its first consumer home robot . Astro used cameras and other sensors to map and navigate your home and workplace , and could proactively patrol, check up on loved ones, and transport small items using its built-in cargo bin. While there was a well-defined feature set and form factor, initially there was no character direction. In fact, even before Astro had a name, there were two main questions—was it simply Alexa on wheels, or was it a robot with its own character? The Astro team was divided. One option was to focus on Alexa, and treat the mobile robot simply as an added utility. Along with the majority of the UX team, I argued for Astro to not focus on Alexa. Our belief was that a thing that moves through your home and turns toward you with intent can never be just an appliance. People would ascribe character to it whether we wanted them to or not, and so the only question was whether we shaped that character or let it happen by accident. Ultimately, Astro became Astro rather than Alexa , and user testing backed up our decision. People didn’t see the robot as Alexa. They saw it as its own character, and that’s what they wanted it to be. Alexa on the device felt somewhat strange and creepy, but building Astro its own voice was too slow and expensive in 2018. So, we settled on Alexa as a supporting character that handled any actual talking, while Astro was the main character, communicating as much as it c…
Built around digital twin technology and customer-dedicated AI models, Cumulo answers the recent announcement by GCHQ for AI Cyber Shield, enabling early identification of threats and vulnerabilities before incidents occur Abingdon, U.K., 19 June, – SOC-as-a-service provider, e2e-assure, today announced the launch of the updated Cumulo, the U.K.’s only sovereign, AI-first, IT/OT connected SOC platform, designed to help organisations defend […] The post e2e-assure introduces Cumulo, the U.K.’s only sovereign, AI-driven, zero-day SOC platform to secure IT and OT environments appeared first on AI News .
Ryan welcomes Cricket Liu, DNS expert and Chief Evangelist at Infoblox, to the show to talk all things DNS. They cover the evolution of one of the oldest DNS server implementations, BIND, and what the future holds for protected DNS configurations; the realities of security threats like DDoS and DNS spoofing; and why outages often trace back to a lack of understanding of DNS’s fundamental role.…
I made a machine learning computer vision model trained it on a known dataset now i want to test that model performance over my dataset how to do that. I am open to suggestions and best practices please give me detailed workflow . I'd really appreciate your help . Also feel free to share references links , YouTube links etc . I'd like to mention that my model is a mix of 5 pre existing model trained on a high standard data. Hope it has learned good enough are there other ways of knowing that apart from standard metric scores.
With GLM-5.2 passing everyone's vibe check, the open models story finally becomes a real frontier story.
Weekly News Digest...
The plan was unveiled Wednesday, in a response to a question posed by metropolitan assembly member Toshimitsu Tamura of the Liberal Democratic Party during an assembly session.
The post AI cites a hospital for health advice, but the hospital uses AI to write the advice. And both are wrong appeared first on The Ken .
Why we're all-in on speculative decoding.
This is 100 Years From Now. Once a week we skip a century and try to picture what life actually looks like when the stuff we're building now has had time to settle in. This week: the war that won't have a country in it.
Today we launched a new plugin for Datasette, datasette-apps , with this launch announcement post on the Datasette project blog. That post has the what , but I'm going to expand on that a little bit here to provide the why . The TL;DR Datasette Apps are self-contained HTML+JavaScript applications that run in a tightly constrained sandbox hosted on your Datasette application. They can use JavaScript to run read-only SQL queries against data in Datasette, and can run write queries too if you configure them with some stored queries . Here's a very simple example and a more complex custom timeline example - the latter looks like this: Apps are allowed to run JavaScript and render HTML and CSS. They are limited in terms of access - the they run in prevents them from accessing cookies or localStorage and they also have an injected CSP header (thanks to this research ) which prevents them from making HTTP requests to outside hosts, preventing a malicious or buggy app from exfiltrating private data. Datasette Apps started out as my attempt at building a Claude Artifacts mechanism for Datasette Agent , but I quickly realised that the sandboxed pattern is interesting for way more than just adding custom apps in a chat interface and promoted it to its own top-level concept within the Datasette ecosystem. They're also a fun way to turn my multi-year experiment in vibe-coded HTML tools into a core feature of my main project! You can try out Datasette Apps by signing in with GitHub to the…
Amazon SageMaker AI provides fully managed real-time inference hosting for machine learning models. You deploy a model to a SageMaker endpoint backed by one or more compute instances, and SageMaker handles provisioning and scaling. SageMaker supports multiple endpoint architectures. This post focuses on the two most relevant to generative AI workloads with detailed observability: Single-model endpoints (SME) and Inference component (IC) endpoints.
Recentemente a Agência Nacional de Proteção de Dados abriu tomada de subsídios para dois temas centrais do ECA Digital: Mecanismos de Aferição Etária e Fornecedores de Produtos ou Serviços de Tecnologia da Informação. Mas o que exatamente a ANPD está propondo para nesses temas? O post Escopo e aferição de idade: entenda as propostas de Guias da ANPD! apareceu primeiro em Data Privacy Brasil Research .
An AI engineering agent built into Phoenix. It works like a coding agent, just point it at your telemetry instead of a source tree. The post Meet PXI: the AI engineering agent inside Phoenix appeared first on Arize AI .
Learn how self-hosted inference caching works in Roboflow Workflows and how to force a deployment refresh.
In a consequential grid infrastructure decision, the Federal Energy Regulatory Commission (FERC) today issued a major milestone on large-load interconnection impacting how those building AI factories, semiconductor fabrication support systems and advanced manufacturing facilities can connect to the grid. In the era of AI, which NVIDIA founder and CEO Jensen Huang has described as a […]
El lanzamiento de LatamGPT, un sistema de procesamiento de lenguaje natural hecho por y para América Latina nos lleva a analizar dónde estamos y qué pasos debemos priorizar en esta región en cuanto a innovación técnica. The post La receta para una inteligencia artificial con sabor latinoamericano appeared first on Access Now .
Health is one of the most meaningful ways people use ChatGPT. Every week, more than 230 million people turn to ChatGPT for help with health and wellness questions: making sense of health information, understanding lab results, preparing for appointments, navigating insurance, building healthier habits, and figuring out what to ask next. With GPT‑5.5 Instant, we’re seeing a substantial step forward in health, with improvements in recognizing when urgent care may be needed, asking for relevant context, explaining uncertainty, and making complex information easier to understand. On our most challenging health evaluations, GPT‑5.5 Instant now performs at a level comparable to our frontier Thinking models. Because it is available to all free users in ChatGPT, more people can benefit from these improvements. That progress reflects both advances in model capabilities and the physician-led work behind our health evaluations. Across our efforts, a global network of physicians helps define what “good” looks like in real-world health situations by reviewing example model responses, describing ideal behavior, and identifying failure modes. Working with physicians gives us a way to measure progress in health and improve how ChatGPT responds over time. Learn more: https://openai.com/index/improving-health-intelligence-in-chatgpt/
Release: datasette-acl 0.6a0 This release expands datasette-acl from table-only permissions toward a general resource-sharing system. Alex Garcia did most of the work for this release - we're fleshing out the plugin that will allow multi-user Datasette instances finely grained control over who can access which resources within Datasette. Tags: datasette , alex-garcia
Show Codex a workflow once. Reuse it as a skill. Record & Replay lets you show Codex a recurring task, like filing an expense report or submitting a time-off request. Codex turns that demo into an inspectable, editable skill. You control when recording starts and stops.
Evaluate off-the-shelf vs. custom computer vision models. When to use each. Learn how fine-tuning RF-DETR bridges the gap to factory production.
We break down the technical architecture behind our multi-stage vulnerability discovery harness and automated triage loop. Learn how we manage state controls, squash false positives through adversarial review, and route around LLM context limits.
We talk about how this legendary investor went from humble beginnings in Singapore to leading rounds in Anthropic, Mistral, Black Forest Labs, and Periodic Labs... and the AMP secret master plan!
OpenAI introduces new spend controls and usage analytics for ChatGPT Enterprise, helping organizations manage costs and scale AI with confidence.
GDM has published an AI Control Roadmap ! From the executive summary: We present the GDM AI Control Roadmap (v0.1) – our plan for implementing and adopting internal guardrails designed to catch potential adversarial behaviour by AI agents, even as they become increasingly harder to oversee and contain. We focus on system-level mitigations that limit the harm a misaligned AI system could cause. Specifically, this report provides: • Threat modelling : Taking inspiration from cybersecurity, we adopt a conservative, worst-case approach to threat modelling throughout this paper, and assume a hypothetical AI adversary pursuing undesirable goals in internal deployment. We introduce TRAIT&R, a taxonomy of tactics and techniques available to such a hypothetical AI adversary, building on the established security framework MITRE ATT&CK. We categorise new hypothetical threats into three core areas: loss of control (e.g., rogue internal deployments), work sabotage (e.g., intentionally flawed alignment and safety research), and direct harm (e.g., critical asset destruction or exfiltration). • Control invariants : We establish two defensive invariants that we aim to maintain, even as the hypothetical AI adversary becomes increasingly capable: i) reliable detection of misaligned intent or actions, and ii) effective prevention and response to attack attempts. For control to serve as an effective line of defence, our ability to detect and prevent attacks should exceed AI agents’ ability to ev…