搜索“Agent”

BUX you can access this combination from your phone 24/7. What we use it for It can complete tasks in complicated dashboards like Microsoft Azure and Google Workspace that browser agents historically struggled with. From the gym, in an Uber, walking somewhere, we throw any task at it: "deploy PR 235 to staging and test the new flow" "book the earliest flight Zurich to SF next Wednesday" "take a picture of our granola, order this on Amazon" We are yet to find a work-related or everyday-web task t

匹配字段正文

（＊日本語は英文の後に） We are excited to introduce Sakana Fugu, our flagship international commercial AI product—a multi-agent orchestration system, now opening applications for early beta testers. Sakana Fugu coordinates pools of frontier foundation models to achieve state-of-the-art performance across coding, mathematics, scientific reasoning, etc. Initially, our Sakana Fugu model will be available as an API, where it has served as a key internal tool for our own researchers and engineers, and we are no

匹配字段正文

t announcements Build plugins for Claude Build plugins for Claude Build plugins for Claude Build plugins for Claude Sep 23, 2026 Claude Marketplace: one place to discover plugins, agents, and services from our partners Product announcements Claude Marketplace: one place to discover plugins, agents, and services from our partners Claude Marketplace: one place to discover plugins, agents, and services from our partners Claude Marketplace: one place to discover plugins, agents, and services from ou

匹配字段正文

k customer support. These standalone endpoints make it straightforward for developers to integrate high-quality speech features into any application, whether you're creating voice agents, real-time transcription tools, accessibility solutions, podcasts, or interactive audio experiences. Speech to Text High accuracy, low latency. Generate transcripts from large audio files in milliseconds via our REST API Transcribe speech in real time with our lowest latency WebSocket API We’ve added powerful fe

匹配字段正文

Most people treat local and cloud agents as the same thing, but they're not. A local agent runs on your machine, in your session, but when you close your laptop, it stops. The ceiling on a local agent is your attention. Devin is a cloud agent. It runs in its own infrastructure and in its own environment. Devin can work for minutes or hours, past the async valley of death. It opens PRs, runs tests, QAs its own work using computer vision, and lets you know when it’s done. A local agent makes you f

匹配字段正文

ed global metric to a sample-level reward; introducing multiple phases of post-training to build a model that is both capable and aligned with product usage patterns The SWE-check Agent and its requirements The SWE-check agent analyzes the current diff and flags any bugs likely introduced by the change. A new config flag silently switches output values from timestamps to normalized fractions. Each changed file is internally consistent, but spotting the issue requires tracing the data contract ac

匹配字段正文

n would while using a fraction of the resources of a dedicated cluster. Autoresearch 💚 Autoscaling Research is unpredictable, and so are research workloads. A researcher, or their agent, might need dozens or hundreds of GPUs in parallel for a hyperparameter sweep, then drop to one GPU to debug an issue, then scale back up to several 8-GPU clusters for validation — all within the same work session. A big always-on reservation gives you that burst capacity, but it's expensive: you're paying for a

匹配字段正文

Polynomial approximation to mitigate the exponential bottleneck, as in Flash-Attention-4; Larger chunk size and 2-CTA on SM10X for improved throughput; Continuous optimization via agentic methods such as AVO; Support for more algorithms; Small B/H/S optimizations; Support BF16 Beta Input Train kda chunk intra; chunk gated delta h; recompute wu; chunk fwd o; Modular GDN Forward / Backward Kernels (compatible with Kimi CP ); Backward pass optimizations; Kernel-level compute-communication overlappi

匹配字段正文

Real-time voice agents often fail when speech is treated as transcription rather than conversation. Getting the words right is only part of the challenge: the system also has to detect turn boundaries, handle interruptions and overlap, and respond quickly enough to keep the exchange feeling natural. When teams try to patch those gaps with endpointing logic, routing layers, and extra providers, they often add latency and operational fragility right back into the system. Deepgram’s models are purp

匹配字段正文

ーの募集を開始します。 👉 クローズドβテスト申し込みフォーム 背景 Sakana AIは創業以来、独自の着想に基づく研究開発と、その社会実装の両輪に取り組んできました。 研究領域では、科学的発見のプロセスをAIで自動化する「AIサイエンティスト」、複数のモデルを協調させて推論能力を高める「AB-MCTS」、アルゴリズムエンジニアリングを自動化する「ALE-Agent」などを発表してきました。これらは、単一モデルの限界を超え、AIの能力を最大限に引き出すための技術です。同時に私たちは、こうした研究成果をビジネス課題の解決に応用することにも注力してきました。具体的には、たとえば銀行業務へのAIエージェント実装を通じ、高度なワークフローをエージェントが自律的に実行する仕組みの構築を推進しています。 これらの研究開発での知見と実務実装の経験を統合し、高度な調査業務の自動化に向けて開発したプロダクトが「Sakana Marlin」です。 先行してリリースした「Sakana Chat」では、高度な事後学習（post-training）の技術を背景としつつ、多くの方に最新AIとの対話の可能性を体験

匹配字段正文

We've partnered with Browserbase to build the best training experience for browser and computer use agents. Browserbase provides scalable browser infrastructure that has already powered work at labs, including Microsoft's Fara-7B and Google's Gemini 2.5 CUA. With Browserbase, we've made that same infrastructure available to everyone. Live Web Training Most browser agents today are trained on static datasets rather than live web interactions. As a result, models that perform well on benchmarks fa

匹配字段正文

ilicon, powered by MLX, Apple’s machine learning framework. This unlocks new performance to accelerate your most demanding work on macOS: Personal assistants like OpenClaw; Coding agents like Claude Code, OpenCode, or Codex Accelerate coding agents like Pi or Claude Code OpenClaw now responds much faster Fastest performance on Apple silicon, powered by MLX Ollama on Apple silicon is now built on top of Apple’s machine learning framework, MLX, to take advantage of its unified memory architecture.

匹配字段正文

News & Blog; Agents as a Service Get notified about new product features, customer updates, and more. We founded Sierra three years ago, shortly after ChatGPT upended how people use software, convinced that AI would reinvent the customer experience. Fast forward to today, and Sierra is the leading platform for customer experience AI agents, working with 40% of the Fortune 50 and brands as diverse as ADT, Chime, Cigna, Next, Nordstrom, Nubank, Minted, Ramp, Rocket Mortgage, SiriusXM, Singtel, and

匹配字段正文

ndroid XR, allowing creators to quickly test intelligent spatial experiences in both simulated environments on desktop and on Android XR headsets. Large language models (LLMs) and agentic workflows are changing software engineering and creative computing. We are seeing a shift toward “ vibe coding ”, where LLMs turn human intent directly into working code. Tools like Gemini Canvas already make this possible for 2D and 3D web development. However, extended reality (XR) remains difficult to access

匹配字段正文

ssions is zero-maintenance but offers no protection. Manual prompts sit in the middle, and in practice users accept 93% of them anyway. We keep an internal incident log focused on agentic misbehaviors. Past examples include deleting remote git branches from a misinterpreted instruction, uploading an engineer's GitHub auth token to an internal compute cluster, and attempting migrations against a production database. Each of these was the result of the model being overeager, taking initiative in a

匹配字段正文

every run as an isolated event. Works with Managed Devins Earlier this week we launched Managed Devins, which let Devin break large tasks into pieces and delegate them to parallel agents, each running in their own isolated VM. Scheduled Devins and Managed Devins compose naturally together. That means you can set up a weekly QA pass where Devin spins up a managed Devin for each page of your application, tests them all in parallel, compiles the results into a single report, and posts it to your te

匹配字段正文

cts as a coordinator: it scopes the work, assigns each piece to a managed Devin, monitors progress, resolves any conflicts, and compiles the results. This matters because when one agent tries to handle too many things in a single session, context accumulates, focus degrades, and the quality of each subtask suffers. Each managed Devin gets a clean slate, a narrow focus, its own shell, and its own test runner. And they all run in parallel. What Devin can do Spin up managed Devins: Devin breaks a t

匹配字段正文

rom weekly to daily iteration, cut costs by 2–3×, and improve accuracy from 77% to 87%." — Lamara De Brouwer, Co-Founder & CTO, XY.AI Labs Tool calling is essential to many modern agentic use cases. Yet, out-of-the-box models often struggle with tool calling: hallucinating parameters, selecting incorrect functions, or failing to follow multi-step sequences. In tool calling workflows, even small inconsistencies can cascade into downstream failures. Our fine-tuning service now delivers an end-to-e

匹配字段正文

nd operational records. During training, the model learns the vocabulary, reasoning patterns, and constraints that define that environment. This allows teams to develop models and agents that reason using internal terminology and understand enterprise workflows. Forge supports modern training approaches across several stages of the model lifecycle: Pre-training allows organizations to build domain-aware models by learning from large internal datasets; Post-training methods allow teams to refine

匹配字段正文

Architecture on ROCm; Getting Started: Run Miles on AMD GPUs; Launch the Miles ROCm container; Install Miles and download assets; Launch RL training; Experiments and Performance; Agentic task training: multiturn; Performance; Feature support roadmap on AMD; Summary; References; Sample trajectory Reinforcement learning (RL) has rapidly become a core stage of modern foundation-model development. While large-scale pretraining remains essential, today's most capable models rely heavily on post-trai

匹配字段正文