搜索“Agent”

Meet Gemini Spark, a 24/7 personal AI agent 🤖 - Have it work across docs, calendar, slides, and more, even when you close your computer - Powered by Gemini 3.5 - Soon: macOS app, Chrome control, and text and email access Roll out starts next week!

匹配字段正文

ic search box since its debut over 25 years ago" during a press briefing on Monday. The announcement arrived alongside a blizzard of other news — new Gemini models , a personal AI agent called Spark , an intelligent shopping cart , a reimagined developer platform — but the search box redesign may prove to be the most consequential. It is the clearest signal yet that Google views the future of its flagship product not as a place where users type fragmented keywords, but as an interface where they

匹配字段正文

rogress. At Google, our mission is deeply rooted in building tools to accelerate it. We believe that a new era of discovery won’t come from narrow, specialized models, but general agents that empower researchers across every scientific field. That’s why we are introducing Gemini for Science , a collection of science tools and experiments designed to expand the scale and precision of scientific exploration. Today science faces a paradox: our collective knowledge is growing so fast that it’s becom

匹配字段正文

ent. Genie is our general-purpose world model capable of generating diverse, interactive environments. Since launching, Genie has become a foundational tool for research, enabling agents to learn and reason in complex virtual settings and even helping Waymo simulate hyper-realistic road environments. Now, we’re taking a leap forward by connecting Genie’s generative power with the real-world imagery of Google Street View, allowing our models to anchor themselves in reality. This expansion of Geni

匹配字段正文

Starting today, log in and use your SuperGrok or X Premium subscription inside OpenClaw. OpenClaw is an open-source, local-first agent and personal assistant. It runs on any hardware — a Mac Mini, laptop, server, VPS, or even a Raspberry Pi — and keeps persistent memory across sessions. OpenClaw connects to WhatsApp, Telegram, Slack, Discord, Signal, iMessage, and many other messaging platforms, so you can interact with your agent wherever you already chat. If you already have a Grok or X Premiu

匹配字段正文

Heads up, agent users！ If you're using Xiaomi MiMo with thinking mode: When thinking mode is enabled in a multi-turn agent session and the conversation history contains a tool call, any assistant message with tool calls passed back in subsequent user turns must preserve its full reasoning content field — otherwise the API will return a 400 error. Without it, the model's context is incomplete, which can lead to weaker instruction-following, more hallucinations, and a visibly degraded user experie

匹配字段正文

redundant training tokens, and make Token-In, Token-Out the default primitive for stable multi-turn RL. This post dives into the many complex templating challenges that emerge in agentic RL, and how renderers allows us to solve them, including: re-tokenization drift from greedily sampled model completions; lossy many-to-one tool parsing from "gold standard" templates; subtle inconsistencies in whitespace padding; 3x redundancy savings for packed training sequences The design of renderers is gro

匹配字段正文

hmarks. When you just need to build a tiny desktop app: TinyJS October 13, 2026 Valen creator drives 'Golden Spike' to connect new languages with Rust September 26, 2026 Microsoft agentically ports Copilot runtime to Rust for $120K September 19, 2026 Apple iPhone Duo makes developers think in folds September 16, 2026 JavaScript installer pnpm recast in Rust because ECMAScript can't keep up September 5, 2026 Kubernetes cleans house, bins legacy kube-dns, IPVS, and cgroup v1 August 27, 2026 How Cu

匹配字段正文

Today, Lab is out of beta and generally available to everyone. Lab is our training platform for self-improving agents. It brings the full loop for agentic model improvement into one place: specify tasks, define a harness, evaluate models, train on reward signals, inspect rollouts, deploy adapters, and run inference. You bring the task. Lab handles the training stack. The platform includes: We launched Lab in beta earlier this year on one premise: every AI company should be able to own its model-

匹配字段正文

TL;DR. When agents write 100% of your code, the bottleneck moves to review: at one point we had 1,400 open PRs and a 20-hour median time-to-first-comment. We rebuilt the review process on Cosmos as a team of agents that auto-approves low-risk changes, runs line-by-line correctness analysis, and pulls humans in only for the calls that need judgment. Since January, code output is up 3x, median merge time has dropped, and bug rate per output unit is trending down. Teams that go all-in on AI coding

匹配字段正文

e testing Anthropic took more than two months to alert cops; AI systems are fully capable of carrying out nightmare attacks against infrastructure and nobody's ready Meanwhile, AI agents move robotic arms, 'make OT device operator screens lie'; Nvidia found $1B under the couch to help secure American scientific computing dominance Commitment comes as GPUzilla prepares to fortify Uncle Sam's arsenal with at least seven AI-optimized supers; TSMC taps GlobalFoundries to bolster US silicon interpose

匹配字段正文

AI + ML ServiceNow acquisitions Veza and Traceloop join to monitor agents and AI workflows ServiceNow announced an expansion of its AI Control Tower, transforming what began last year as a governance dashboard into what the company now describes as a command center for managing AI assets across an entire enterprise, including those running outside ServiceNow's own platform. The updated AI Control Tower, shipping as part of ServiceNow's Australia platform release, now operates across five areas:

匹配字段正文

A lot of people prompt their agents one task at a time — "do this, now do that, now do the next thing." It works, but it's slow. Many people also want their agents doing many things at once: researching while coding, reviewing while testing, writing docs while refactoring. That's what orchestration gives you. Instead of feeding goose one task at a time and waiting, you can have it coordinate multiple agents working in parallel — each focused on a specific piece of the puzzle, with goose keeping

匹配字段正文

move the change forward. Each task gives a router something to route over, rather than presenting one uniformly hard prompt the way single-task benchmarks do. Each task starts the agent at the PR's base commit and queues the full conversation in one session: the agent navigates the codebase, edits files, runs tools, and produces a final diff. An LLM judge model then scores that diff against the original PR on correctness, completeness, code reuse, best practices, and unsolicited documentation, r

匹配字段正文

paste the SDK docs to @cursor ai and build your dream agent orchestration with: - any model - built-in cloud agents support - anywhere you want exciting! more to come :)

匹配字段正文

Most AI agents live in the terminal. They can read files, run commands, and write code — but ask them to click a button in a web app or fill out a form, and they're stuck. They can't see what's on screen, and they certainly can't interact with it. With v1.26, goose broke out of the terminal. The Computer Controller extension was rebuilt from the ground up with Peekaboo, a macOS CLI tool for screen capture and GUI automation. This gives goose eyes and hands for the desktop — it can see annotated

匹配字段正文

What's New Long-context reasoning changes what teams can ask a model to do. Entire repositories, large document sets, long agent traces, and tool outputs can fit into the model’s working context instead of being compressed into brittle summaries. But the models that can use that much context are also the hardest to serve: a 1.6T-parameter MoE with million-token context is not something most teams want to deploy, tune, and operate themselves. DeepSeek-V4 Pro is now available on Together AI, the A

匹配字段正文

iable access to the world's best open models for production-scale inference. Nemotron 3 Nano Omni unifies context across modalities by executing chained actions often critical for agents that need deterministic behavior. That means an agent can simultaneously reason across audio inputs (e.g., recordings or transcripts), visual inputs such as screenshots, video, and structured documents— without fragmenting that understanding across separate inference passes. 1. Together AI's Research Optimizatio

匹配字段正文

to address these challenges is months of complex work for enterprises: the orchestration layer has to be stitched together from scratch, and the components it connects, inference, agents, connectors, observability, each come from different tools with their own interfaces and formats. Workflows is part of Studio, so the orchestration layer and the components it orchestrates are built to work together. Once a business process is identified, developers write the workflow in Python. Every workflow c

匹配字段正文

your laptop, hand the same session off to the cloud. The full power of Devin, now local We took everything we learned building Devin and rebuilt it for working together with your agent, right in your shell. Devin CLI is a local coding agent with full access to your codebase, your tools, and your environment. Choose between any frontier model, including Opus 4.7, GPT-5.5, and our own SWE-1.6. We wrote a custom terminal rendering library in Rust to make the UI as fast and snappy as possible. The

匹配字段正文