搜索“Agent”

to most effectively structure your prompt, use tools, and layer on compaction. It is often said in engineering that "cache rules everything around me", and the same rule holds for agents. Long running agentic products like Claude Code are made feasible by prompt caching which allows us to reuse computation from previous roundtrips and significantly decrease latency and cost. At Claude Code, we build our entire harness around prompt caching. A high prompt cache hit rate decreases costs and helps

匹配字段正文

Learn how the Claude Code team designs, tests, and evolves tools by thinking from the model's point of view. One of the hardest parts about building an agent harness is constructing its tools. So how do you design your agents' tools? Do you give it one general-purpose tool like bash or code execution? Or fifty specialized tools, one for each use case? To put yourself in the mind of the model, imagine being given a difficult math problem. What tools would you want in order to solve it? It would d

匹配字段正文

d designs, and getting it to build complete applications without human intervention. This work originated with earlier efforts on our frontend design skill and long-running coding agent harness , where my colleagues and I were able to improve Claude’s performance well above baseline through prompt engineering and harness design—but both eventually hit ceilings. To break through, I sought out novel AI engineering approaches that held across two quite different domains, one defined by subjective t

匹配字段正文

d architectures are still a novelty, and the main selling point is mainly (long-context) efficiency versus just modeling performance. Hence, I think they are a great candidate for agent contexts (like OpenClaw). Personally, I think the problem with hybrid architectures is also that the inference stacks are not quite as optimized, yet, and I find that I get better tok/sec throughput when running LLMs locally using more classic setups like GPT-OSS with grouped-query attention. Anyways, I am curiou

匹配字段正文

man deliverables, which often leave much more informative first impressions). The rest of the post remains the same as it was on March 3 2026. Summary: Opus 4.6 can, with a simple agent scaffold, create mostly-playable but somewhat broken CLI versions of Slay the Spire and Balatro1. Intro Last weekend I was trying to think of really difficult tasks we could give to AI agents to upper-bound their capabilities. I thought of two examples: Recreating a basic version of the video game Slay the Spire

匹配字段正文

sign, but requires you to build inside its component framework. We needed determinism from the outside, applied to arbitrary web content. Second, our videos are generated by an AI agent. Constraining the agent to Remotion's component model would mean teaching it one library's idioms instead of letting it use the entire web platform. The less framework surface area the agent has to reason about, the better the output. So: no special framework. No library buy-in. Just a URL. This meant building th

匹配字段正文

never released as an open-weight model.) The obligatory benchmark overview shows that Qwen3.5 exceeds the previous Qwen3-Max model across the board, with a much stronger focus on agentic terminal coding applications (the main theme this year). Qwen3.5 appears to be roughly on par with GLM-5 and MiniMax M2.5 in terms of pure agentic coding performance (e.g., SWE-Bench Verified). Since the Qwen team likes to release a separate coding model (e.g., see Qwen3-Coder-Next, which we discussed previousl

匹配字段正文

ywhere. After configuring, make sure you select Finished to save your desired configuration. Selecting a model Ollama shows a model selector with recommended and available models. Agents work best with at least 64k context length. Ollama’s cloud models have full context length, which provide the best experience with agents like OpenClaw. Cloud models: Local models (requires GPU VRAM): Running securely OpenClaw has the ability to read files and execute actions when tools are enabled. Ensure that

匹配字段正文

Ramp uses Modal to power Ramp Inspect, an internal background coding agent that now writes over half of all merged pull requests at Ramp. Leveraging Modal Sandboxes, Ramp spins up full development environments in seconds, giving every builder at the company access to what is effectively unlimited parallel engineering capacity grounded by Ramp’s internal codebase, enterprise context, and developer tooling. The idea: A coding agent as fast as local, accessible to everyone Ramp's AI team saw an opp

匹配字段正文

ago, for the vast majority of people, “using AI” meant talking to a chatbot in a back-and-forth conversation. But over the past few months, it has become practical to use AI as an agent: you can assign them to a task and they do them, using tools as appropriate. Because of this change, you have to consider three things when deciding what AI to use: Models, Apps, and Harnesses. The exact same model, Claude Opus 4.6, asked the exact same question, “Compare ChatGPT and Claude and Gemini” in three d

匹配字段正文

Written by Nicholas Carlini, a researcher on our Safeguards team. I've been experimenting with a new approach to supervising language models that we’re calling "agent teams." With agent teams, multiple Claude instances work in parallel on a shared codebase without active human intervention. This approach dramatically expands the scope of what's achievable with LLM agents. To stress test it, I tasked 16 agents with writing a Rust-based C compiler, from scratch, capable of compiling the Linux kern

匹配字段正文

aluations 100 hard browser tasks, one leaderboard; The judge; Results; Why Cloud scores higher; Using the benchmark 100 hard browser tasks, one leaderboard To truly understand our agent performance, we built a suite of internal tools for evaluating our agent in a standardized and repeatable way so we can compare versions and models and continuously improve. We take evaluations seriously. As of now, we have over 600,000 tasks run in testing. This is our first open source benchmark. BU Bench V1: 1

匹配字段正文

Introduction Good evaluations help teams ship AI agents more confidently. Without them, it’s easy to get stuck in reactive loops—catching issues only in production, where fixing one failure creates others. Evals make problems and behavioral changes visible before they affect users, and their value compounds over the lifecycle of an agent. As we described in Building effective agents , agents operate over many turns: calling tools, modifying state, and adapting based on intermediate results. Thes

匹配字段正文

h V2, it achieves gold-level performance on math benchmarks. However, the model is also trained with tool-use in mind and also performs well on other tasks, for instance, code and agentic tasks. At the same time, the DeepSeek team writes about computational efficiency as a big, motivating factor. That’s why they use the Multi-Head Latent Attention (MLA) mechanism from V2 and V3 together with the DeepSeek Sparse Attention (DSA) mechanism, which they added in V3.2. In fact, the paper says that “De

匹配字段正文

ugs in August before. Unfortunately, Google’s latest Antigravity IDE is vulnerable to many of the same issues as Windsurf, with disclosures going back to May 2025. Overall, coding agents are a game changer, but we also have to take security seriously. There are currently other, more mature, coding agents out there with better security and patch history, including Claude Code, GitHub Copilot, Cursor, Codex, Google’s own Gemini CLI,… and some also support Gemini 3 already. Keep an eye out for Anti

匹配字段正文

e, and if AI can work with code it can do anything someone with a computer can: build you dashboards, work with websites, create PowerPoint, read your files, and so on. This makes agents that can code general purpose tools. Antigravity embraces this idea, with the concept of an Inbox, a place where I can send AI agents off on assignments and where they can ping me when they need permission or help. It then did web research, created a site, took over my browser to confirm the site worked, and pre

匹配字段正文

wise training-inference consistency a scalable and reusable feature. If you're interested or would like to contribute, please join these Slack channels: sig-post-training; sig-batch-invariant Related Posts DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0 Within three weeks of release, vLLM made DeepSeek-V4.1-Flash 1.9x faster at low concurrency and lifted its throughput 5x on SemiAnalysis AgentX, with SWA bounded replay, CUDA graphs, DeepSeek's new kernels, and vLLM kernel fusions.

匹配字段正文

tion LLMs. It seemed to work fine with regular prompts, but it had poor accuracy in reasoning and multi-turn tasks, which are not only important for regular chat sessions but also agentic applications. This could have been a turning point where linear attention may not be worth pursuing after all. However, it gets more interesting. In October, the Kimi team released their new Kimi Linear model with linear attention. For this linear attention aspect, both Qwen3-Next and Kimi Linear adopt a Gated

匹配字段正文

The Model Context Protocol (MCP) is an open standard for connecting AI agents to external systems. Connecting agents to tools and data traditionally requires a custom integration for each pairing, creating fragmentation and duplicated effort that makes it difficult to scale truly connected systems. MCP provides a universal protocol—developers implement MCP once in their agent and it unlocks an entire ecosystem of integrations. Since launching MCP in November 2024, adoption has been rapid: the co

匹配字段正文

2025-11-02 After months of agentic coding frenzy, Twitter is still ablaze with discussions about MCP servers. I previously did some very light benchmarking to see if Bash tools or MCP servers are better suited for a specific task. The TL;DR: both can be efficient if you take care. Unfortunately, many of the most popular MCP servers are inefficient for a specific task. They need to cover all bases, which means they provide large numbers of tools with lengthy descriptions, consuming significant co

匹配字段正文