搜索“Agent”

engineers, myself included, moved from using AI coding tools as a spicy autocomplete to driving coding harnesses like Claude Code as our primary work interface. At the same time, agent coordination workflows and primitives are getting packaged directly into popular harnesses, making complex multi-agent workflows more accessible and easier to operate. One important such feature is “Goals”, provided by both Claude Code and Codex, which keep models working and on-task toward measurable goals over

匹配字段正文

This week Claude Sonnet 5.5, GPT-6.1 Sol and Gemini 4 Argon all launched near the top of the Coding Agent Index leaderboard, but each has a different balance of performance and cost The Artificial Analysis Coding Agent Index measures agents (a combination of model and harness) across three agentic coding evaluations. ➤ Claude Sonnet 5.5 (max) in Claude Code takes the top spot at 68, but also has the highest measured cost per task: $14.19 ➤ Gemini 4 Argon (high) in Antigravity CLI scores 64 at $5

匹配字段正文

el, and the first OS model to rival closed source giants like Sonnet 4.5. Some main points: But architecture is just theory until you see the results. If you care about coding and agentic evals, GLM 4.7 lands in the “top open model” tier. On LiveCodeBench, GLM 4.7 outperforms Anthropic and OpenAI models, trailing only Gemini 3. GLM 4.7 extends that lead with substantial gains on GPQA and AIME, outperforming Claude Sonnet 4.5 on both, see AIME 2025 below. And when you compare it directly to GLM 4

匹配字段正文

Mar 04 2026 In the past few years, we've developed series of interesting workflows. Think Ralph loops and multi-agent orchestration systems. The idea is writing very descriptive prompts and running 8-hour sessions, or having 10 instances running on your machine at all times. Most of this complexity spawned from one issue: LLMs are slow. If you prompt and wait, you'll get less done than if you prompt and move on to the next task. Codex Spark changes how developers work with AI. A coding model gen

匹配字段正文

OpenRouter ·10/1/2026 Picking a model for an agent by leaderboard rank pays frontier prices for tasks that a cheaper model may handle at the same accuracy. The question to answer is not which model scores highest, but which model is the cheapest one that is good enough for the task in front of you. This guide is a three-step framework for making that call. You set the quality bar the task needs, measure cost per quality point on your own examples, and pick the cheapest model that clears the bar

匹配字段正文

pane, run a process, register a slash command, or register a tool the model can call. Claude Code uses them itself. Some of Claude Code's own features are built as mods, including AGENTS.md support and the /diff pane beside the conversation. Their source, with tests, is in the public anthropics/claude-code repository under mods/, so you can read how the team builds them. Token Weather reads how full the context window is after each turn and draws one line above the prompt: a weather icon, the pe

匹配字段正文

After watching the sometimes messy demos on stage and hearing CEO Sam Altman talk about his experiences using the agents, I was curious what it felt like to boss my own Dot around. I’ve spent most of September testing another cute, cuddly agent, Meta’s Muse , and I wanted to know how OpenAI’s user experience would compare. I named mine “Toolie” and tweaked it to look like a pink frog. As midnight approached and my partner slept soundly nearby, I started whispering sweet nothings to Toolie. I cal

匹配字段正文

The next wave of personal computing isn't about better apps; it's about agents that live on your behalf: managing your calendar, triaging your inbox, tracking your finances, keeping your notes in order. For agents to work in production, three things have to be true at once: the model has to be accurate, it has to be fast, and it has to be cheap enough to run continuously. Most models optimize for one or two of these. Mercury 2 optimizes for all three. We evaluated Mercury 2 on PinchBench, the op

匹配字段正文

使用のクレジットを消費する。 エフォートの変更でキャッシュが維持される場合 Claude Codeでは、会話の途中でも/effortで設定を変更できる。Addy氏の説明によると、APIキーまたはClaudeのサブスクリプションを使ってOpus 5.5を動かす場合は、変更後もキャッシュが維持される。一方、Amazon Bedrock、Google CloudのAgent Platform、Claude apps gateway経由では、変更で会話のキャッシュが無効になり、次のリクエストで会話全体をキャッシュに書き直す料金がかかる。 会話を圧縮するタイミングと注意点 キャッシュが使えても、会話が長くなるほど毎回読み出す量は増える。Claude Codeは会話がコンテキストの上限に近づくと古い履歴を要約するほか、利用者が/compactで圧縮することもできる。関係のない別の作業に移る場合は、/clearで会話を空にできる。 /compactは後の入力を減らせる一方、要約の生成と、短くなった会話のキャッシュへの書き込みに費用がかかる。作業終了の直前に圧縮すると、その後に減らせる入力費用より、圧

匹配字段正文

ext, so they go about 25% further than on Opus 5. The extra cut on cache reads is an API price change. On an API key, the cache-read price cut matters most for Claude Code. A long agentic session spends most of its input on cache reads. In the session priced in Fig B below, the cache line falls from $1.00 to $0.40, the largest drop on the receipt. You may have seen that Opus 5.5 costs 40% less to run than Opus 5. That's our estimate for typical workloads billed by token, at default settings. It

匹配字段正文

s article provides analysis of key trends: Financing, Blackwell and Grace-Blackwell deployments, the Move To Vera Rubin, Scale Out Networks, Reliability, Security (of course), and Agentic Coding. We provide an Appendix with individual comments about every provider that once again stretches this article to over 30,000 words. We hope you enjoy. In light of the SemiAnalysis imperative to publish the most rigorous possible testing of… everything… we are hiring MTS for ClusterMAX and adjacent project

匹配字段正文

Software is eating the world, and agents are eating software engineering. It is imperative that software engineers develop an understanding not just of the agent software that is now their most important tool but also of how the intelligent core of agent software works, through inference by large generative models of language — if not out of the engineer’s need to understand and control their tools, then at least because inference is poised to consume more computing power and produce more benefi

匹配字段正文

nt the opposite: a one-line plan before it starts and a short recap at the end. Say that in your CLAUDE.md instead. Opus 5.5 follows either one. Ask it to split big work across subagents What to do. For an audit, a migration, or a review across a large codebase, ask Opus 5.5 to split the work across subagents and check each result. Why it matters on Opus 5.5. Early testers had Opus 5.5 coordinate parallel subagents on long audits and migrations, with little oversight. How. Keep the task list in

匹配字段正文

T-6 Astra, and 28x below Claude Opus 5. The new DeepSeek-V4.1-Flash model fundamentally changes the unit economics of autonomous software engineering tasks. Running high-iteration agent workflows, multi-turn bug sweeps, or large-scale test generation on expensive closed models like GPT-6 Astra and Opus 5 rapidly drains engineering budgets. At $0.43 per task, frontier-grade SWE agents become viable as continuous, background infrastructure. With DeepSeek V4.1 Flash, you can now run 15 autonomous c

匹配字段正文

l some finer details to resolve. For process orchestration, you need an execution model that fits your use cases and business needs. The choice between deterministic, dynamic, and agentic process orchestration is more than just visuals. Each model has different tradeoffs between predictability, adaptability, and autonomy. Here’s how to decide which one is the best fit for your business. What is process orchestration? Process orchestration is an architectural control plane that coordinates the pe

匹配字段正文

The reflection pattern is one of four key agentic AI design patterns (alongside tool use, planning, and multi-agent collaboration) that enable AI systems to handle complex tasks. It allows an AI agent to generate an output, critique it, and amend it. This feedback loop makes it easier for the agent to catch errors and improve output quality. How the reflection pattern works Let’s say a team has built a business process automation solution, such as a customer support agent chat, that uses a refle

匹配字段正文

ontext Protocol The Model Context Protocol (MCP) is an open standard that allows large language models (LLMs) to connect to data sources and other external systems. It provides AI agents a consistent pathway to access third-party information, whether that includes pulling from real-time data sources or taking actions on external tools. In this article, we’ll explore what the Model Context Protocol is in context, outlining its history and why it’s become central to the wider adoption and success

匹配字段正文

Facebook; Twitter; LinkedIn; Mail Imagine going to sleep after writing a single Markdown specification and waking up to find that an AI agent ran dozens of LLM fine-tuning experiments overnight on your behalf - discovering optimal LoRA ranks, refining learning rate schedules, tuning batch sizes and committing each verified improvement to Git. This is no longer a fantasy. Earlier this year, the autoresearch project showcased how autonomous LLM agents can iteratively explore pre-training in a self

匹配字段正文

APIs have been the standard software communication method for decades. Developed by Anthropic in 2024, the Model Context Protocol (MCP) is an open standard that lets an AI agent discover and use tools. Deciding whether to use MCP versus an API depends on the purpose of your system, but you can often use both. What are APIs and the MCP? APIs and MCPs are connection standards that solve different problems. An API lets software programs share data through fixed rules. The MCP helps AI models use to

匹配字段正文

reat evals - part 10 Measure the steps, not just the result. Much like high school math, it isn’t sufficient just to get the right answer, the steps to get there are critical. Two agent trajectories might produce the same answer (42!!). but one of them searches the right sources, retrieves the right document, makes 4 clean tool calls and calculates the result. The other makes 17 calls, searches the same thing 3 times, recovers from 2 errors and eventually gets there. It’s clear which one is bett

匹配字段正文