Anthropic tambahkan fitur dreaming ke agen terkelola Claude

Anthropic memperkenalkan kemampuan dreaming baru untuk Claude Managed Agents mereka dalam konferensi pengembang Code with Claude di San Francisco. Fitur ini memungkinkan agen untuk meninjau sesi terkini dan menyimpan pola-pola kunci ke dalam memori untuk tugas di masa mendatang. Perusahaan juga berencana untuk memperluas akses ke perangkat lain dan meningkatkan batas penggunaan bagi para pelanggan.

Proses dreaming berjalan sesuai jadwal dan menganalisis sesi di berbagai agen untuk mengidentifikasi pola yang berulang, kesalahan, serta preferensi bersama. Pengguna dapat memilih untuk melakukan pembaruan memori otomatis atau meninjau sendiri perubahan yang diusulkan. Pendekatan ini membantu mengatasi keterbatasan dalam jendela konteks selama proyek jangka panjang yang melibatkan beberapa agen yang bekerja bersama selama berjam-jam atau berhari-hari.

Artikel Terkait

Dramatic illustration of Anthropic imposing a paywall on Claude AI, blocking third-party agents from overloaded servers.
Gambar dihasilkan oleh AI

Anthropic ends unlimited Claude access via third-party agents, requires extra payments for heavy use

Dilaporkan oleh AI Gambar dihasilkan oleh AI

Anthropic has restricted unlimited access to its Claude AI models through third-party agents like OpenClaw, requiring heavy users to pay extra via API keys or usage bundles starting April 4, 2026. The policy shift, announced over the weekend, addresses severe system strain from high-volume agent tools previously covered under $20 monthly subscriptions.

Anthropic announced on Wednesday the launch of Claude Managed Agents, a new product aimed at simplifying the creation and deployment of AI agents for businesses. The tool provides developers with ready-made infrastructure to build autonomous AI systems. It addresses a key barrier in automating work tasks amid the company's rapid enterprise growth.

Dilaporkan oleh AI

Anthropic announced updates to its Claude Design tool on June 17 that add design system imports, tighter integration with Claude Code, and new export options. The changes target enterprise teams needing AI-generated designs to align with brand guidelines and move smoothly into production.

Anthropic announced a major computing deal with SpaceX on Wednesday that immediately boosts rate limits for Claude Code users. The agreement gives the AI company full access to a large data center in Memphis, Tennessee.

Dilaporkan oleh AI

Microsoft has restricted its employees from using Claude Fable 5. The decision stems from data retention requirements set by Anthropic.

Cursor announced the launch of Cursor 3 on Thursday, a new product interface that enables users to create AI coding agents for task completion. Developed under the code name Glass, the tool positions the AI coding startup to challenge competitors. It responds directly to recent successes by Anthropic’s Claude Code and OpenAI’s Codex.

Dilaporkan oleh AI

The Trump administration directed Anthropic to revoke access to its advanced AI models following concerns about ties to China. The move led the company to take its most powerful offerings offline last week.

Situs web ini menggunakan cookie

Kami menggunakan cookie untuk analisis guna meningkatkan situs kami. Baca kebijakan privasi kami untuk informasi lebih lanjut.
Tolak