AI TrackerUnduh

Berita Coding,
untuk developer.

Berita Coding terbaru dari setiap penyedia AI: peluncuran, perubahan harga, dan penghentian, diringkas beserta artinya bagi Anda.

Model· 1 diskusi

Artificial Analysis merilis Coding Agent Index v2.0; Claude Code dengan Opus 5.5 memimpin dengan skor 61,7

Artificial Analysis meluncurkan Coding Agent Index v2.0, yang menilai model bersama harness agen mereka pada 290 tugas di bidang rekayasa perangkat lunak, penggunaan terminal, dan tanya jawab repositori, dengan bobot yang sama. Skor tersebut berasal dari Artificial Analysis sendiri dan belum diverifikasi secara independen.
GitHub Copilot· Coding

API metrik penggunaan Copilot kini mencantumkan nama skill kustom, agen, dan server MCP

GitHub menyatakan bahwa metrik penggunaan Copilot kini menampilkan nama yang dikonfigurasi untuk skill, agen kustom, server Model Context Protocol (MCP), perintah garis miring, dan plugin yang dibuat organisasi, alih-alih mengelompokkannya sebagai other atau custom. Fitur ini melanjutkan metrik kustomisasi CLI agentik yang dirilis pada September.
Anthropic· Coding

Claude Code 2.1.309 memperbaiki celah sandbox dan pemeriksaan izin serta mengubah penanganan `sed -i` dan `rm`

Claude Code v2.1.309, dirilis pada 22 Oktober 2026, menurut catatan rilisnya:
Anthropic· Coding· 1 diskusi

Anthropic menyarankan untuk menggabungkan subagen ke dalam loop agen utama, dengan kit migrasi

Dalam artikel bertanggal 22 Oktober 2026, tim Applied AI Anthropic menyebutkan bahwa dalam beberapa penerapan perusahaan di Claude Platform, satu agen yang menggunakan skill dan pencarian tool sering kali menghasilkan kualitas lebih baik daripada desain satu prompt maupun desain subagen, dan sering kali dengan biaya serta latensi lebih rendah. Satu pelanggan dilaporkan mengalami runtime sekitar 2x lebih cepat setelah beralih dari harness multiagen ke satu loop. Ini adalah pengamatan Anthropic sendiri, bukan hasil pengukuran yang dipublikasikan.
Anthropic· Model· 2 diskusi

Anthropic menyatakan Claude menulis bukti formal bahwa 123 pustaka sumber terbuka tidak dapat mengalami crash

Dalam kolaborasi dengan Theorem, Anthropic menyatakan menggunakan Claude untuk membuktikan properti keamanan pada tingkat assembly (RISC-V) di lebih dari 100 pustaka sumber terbuka yang digunakan di dunia nyata. Anthropic menyebutnya sebagai penggunaan AI skala besar pertama untuk memverifikasi perangkat lunak produksi secara formal pada tingkat tersebut.
Anthropic· Coding· 1 diskusi

Anthropic menyumbangkan standar Agent Skills kepada Agentic AI Foundation

Anthropic mengumumkan pada 22 Oktober bahwa mereka menyumbangkan Agent Skills kepada Agentic AI Foundation (AAIF), yayasan yang sebelumnya menerima sumbangan MCP dari Anthropic. Anthropic menyebut standar ini telah diintegrasikan oleh lebih dari 70 platform agen sejak Desember 2025, termasuk ChatGPT, Cursor, GitHub Copilot, dan VS Code.
GitHub Copilot· Coding

GitHub Copilot CLI 1.0.103 menghentikan penggunaan flag --remote lama dan memperluas dukungan sandbox

GitHub Copilot CLI 1.0.103, bertanggal 22 Oktober 2026, menurut catatan rilisnya:
OpenCode Go· Coding

OpenCode v1.19.4 upgrades its bundled Bun runtime for security fixes

OpenCode v1.19.4 upgrades the Bun runtime bundled with the tool to version 1.4.4. According to the release notes, that version includes security fixes for Brotli, TLS, HTTP/1.1, HTTP/2, HTTP/3, WebSocket and fetch, and updates the root certificates to NSS 3.131.1. The release notes list no other changes.
Coding

Amp lets you self-host orbs, free for individuals and teams

Thorsten Ball announced on X that orbs, a feature of the Amp coding agent, can now be self-hosted. He says self-hosting is free for individuals and teams. Details are in Amp's news post, "Self-hosted orbs".
OpenAI· Coding

OpenAI publishes an official command-line tool for its API

OpenAI published openai-cli on GitHub, which it calls the official CLI for the OpenAI REST API. It is written in Go (1.26 or later to build from source), licensed under Apache 2.0, and installs with brew install openai/tools/openai or go install. Pull requests are limited to repository collaborators.
Anthropic· Coding

Anthropic releases Claude API version 2026-10-21, with breaking changes

Anthropic's ClaudeDevs account announced API version 2026-10-21, which it calls the first official Claude API version release since 2023. Anthropic says it plans to release versions more often, so developers can handle breaking changes before a new model requires them. The older version, 2023-06-01, is not deprecated.
Anthropic· Coding

Claude Security now scans continuously and tracks fixes

Anthropic announced on October 21 that Claude Security, in public beta on Claude Enterprise, now keeps its findings current as code changes. After repositories are connected once, Claude runs a deep first scan and then re-scans as changes land.
OpenCode Go· Model

OpenCode adds Meta's Muse Wonder model

OpenCode announced on X on October 21 that Meta's Muse Wonder model is now available in OpenCode. The post gives no further detail, such as which variant, pricing or how to select it. A minute earlier the account had posted the same announcement under the name "Meta Wonder".
Model· 1 diskusi

Recursive releases Flint, an open-weight local coding model

Recursive (@Recursive_SI) announced Flint on X on October 21, calling it its first model: a fast coding model meant to run on a user's own machine. The post, by Richard Socher, says it was built with the company's automated research system, the Eureka Machine, and from scratch in under four months.
Coding

Trail of Bits publishes patching-bugs and regression-hunt plugins for coding agents

Security firm Trail of Bits published two plugins that let engineers hand patch development and regression checks to coding agents. The patching-bugs plugin reproduces a reported bug, writes a fix and tests it. The regression-hunt plugin checks whether a change breaks behavior that used to work. Both grew out of Patch the Planet, Trail of Bits' joint initiative with OpenAI, and draw on its engineers' Codex sessions.
OpenAI· Model· 4 diskusi

OpenAI says its models are coming to Google Cloud

OpenAI has published a post titled "OpenAI models are coming to Google Cloud". Its summary says OpenAI and Google Cloud are bringing frontier models and Codex workflows to Gemini's Model Garden, available through Google Cloud Marketplace. This is OpenAI's own account. Posts on X about the announcement say the models and Codex arrive on Google Cloud in the coming weeks.
Model· 1 diskusi

KRAFTON AI releases Raon-1 mini preview, an open 30B mixture-of-experts model

KRAFTON AI announced a preview of Raon-1 mini on October 20, a mixture-of-experts language model trained from scratch with about 30B parameters in total and 4B active. The weights are on Hugging Face as KRAFTON/Raon-1-mini-preview under Apache 2.0.
Coding· 1 diskusi

Vercel introduces durable-harness for running coding-agent harnesses durably

Vercel announced durable-harness on X. In Vercel's words, it lets users run Pi, OpenCode, Codex, Claude Code, eve, fx or their own harness durably on Vercel, and agents automatically resume work after failures and run for hours, days or months.
Anthropic· Coding

Claude Code 2.1.305 fixes a 2.1.304 tool-search regression and adds a Linux sandbox setting

Claude Code v2.1.305, released October 20, 2026, per its release notes:
Anthropic· Coding· 1 diskusi

Anthropic's Frontier Red Team: Claude found 493 attack-surface issues across 25 open-source projects

Anthropic published "Using Claude to reduce the attack surface of code" on Oct 20, 2026. Everything below is Anthropic's own account.