AI Tracker앱 받기

코딩 뉴스,
개발자를 위해.

모든 AI 제공업체의 최신 코딩 뉴스: 출시, 가격 변경, 지원 종료를 나에게 미치는 영향과 함께 요약했습니다.

모델· 토론 1개

Artificial Analysis, Coding Agent Index v2.0 공개… Claude Code와 Opus 5.5가 61.7점으로 선두

Artificial Analysis가 Coding Agent Index v2.0을 공개했습니다. 이 지수는 소프트웨어 엔지니어링, 터미널 사용, 저장소 Q&A에 걸친 290개 과제에서 모델과 에이전트 하네스를 함께 평가하며, 각 항목에 동일한 가중치를 부여합니다. 점수는 Artificial Analysis 자체 평가이며, 독립적으로 검증되지는 않았습니다.GitHub Copilot· 코딩

사용량 지표 API에 이제 커스텀 스킬, 에이전트, MCP 서버 이름이 표시됩니다

GitHub에 따르면 이제 Copilot 사용량 지표에는 조직이 만든 스킬, 커스텀 에이전트, Model Context Protocol (MCP) 서버, 슬래시 명령 및 플러그인의 설정된 이름이 표시됩니다. 이전에는 이러한 항목이 other 또는 custom으로 묶였습니다. 이번 변경은 9월에 출시된 에이전트형 CLI 사용자 지정 지표를 기반으로 합니다.Anthropic· 코딩

Claude Code 2.1.309, 샌드박스 및 권한 검사 우회 문제 수정, `sed -i`와 `rm` 처리 방식 변경

Claude Code v2.1.309은 릴리스 노트에 따르면 2026년 10월 22일에 출시되었습니다.Anthropic· 코딩· 토론 1개

Anthropic, 서브에이전트를 메인 에이전트 루프에 통합할 것을 권고하며 마이그레이션 키트 제공

2026년 10월 22일자 글에서 Anthropic Applied AI 팀은 Claude Platform을 사용하는 여러 엔터프라이즈 배포 사례에서, 스킬과 도구 검색을 사용하는 단일 에이전트가 단일 프롬프트 방식과 서브에이전트 방식 모두보다 품질 면에서 더 나은 경우가 많았고, 비용과 지연 시간도 대체로 낮았다고 밝혔습니다. 한 고객은 멀티 에이전트 하네스에서 단일 루프로 전환한 뒤 실행 시간이 약 2배 빨라졌다고 합니다. 이는 Anthropic 자체의 관찰 결과이며, 공개된 측정치는 아닙니다.Anthropic· 모델· 토론 2개

Anthropic says Claude wrote formal proofs that 123 open-source libraries cannot crash

In a collaboration with Theorem, Anthropic says it used Claude to prove security properties at the assembly level (RISC-V) in over 100 real-world open-source libraries, which it calls the first large-scale use of AI to formally verify production software at that level.Anthropic· 코딩· 토론 1개

Anthropic donates the Agent Skills standard to the Agentic AI Foundation

Anthropic announced on October 22 that it is donating Agent Skills to the Agentic AI Foundation (AAIF), the foundation it earlier donated MCP to. Anthropic says the standard has been integrated by more than 70 agent platforms since December 2025, including ChatGPT, Cursor, GitHub Copilot and VS Code.GitHub Copilot· 코딩

GitHub Copilot CLI 1.0.103, 레거시 --remote 플래그를 폐지하고 샌드박스 지원 확대

GitHub Copilot CLI 1.0.103의 2026년 10월 22일자 릴리스 노트에 따르면:OpenCode Go· 코딩

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.코딩

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· 코딩

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· 코딩

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· 코딩

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· 모델

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".모델· 토론 1개

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.코딩

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· 모델· 토론 4개

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.모델· 토론 1개

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.코딩· 토론 1개

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· 코딩

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· 코딩· 토론 1개

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.
이전 뉴스