AI TrackerScarica l'app

Coding: le notizie,
per chi sviluppa.

Le ultime notizie su coding da ogni provider AI: lanci, cambi di prezzo e dismissioni, riassunti con cosa significano per te.

Modelli· 1 discussione

Artificial Analysis pubblica Coding Agent Index v2.0; Claude Code con Opus 5.5 è in testa con 61,7

Artificial Analysis ha lanciato la versione 2.0 del suo Coding Agent Index, che valuta modelli insieme ai relativi harness agentici su 290 attività di ingegneria del software, uso del terminale e domande e risposte sui repository, con ponderazione uniforme. I punteggi sono calcolati da Artificial Analysis e non sono stati verificati in modo indipendente.
GitHub Copilot· Coding

L'API delle metriche di utilizzo di Copilot ora mostra i nomi di skill personalizzate, agenti e server MCP

GitHub afferma che le metriche di utilizzo di Copilot mostrano ora i nomi configurati di skill, agenti personalizzati, server Model Context Protocol (MCP), comandi slash e plugin creati da un'organizzazione, invece di raggrupparli sotto other o custom. La novità si basa sulle metriche di personalizzazione agentica della CLI rilasciate a settembre.
Anthropic· Coding

Claude Code 2.1.309 corregge le vulnerabilità che consentivano di aggirare la sandbox e i controlli delle autorizzazioni e cambia la gestione di `sed -i` e `rm`

Claude Code v2.1.309, rilasciato il 22 ottobre 2026, secondo le note di rilascio:
Anthropic· Coding· 1 discussione

Anthropic consiglia di integrare i subagent nel ciclo principale dell’agente, con un kit di migrazione

In un articolo datato 22 ottobre 2026, il team Applied AI di Anthropic afferma che, in diverse implementazioni aziendali su Claude Platform, un singolo agente che usa skill e la ricerca degli strumenti ha spesso superato in qualità sia un approccio basato su un unico prompt sia uno basato su subagent, spesso con costi e latenza inferiori. Secondo quanto riferito, un cliente ha registrato un runtime circa 2 volte più rapido passando da un sistema multi-agente a un ciclo unico. Si tratta di osservazioni di Anthropic, non di misurazioni pubblicate.
Anthropic· Modelli· 2 discussioni

Anthropic afferma che Claude ha scritto prove formali secondo cui 123 librerie open source non possono andare in crash

In collaborazione con Theorem, Anthropic afferma di aver usato Claude per dimostrare proprietà di sicurezza a livello di assembly (RISC-V) in oltre 100 librerie open source usate nel mondo reale. L’azienda definisce il lavoro il primo impiego su larga scala dell’AI per verificare formalmente software di produzione a quel livello.
Anthropic· Coding· 1 discussione

Anthropic dona lo standard Agent Skills alla Agentic AI Foundation

Il 22 ottobre, Anthropic ha annunciato che donerà Agent Skills alla Agentic AI Foundation (AAIF), la fondazione a cui aveva già donato MCP. Anthropic afferma che, da dicembre 2025, lo standard è stato integrato in oltre 70 piattaforme per agenti, tra cui ChatGPT, Cursor, GitHub Copilot e VS Code.
GitHub Copilot· Coding

GitHub Copilot CLI 1.0.103 elimina i flag legacy `--remote` ed estende il supporto per la sandbox

GitHub Copilot CLI 1.0.103, datato 22 ottobre 2026, secondo le note di rilascio:
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· Modelli

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".
Modelli· 1 discussione

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· Modelli· 4 discussioni

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.
Modelli· 1 discussione

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 discussione

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 discussione

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.