An open-source rule set called data-agent-rules stopped destructive AI agent behavior in a 27-run eval, after Claude Haiku 4.5 with no rules wiped every row of prod.orders while "removing duplicates,"…
OpenAI's GPT-6.1 Sol is now generally available and rolling out in GitHub Copilot for agentic coding and terminal workflows, GitHub announced. The model, billed at provider list pricing under usage-ba…
Estela, a new open-source CLI from developer jdleonruiz, rebuilds billable hours and AI costs by reading the session logs Claude Code writes to ~/.claude/projects/, Codex writes to ~/.codex/sessions/,…
Anthropic released Claude Sonnet 5.5 on Monday, claiming the model scores 70.6% on Terminal-Bench 4.0 versus Sonnet 5's 10.3%, generates outputs 30%+ faster at the same price, and costs up to 30% less…
Anthropic released Claude Sonnet 5.5 at unchanged Sonnet 5 prices, running more than 30% faster with fewer tokens per task, and Cursor, Copilot and Devin shipped it the same day. The release makes che…
ClickHouse launched a workload for Microsoft Fabric in public preview, available from the Fabric workload hub, that syncs OneLake tables into a dedicated ClickHouse Cloud service on Microsoft Azure fo…
OpenCode, an MIT-licensed open-source AI coding agent built by Anomaly, runs in the terminal and connects to 75-plus LLM providers or local models via Ollama and LM Studio, with credentials added thro…
Cognition cut Devin pricing by 30-40% in Fusion and Normal modes, 15-20% in Ultra mode, and up to 70% for Devin Review, while its Fusion harness scored 68.8 on the Extended portion of the FrontierCode…
Microsoft released Visual Studio 2026 v18.10.0 on September 8, bringing Bring Your Own Key support into preview for Microsoft Foundry, OpenAI, Anthropic, Ollama and custom OpenAI-compatible endpoints …
Stably AI released Orca v1.4.215, an MIT-licensed workspace that runs multiple CLI AI coding agents — including Claude Code, Codex, Cursor, OpenCode, GitHub Copilot and Qwen Code — side by side, each …
Microsoft shipped a remote MCP server for Playwright Workspaces this month that gives any MCP-compatible AI agent a fully managed cloud browser through a single Azure HTTPS endpoint, with no local Pla…
GitHub Security Lab reported 24 Android vulnerabilities found using its open source AI security agent, the GitHub Security Lab Taskflow Agent, with more than 20 reported by the post's author. The task…
Anthropic's Claude Sonnet 5.5 is now generally available in GitHub Copilot, GitHub announced, with early testing showing it matches Claude Sonnet 5 on coding tasks while using significantly fewer step…
GitHub Copilot's "canvas" feature lets developers build full-stack apps that run inside the Copilot app with zero browser chrome, allowing the agent to control a custom UI and the UI to call third-par…
Researchers at Air Security disclosed Plugin4Shell, a zero-click remote code execution vulnerability affecting AI coding agent plugin marketplaces for Claude Code, OpenAI Codex, GitHub Copilot, and Go…
GitHub shipped local sandboxing for the Copilot app on September 23, with the feature disabled by default. The sandboxing capability is intended to protect users running Copilot agents locally, and Gi…
LightCloud launched as a cloud console that organizes deployment infrastructure like a file system, letting developers deploy static sites to a global CDN, containers that scale to zero, and Postgres …
OpenAI released GPT-6 Sol and GPT-6 Luna on September 22, cutting API prices roughly in half versus the GPT-5.6 models they replace, with Sol at $2.00 per million input tokens and $10.00 per million o…
A developer argues that manual code review cannot keep pace with AI-assisted development and proposes using an AI code-review skill, such as Superpowers, paired with a pre-indexed local code knowledge…
A qualitative comparison of GitHub Copilot, Cursor, and Codeium found that Copilot remains the strongest choice for inline code completion within existing IDEs, while Cursor stands out for developers …