Full-text search across 63147 articles. Combine with topic and date filters; results sorted by relevance.
Security research firm Calif, working under OpenAI's Patch the Planet initiative, disclosed two critical PHP core vulnerabilities, CVE-2026-109618 and CVE-2026-109619, that let unauthenticated attackers read a PHP worker…
A developer built LicenseGuard MCP, an open-source Model Context Protocol server that connects AI coding agents such as Claude Desktop, Cursor, Devin, and Cline to a deterministic license-compliance engine over JSON-RPC …
CodeRabbit is now an authorized partner in the SpaceX Super Intelligence Partner Network and is available in the Grok Build Plugin Marketplace, letting teams pair Grok Build code generation with CodeRabbit's Agentic Chan…
A trader ran TypeSafe's "System One" model Jev (jev-1.13.0) alongside a reasoning LLM agent, gpt-6-luna, on the same small real KuCoin perpetual futures account for 17 days to test whether a sub-second classifier could c…
MiniMax launched M3.1-Flash-Preview inside its MiniMax Code agent tool on September 27, 2026, with no model card, benchmark report or public pricing, after developers spent two weeks testing the same system as a free Ope…
GitHub on October 15 made agentic autofix for code scanning alerts generally available, letting Copilot agents explore a codebase, rerun CodeQL to confirm a proposed change closes the alert, and open a draft pull request…
Databricks' Genie One and Genie Code AI coworkers draw enterprise context from four distinct places, according to a Databricks walkthrough: company-wide facts go in Genie Ontology, team rules in instructions files, repea…
Google's own benchmark table for Gemini 4 Argon shows the model taking the top score in 13 of 19 rows, with GPT-6 Astra winning 3 and Claude Opus 5.5 winning 2, according to figures Google published on its Gemini 4 Argon…
Complyance runs AI agents that write and execute code against customer systems such as GitHub organisations, AWS accounts, identity providers and document stores from an internet-connected gVisor sandbox that holds no cr…
Plannotator released Plannotator Inbox, an async inbox that collects questions, blockers, plans, prototypes and diffs from long-running coding agents into a single list, run via the `plannotator inbox` command. The produ…
Anthropic's zero data retention (ZDR) agreements apply only to eligible Anthropic APIs, Anthropic products that use a customer's Commercial organization API key (including Claude Code accessed via the API), and Claude Co…
Microsoft released a public slice of GitHub Copilot coding-agent telemetry on October 1st, giving researchers 301,026 sessions covering 9.3 million LLM calls and 8.7 million tool calls, according to Microsoft Azure Resea…
Google Labs' Opal, a free no-code builder for chaining prompts, models and tools into shareable AI mini-apps, added an Agent step on 24 February 2026 powered by Gemini 3 Flash that plans an approach, picks tools and mode…
Chroma's July 14, 2025 study "Context Rot: How Increasing Input Tokens Impacts LLM Performance," by Kelly Hong, Anton Troynikov and Jeff Huber, tested 18 models and found that even a single distractor reduces performance…
Claude-mem, an open-source Claude Code plugin at version 13.25.3 with about 94,000 GitHub stars under Apache 2.0, gives Claude Code memory across sessions by capturing lifecycle hooks, compressing them with a local Bun w…
A developer has released repowiki, an MIT-licensed, PyPI-published open-source tool that handles the deterministic orchestration of generating repository wikis so that coding agents such as Claude Code, Codex, and OpenCo…
AI coding agents can produce changes that pass TypeScript, tests, and builds yet still violate a project's intended architecture, according to a first-person account of working with coding agents on larger changes. The a…
A developer argues that workflow engines, which hold control flow in their own process and invoke coding agents as subroutines, offer machine-checkable control flow that orchestrator skills written as Markdown prose cann…
A new MIT-licensed tool called never-again converts each bug a developer fixes into either a blocking hook or a one-line rule so AI coding agents stop repeating the same mistakes. The tool runs locally with no account, t…
A developer who uses AI coding tools daily reports that while AI-generated first drafts cut generation costs to near zero, review and maintenance costs stayed flat, producing projects that look highly productive in week …