Full-text search across 63168 articles. Combine with topic and date filters; results sorted by relevance.
At AI DevCon London, a Docker engineer demonstrated why prompt-level guardrails are insufficient for coding agents, advocating for isolated microVM environments like Docker Sandboxes. The talk highlighted the risks of ag…
NVIDIA's AI Red Team found that the most common failure mode in AI agent deployments is a lack of access control, with many agents holding user credentials accessible to any authorized network user. The team also identif…
Snowflake Inc. announced the spark-migration skill in its CoCo AI coding agent, which migrates Apache Spark codebases to Snowpark Connect with minimal manual changes. The tool scans files for compatibility issues, applie…
1Password has released SuperSAGE v2, an AI-powered security code review pipeline that solves context-window limits and nondeterminism by generating incremental, compressed scaffolding files per source directory. The syst…
Claude Code, Cursor, and Windsurf each offer distinct advantages for building AI agents, with Windsurf's Flow providing superior context tracking and Cursor's Composer feeling like directing a smart intern, while Claude …
A developer built a WhatsApp AI agent powered by Google Gemini, using Gemini itself as a coding copilot to scaffold, debug, and extend the code. The agent receives WhatsApp messages via Meta's Cloud API, processes them t…
Frontend CI/CD pipelines are slowing down as AI-generated code produces an explosion of tests, Neciu Dan writes in a technical blog post. Dan argues that CI and CD should be treated as separate problems and proposes buil…
Microsoft patched a record 622 security flaws in July, triple the previous monthly record, while China's 360 Digital Security Group has used an AI agent to uncover nearly 1,000 previously unknown bugs. OpenAI's Codex Sec…
Anthropic deleted over 80% of Claude Code's system prompt when migrating to Claude Opus 5 and Fable 5, with no measurable loss on coding benchmarks, according to Thariq Shihipar, a Member of Technical Staff at Anthropic.…
Sandbox-CLI, an open-source tool that runs coding agents like Claude Code and Codex inside disposable Docker containers with strict isolation, is now in public beta. The tool mounts only the user's project directory, blo…
Qarinah, an open-source local memory compiler for coding agents, claims to reduce input-context tokens by 98.71% and achieve a 77.81:1 compression ratio, cutting estimated input-context cost from $0.4421 to $0.0057 per q…
AI can write test code quickly, but the real cost lies in maintenance, review, and signal quality after tests enter the repository. A developer warns that AI-generated frontend changes often fail in CI due to missing ope…
The Organic Code Movement has published a specification for a 100% AI-free software supply chain, requiring developers to use only tools, compilers, and operating systems from 2017 or earlier to guarantee no AI involveme…
Loop engineering, a term coined by Addy Osmani in June 2026, is replacing prompt engineering as the dominant paradigm for coding agents, shifting focus from prompting models to designing autonomous loops that prompt mode…
InsForge, an AI-native backend platform built for agentic coding, positions itself as an alternative to Firebase by offering managed Postgres databases with full ACID transactions and structured relational data. CEO Hang…
Aditya Arakeri released senior-agent-skills, a set of eight portable playbooks that make coding agents behave like careful senior engineers, working identically across Claude Code, Codex CLI, Google Antigravity, OpenCode…
Snowflake is expanding its Cortex Agents platform with new capabilities for building, deploying, and operating enterprise AI agents at scale, including a coding agent backed by the same runtime as CoCo, async API, code e…
A developer redesigned their LLM verification pipeline after commenters Alexey and Manuel pointed out that deterministic code checks could catch garbage scenarios before any LLM call. The new pipeline layers code checks …
OpenAI released GPT-5.6 Sol, Terra, and Luna on July 9 with three API-level breaking changes that require immediate fixes for production tool-calling code. Parallel tool dispatch is now on by default, the legacy code_int…
Bun creator Jarred Sumner used 64 parallel Claude Code agents to rewrite 535,000 lines of Zig into Rust in 11 days at an API cost of approximately $165,000, shipping the result in Claude Code v2.1.181. The rewrite elimin…