Full-text search across 63242 articles. Combine with topic and date filters; results sorted by relevance.
Ollama 0.31 introduces multi-token prediction for Gemma 4 on Apple Silicon, cutting token generation time by 90% on Aider's coding benchmark. The update automatically accelerates local coding agents without quality trade…
Loop engineering, where developers define loops that prompt coding agents until a task is complete, is gaining attention from figures like Peter Steinberger and Boris Cherny. However, the approach faces challenges: codin…
Panoptes, an AI audit and alignment layer, launches to provide universal observability, audit trails, and policy enforcement for AI coding agents like Claude Code, OpenAI Codex, Google Antigravity, and Hermes Agent. The …
Abuja-based developer Okhai has released Foundation, an open-source full-stack application substrate designed for teams building high-performance, event-driven systems with AI coding agents. The project aims to reduce th…
OmniRoute, an open-source AI gateway, has released version 3.8.42, enabling developers to connect to over 236 AI providers through a single API endpoint. The tool offers automatic failover, token compression, and support…
Repository intelligence, which analyzes full commit history, PR discussions, and architectural decisions alongside current code, is transforming AI coding assistants in 2026. ANZ Bank reported a 42.36% reduction in task …
A developer ported 100k lines of TypeScript to Rust in one month using AI, despite having no prior Rust experience. The resulting code relies heavily on Arc<Mutex<>> wrappers, an anti-pattern that undermines Rust's safet…
Anthropic's study of 400,000 Claude Code sessions shows debugging dropped by half while task value rose 25%, signaling expertise shifting from coding to system design. New tools like 'dropped' detect truncated instructio…
AI coding tools rapidly generate 80% of a project's code, but the remaining 20%—edge cases, failure modes, and operational realities—is where engineers historically built critical judgment. This missing portion, now ofte…
Mistral launched Vibe, a unified AI agent that replaces Le Chat and combines work assistant and coding agent capabilities under a single license. The agent runs on Mistral's own models and infrastructure, targeting enter…
Zhipu AI's open-weight GLM 5.2 model achieved a 39% F1 score in Semgrep's IDOR detection benchmark, outperforming Claude Code's 32% and Claude Opus 4.8. The MIT-licensed model runs locally, enabling secure code analysis …
A developer proposes a method called 'Named-Persona Adversarial Review' to overcome the blind spots of single-modal LLMs in code review. By asking the AI to review code as specific named individuals with documented philo…
AI-assisted coding tools are exposing the difference between developers who understand software and those who merely produce it, according to an engineer. While AI can generate code quickly, developers remain responsible…
A developer proposes using a read-only reviewer agent to catch errors in code generated by a main agent. The reviewer, which cannot edit code, identifies spec drift, missing cases, test-implementation coupling, and termi…
AWS launched Lambda MicroVMs on June 22, a new compute primitive that provides each user or AI session with its own Firecracker-isolated virtual machine, preserving state for up to eight hours and enabling near-instant l…
A Claude Code user lost their entire home directory, including family photos, when an agent ran a cleanup command that matched more than intended, highlighting the lack of permission boundaries in AI coding agents. As ag…
Google Labs open-sourced DESIGN.md, a plain-text format that gives AI coding agents persistent access to a project's visual design system, including tokens and rationale. The format, now at v0.3.0 with over 18,900 GitHub…
Microsoft's VS Code team published findings from 50,000 runs of a 5-line evaluation, revealing how AI coding models calibrate effort, token cost, and tool use. The blog also announced new features including bring-your-ow…
A developer conducted an experiment asking AI to build an entire backend application, then audited it for security. The audit revealed that while the code worked correctly, it contained dozens of small security assumptio…
A Korean developer analysis revealed that Claude Code's 'Extended Thinking' text is a 600-character encrypted signature, not the model's reasoning, making agent audits impossible. Meanwhile, Anthropic's Slack beta for Cl…