Full-text search across 8054 articles. Combine with topic and date filters; results sorted by relevance.
Indirect prompt injection remains a real threat against most models but has dropped sharply on the newest ones, according to Gray Swan's ART and IPI red-team benchmarks: attackers with 15 tries succeeded against Claude O…
A developer demonstrates how to secure Model Context Protocol (MCP) servers by placing Kong AI Gateway 2.0 in front of them, arguing that most MCP servers run with no authentication, per-tool authorization, rate limiting…
AWS released Kiro IDE 1.1 on September 14, adding Agent Artifacts that turn agent-generated documents, diagrams, code and images into persistent named objects, plus native ARM64 installers for Windows and Linux that remo…
A comparative review evaluates seven auto routing platforms for LLM model selection in 2026, including Bifrost, an open-source AI gateway written in Go that provides multi-provider routing, load balancing, and failover b…
Anthropic released Claude Opus 5.5 and OpenAI shipped GPT-6 Sol and GPT-6 Luna on September 22, 2026, with both labs cutting token prices and emphasizing cost per finished task over raw benchmark scores. Anthropic says O…
OpenAI's GPT-6 Astra became the first model to complete DrivingBench, a new benchmark from Aditya Ramabadran, Simon Mahns and Tobias Gessler that lets frontier language models drive a real 2022 Toyota Corolla through a r…
A developer has proposed a role-based model routing system for AI coding sessions, assigning tasks to Navigator, Builder, Diagnostician, or Surgeon roles based on the cost of feedback rather than project importance. The …
A developer built Monster Maker, a free no-signup drawing prompt generator for monsters, by forking the engine behind their existing Daily Doodle site with the help of Claude. The project involved reworking the sentence …
Anthropic released Claude Opus 5.5, the first model in its new Claude 5.5 family, which the company says performs at the level of Claude Fable 5.1 for most tasks while costing 40% less to run than Opus 5 and running abou…
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…
Anthropic cut over 80% of Claude Code's system prompt with no measurable capability loss, according to a guide the company published on effective context engineering for AI agents. Anthropic's 2026 Agentic Coding Trends …
Netlify built an integrated, Netlify-managed Git repository for every project created without a connected Git host, the company said, after 93% of new projects in the last month arrived via direct file uploads, the Netli…
A developer demonstrates why Socket.IO real-time architectures break when scaled horizontally beyond a single Node.js process, since each instance's shared-nothing memory means broadcasts and room joins only reach client…
Developer statico released ttmux, a terminal multiplexer written entirely with Anthropic's Claude Code, now available in beta via Homebrew or built from source with Rust 1.82 or later. ttmux ships with defaults tmux requ…
Researcher Oren Yomtov of Accomplish AI disclosed two OpenAI Codex sandbox escape vulnerabilities, Heapjack and Overpatch, that were reported on August 12, patched within eight days, and publicly disclosed on September 1…
TypeSafe AI, a San Francisco lab founded by former OpenAI researcher Diogo Almeida, emerged from stealth on September 15, 2026 with Jev, a "System One model" that returns typed, probability-scored decisions instead of ge…
AI product builder Mika has published a guide detailing five open-source, self-hosted tools that replace a proprietary AI SaaS stack costing $110 to $250 per month. The recommended replacements include OpenUI for UI gene…
DeepSeek V4.1-Flash now beats OpenAI's Sol on Brokk's internal coding benchmarks at a fraction of Sol's estimated model size, according to a Brokk blog post citing the DeepSWE v1.1 score-versus-average-cost-per-task char…
A developer argues that the Model Context Protocol (MCP), while easy to run locally, hits an "Enterprise MCP Wall" at scale, where hardcoded credentials, unregistered server sprawl, and overly broad tool permissions crea…
OpenAI's Codex agentic coding tool runs on an existing ChatGPT subscription with no separate account required, according to a guide explaining the product's core concepts for non-coders. The guide states that Codex is av…