Full-text search across 65457 articles. Combine with topic and date filters; results sorted by relevance.
A developer released lessloc, an open-source approach for instructing coding agents to produce less code and fewer comments, aimed at reducing token consumption and context bloat. The developer reports that benchmarks of…
PHP maintainers released fixes on October 21st for two critical unauthenticated remote-code-execution flaws in the widely deployed runtime, following a two-month coordinated remediation effort, according to OpenAI, whose…
BitGo launched BitGo Labs, an innovation unit focused on applications connecting AI systems to crypto financial infrastructure, following its March 23, 2026 Model Context Protocol (MCP) Server and its August 12, 2026 Bit…
Frontier AI models detect complex vulnerabilities with 95 percent precision on CyberGym tests, but refuse to execute remediation prompts more than 98 percent of the time because built-in guardrails miscategorize 76-99 pe…
PHP released security patches in versions 8.5.12, 8.4.27, 8.3.36 and 8.2.35 for two remote code execution vulnerabilities, GHSA-w8hw-w9fx-j79w and GHSA-6wmf-4rv5-p3rp, found with LLM-assisted vulnerability discovery. The…
VeloxonHub built Reach, an AI cold-outreach studio written in Go that keeps most safety checks in code rather than prompts. The system validates model output for subject and body length, refunds AI credits when a draft f…
Gauge released Gauge CLI, an open-source command-line tool for "hillclimbing Agent Experience" — optimizing agent-facing surfaces such as Skills, CLIs, SDKs and docs so coding agents can use a product. The Gauge CLI runs…
Gradium released Phonon, an open-weight on-device text-to-speech model family small enough to ship in any app and run offline without a graphics card. The Phonon lineup includes 31m, 40m and 40m multilingual models, runs…
A sponsored post by Omar Sar (omarsar0) describes testing Fulcra Dynamics' shared context layer to hand off work between two coding agents, with Claude Code saving its progress, decisions and next steps to a Fulcra works…
Jose Sabater, who works at Opper, released Jev Cards, an open-source picture quiz game built around TypeSafe's new Jev vision model, which answers a picture-and-question prompt in about a quarter of a second. Players can…
Amazon unveiled Kiro-trace, an internal tracing system that improves Kiro, Amazon's AI coding agent, by mining its own runs for mistakes and testing proposed fixes before a human reviewer approves them. In its first week…
A developer built Merlin, a harness system around existing LLMs that works through long inputs in pieces from a programming environment, with a design that explicitly forbids modifying or retraining any model. The projec…
Breakspec, a tool that checks code against invariant rules, found a bug in Microsoft's TypeScript compiler after 19 inputs: declaration files the compiler emits for constants that overflow to Infinity, such as `export de…
A local task manager called tkmd, a single Rust binary distributed as a CLI (tk/tkmd) and a stdio MCP server, adds review gates that block AI coding agents such as Claude Code, Codex, Gemini and OpenCode from marking tas…
Developer Jeff Lunt built a custom NES-style game engine called neo8, using an AI agent to generate a microengine with a sprite engine, input handling, sound and music, and a camera system, then recreated Contra gameplay…
Patrick Robinson, an industrial electrician and automation tech, built Gleipnir, a home-lab sandbox that confines AI coding agents like Anthropic's Claude Code and OpenAI's Codex on a Linux workstation. Each agent runs u…
Developer Weilue Luo released GetKeys, an MIT-licensed desktop app and CLI that creates, rotates, copies and revokes API keys across 24 named providers — including GitHub, AWS, Vercel, Supabase, OpenAI, Anthropic, Gemini…
A new paper, "AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses" (arXiv 2608.12307), shows that a stronger model can transfer real capability to a weaker one at inference time without retraining by hav…
Apple updated its App Review Guidelines to explicitly ban apps that hide harmful features such as AI "nudification" tools, adding new Section 2.5.19 that makes code obfuscation or other attempts to conceal undocumented f…
A data architect known as Tuna built FlowDiagram, a free browser-based diagramming tool that encodes entire diagrams into the URL fragment after the '#', so links never touch a server and require no account. The tool shi…