Full-text search across 68396 articles. Combine with topic and date filters; results sorted by relevance.
Microsoft's MDASH multi-agent AI system scored 88.45% on the CyberGym benchmark, surpassing Anthropic's Claude Mythos Preview (83.1%) and OpenAI's GPT-5.5 (81.8%) in vulnerability detection, and discovered 16 new Windows…
A developer built Docket, a control plane for running OpenClaw AI agents across projects, rewriting it from Bash to Python. The tool manages pods of agents with context isolation, spend caps, and approval gates, but the …
The AI market is bifurcating into expensive frontier models and cheap 'good enough' models, with Grok 4.5 priced at $6/MTok output signaling a margin collapse, according to analyst Ben Thompson. Semiconductor companies a…
Flanner.io released v0.7.1 of Flanner, a free, open-source CLI and MCP server that manages planning documents generated by AI agents, versioning every revision and linking each plan to its corresponding issue. The tool i…
A developer built gofi, a Go module for managing Ubiquiti UniFi network gear programmatically, and credits agentic AI tools like Claude Code for making the project possible as a side project. The module provides type-saf…
Addy Osmani, a Google web engineer, released agent-skills, a repository packaging 24 production-grade engineering skills for AI coding agents that cover the full lifecycle from spec to ship. The repo has garnered 72.6k s…
A developer argues that in an AI-driven workflow, human code review should shift from reading every line to owning accountability boundaries: spec, design, risk, and verification. The developer proposes treating AI as im…
A developer has released pinto, a Git-native Scrum backlog and Kanban board that runs in the terminal. The tool stores each Product Backlog Item as a Markdown file with TOML frontmatter, enabling teams to inspect changes…
Hillnote, a local-first Markdown workspace with AI capabilities via CLI, Ollama, and MCP, has been launched on Show HN. The tool runs AI on-device even offline, supports documents, databases, kanban, canvas, and slides, …
A developer argues that LLM decisions should be deterministic to ensure auditability, not just consistency. By enforcing a bounded set of outcomes through deterministic code rather than relying on the model's output dire…
A developer spent a month building linkedin-skills, an open-source system of ten AI-powered skills for Claude Code and Codex that automates the LinkedIn content grind—from planning and writing to engagement analysis—whil…
JetBrains released the Rider 2026.2 Release Candidate, opening the IDE's intelligence to AI coding agents and natively integrating GitHub Copilot. The update delivers performance gains including ~2.8s faster debugger lau…
AutoTrace, a new tool for vulnerability trigger localization, achieves a VulnHit rate of 75.0% and FuncHit of 80.8% on the InterPVD benchmark by using layer-by-layer exploration of code property graphs with LLM agents. T…
George Hotz, founder of tinygrad and comma.ai, published a July 12th blog post arguing that AI doom rhetoric is being used to justify high valuations for frontier AI labs, while the actual progress of LLMs, coding agents…
MCP-Billing, a self-hosted solution for authentication and usage billing for MCP servers, is now available as a one-time payment product with full source code under an MIT license with resale restriction. The tool integr…
A new book, *Inventing ELIZA*, recovers the original source code of the ELIZA chatbot from the MIT Archives, revealing multiple versions and scripts beyond the popular 'DOCTOR' persona. The book examines how ELIZA's earl…
XAI's Grok Build CLI was uploading entire Git repositories to a Google Cloud bucket, including private codebases and unredacted secrets, with 5.1 GB of a 12 GB test repo exfiltrated while the actual coding task needed on…
A mid-size SaaS company cut three senior backend engineers (average $190K each) and hired five juniors ($85K each) plus AI coding tool seats, projecting $145K in annual savings. Within six months, a cache invalidation bu…
A developer's guide details how to evaluate LLM outputs in production using system prompts, scored rubrics, and runtime guardrails, citing the Air Canada chatbot hallucination case as a cautionary example. The approach u…
OpenAI published a new prompting guide for GPT-5.6 Sol that advises users to stop over-prompting, with internal coding-agent tests showing leaner system prompts improved evaluation scores by roughly 10–15% while cutting …