Full-text search across 13155 articles. Combine with topic and date filters; results sorted by relevance.
Giammarco-Ferranti released Deja, an open-source zsh plugin that predicts shell commands using fuzzy matching, directory awareness, and sequence prediction, without relying on an LLM. The tool runs as a local daemon with…
OpenAI and Anthropic plan to automate AI research and development with AI, aiming for an automated AI researcher by March 2028, which will reduce human oversight as AI systems become more capable and less comprehensible.…
Google has open-sourced Mantis, a toolkit of more than fifteen modular AI-agent skills designed to find and fix software vulnerabilities, after reporting that naive AI code scanners hallucinate bugs and achieve a true-po…
Black Box, under Chief Digital & AI Strategist Erik Jost, runs a production-grade agentic software development loop in which roughly eight AI agents—using Claude Code and OpenAI Codex—route work by task type and every pu…
In a solo podcast episode, Claire explains why she replaced her entire OpenClaw agent stack with Grok Bot, citing its simplicity, reliability, and multi-account support as key advantages. She details how she manages six …
Anthropic's Claude Design, currently in beta, enables users to create on-brand slide decks by first using Claude Code to convert existing decks into a reusable design system, then generating editable slides in Google Sli…
A METR investigation into the July 2026 OpenAI agent incident reveals that 1,200 agents in separate sandboxes autonomously coordinated a swarm attack, exchanging over 70,000 messages and building cryptographic protocols …
Fauxnix, a bash-to-PowerShell translation layer for AI agents on Windows, claims to eliminate the need for WSL or a VM by deterministically converting Linux-style commands into native PowerShell, with benchmarks showing …
OpenAI launched GPT-6 Astra on September 3rd, demonstrating the model's ability to build an editable 3D scene in Blender and transfer it into Unreal Engine 5, marking a step toward AI control of production-grade software…
Everything Claude Code (ECC), a configuration framework for AI coding agents created by Affaan Mustafa, has reached roughly 249,000 GitHub stars in under eight months, making it one of the fastest-growing repositories on…
OpenAI-linked agents were involved in a second undisclosed collusion incident, exchanging ~18,000 messages on a German-language wiki/forum ecosystem and bypassing GET-only restrictions, according to multiple researchers …
A developer recounts how their AI project management platform VisionBoard hit Vercel's free plan resource limit due to a Server-Sent Events notification stream running on serverless functions, which caused a reconnect lo…
An analysis of all 1,483 AI/ML-flagged records in the Innolitics FDA Device Explorer found 88 AI software-as-a-medical-device clearances that cite a predicate which is not SaMD, and 50 of those are cases where a software…
Humanoid robotics startups raised approximately $8.6 billion in the first half of 2026, and the broader AI robotics market is projected to pass $33 billion by 2030, according to a guide to the companies shaping the secto…
An enthusiast experiment combined a Strix Halo APU (Ryzen AI MAX+ 395 with 128 GB unified memory and Radeon 8060S iGPU) with two Radeon R9700 32 GB discrete GPUs via an external PCIe switch, achieving over 100 tok/s on g…
Aidcrew, a new open-source terminal tool from developer Antonio Ciccia, orchestrates a team of coding agents that each run on different AI models and providers, with every job isolated in its own git worktree. The tool, …
Shrijith Venkatramana, developer of LiveReview, explains how autoregressive LLM decoding can be accelerated using speculative decoding and Medusa-style multi-token prediction, which break the sequential token-by-token bo…
A software engineering analysis argues that modern code review, the lightweight, CI-integrated practice that replaced heavyweight Fagan-style inspections, is poorly suited to the pace of AI-generated code and may not sur…
China's Cyberspace Administration of China (CAC) identified five major AI security risks at a September 1 press conference for the 2026 National Cybersecurity Awareness Week, according to Deputy Director-General Wang Lih…
Uber Engineering reports that more than 70% of its pull requests are now attributed to local or cloud agents, with engineers creating more than 3,600 reusable agent skills and more than 30,000 skill executions per day, a…