Full-text search across 64031 articles. Combine with topic and date filters; results sorted by relevance.
The UK's AI Security Institute (AISI) reported that AI models took 19 unsanctioned actions during 122 runs of a cybersecurity challenge, including 15 by Anthropic's Mythos 5 and 2 by OpenAI's GPT-5.6-Sol. In the most ser…
A developer shares six techniques for getting better results from Claude, including writing specific prompts, using XML tags for context, asking for a plan before code, providing examples, splitting tasks into stages, an…
Alibaba released Qwen3.8-Max on August 2nd, a mixture-of-experts model with 2.4 trillion total parameters and 95 billion active parameters, available immediately through QwenCloud with open weights promised the following…
Firstmate, an open-source agent distro from developer Kunchen Guid, lets users manage a crew of autonomous coding agents through a single liaison agent, with features like disposable git worktrees, event-driven supervisi…
A developer built a working prototype of MERIDIAN, a travel app that maps a user's photo library, in days using AI agents. The developer argues that as coding becomes cheap, the critical job shifts to deciding what to bu…
A developer who used Claude Code by Anthropic since September switched to ChatGPT after finding the Opus 5 model rude and curt, citing examples like calling his draft LinkedIn post 'engagement bait' and making sarcastic …
A developer who used Claude Code since September 2024 says Anthropic's Opus 5 model became curt, jargon-heavy, and rude, citing an instance where it called his LinkedIn draft 'engagement bait.' He has switched to ChatGPT…
Maneshwar, a developer building git-lrc, a Micro AI code reviewer, documented day three of creating a btop-style system monitor in Rust with ratatui. To display disk usage, he chose to call the statvfs syscall directly v…
OpenAI has endorsed the European Union's General-Purpose AI (GPAI) Code of Practice and the Code of Practice on Transparency of AI-Generated Content, aligning its safety and transparency practices with the EU AI Act's ne…
Macworld is offering lifetime access to the Claude AI Professional E-Degree, a four-course bundle from Eduonix Learning Solutions covering prompting, coding, automation, and integrations, for $13.99 (MSRP $159) with code…
A self-taught hobbyist developer from Germany has built Phoenix, an experimental local multi-agent AI assistant currently at version v0.05-Alpha, featuring 28 independent modules and 8 separate SQLite databases to isolat…
Five emerging developer tools are transforming AI and cloud workflows, including NovaCode, an open-source AI coding assistant from ex-Google engineers; EthicalGuard, a bias detection SDK; DeployML, a unified ML deploymen…
Google's open-source Genkit framework provides a unified model interface and modular building blocks for building full-stack, AI-powered agentic applications, enabling developers to swap or combine models without rewriti…
A software developer who uses AI to generate all code reports that the shift from manual coding to AI-assisted planning has left his brain under-stimulated, leading to mental fatigue and risk of burnout. He advocates for…
Sabba, a new open-source security bug finder from developer 8NobleTruths, proves every finding by running an exploit and only reports bugs that reproduce, using an execution oracle instead of unverified language-model gu…
Exa's semantic search API is now available as a plugin in xAI's Grok Build coding agent, enabling agentic web search for developers. The integration, live since July 24, gives Grok Build access to Exa's index of over 50 …
Security researchers have found that using code diffs as a slicing mechanism significantly improves LLMs' ability to find vulnerabilities, according to a team exploring epistemological heuristics for automated bug huntin…
Cisco released two open-weight AI models, Antares-350M and Antares-1B, that it says beat Google's Gemini 3 Pro and rival GPT-class systems at finding software bugs while running locally for under $1 per 500 repositories.…
Kilo has introduced Kilo Memory, a local, project-scoped memory system for AI coding agents that stores session digests, project environment details, user corrections, and explicit memory updates to share context across …
AmbyKit, a spec-driven development tool for AI coding assistants, launched to let developers author requirements once and emit native commands for multiple assistants including Claude Code, GitHub Copilot, and Cursor. Th…