Full-text search across 67646 articles. Combine with topic and date filters; results sorted by relevance.
A developer known as workofart has created a PyTorch-like framework for training AI agent harnesses, achieving a 45-minute experiment cycle on terminal bench tasks by enforcing deterministic inference via SGLang on NVIDI…
A developer released agent-starter, a tool that enforces safety hooks and lint rules on AI coding agents in a single command. The tool blocks dangerous commands like git push --force, catches silent error swallowing, and…
OpenAI's GPT-5.6, offered as three separate models—Sol, Terra, and Luna—outperforms Anthropic's Claude Fable 5 on key benchmarks at lower cost, according to a review by Decrypt. Sol costs $5 per million input tokens and …
The AI-Driven Development Manifesto (AIDD), a set of four values and twelve commitments by developers against vibe coding, risks adding inertia to agentic engineering by grafting AI onto existing lifecycles rather than r…
Together AI has open-sourced Hallmark, a design tool that forces AI coding assistants to generate unique, hand-crafted interfaces instead of generic 'AI slop.' Built by Hassan El Mghari (Nutlope), Hallmark runs 57 design…
Google Cloud COO Francis deSouza announced that AI-powered defenders now have a decisive advantage over attackers by leveraging deep enterprise context, citing the first known AI-built zero-day exploit documented by Goog…
Whale, an open-source AI coding agent built specifically for DeepSeek, achieves approximately 98% prompt cache hit rates, drastically reducing costs to pennies per session. The tool supports long context (1M tokens), too…
Inkling, a new open-weights AI model with 975B total parameters and 41B active parameters, has been released by an unnamed organization to advance its mission of building AI that extends human will and judgment. The mixt…
SendLang, a new domain-specific language for email automation, lets developers define email segments with SendQL and lifecycle workflows with SendFlow as plain-text files that live in version control. The language is des…
Microsoft released two open-source tools in May — RAMPART and Clarity — to help developers test AI agents for adversarial failure modes before deployment. RAMPART is a pytest-native framework for writing and running safe…
An indie hacker spent a month testing Chinese AI APIs from DeepSeek, Qwen, Kimi, and GLM, finding that DeepSeek V4 Flash offers 95% of GPT-4o quality at 2.5% of the price. The developer recommends DeepSeek for code gener…
Cdbx.ai launched an AI-powered browser IDE that lets users describe, build, and publish apps without setup or coding experience. The platform features a full Monaco editor, real terminal, AI agents for planning and self-…
Kairos, an experimental local-first AI agent platform, has released an early MVP featuring goal mode, guarded swarms, smart model routing, memory, tools, and a bundled AI skills library. The terminal-based system support…
Refuse, an open-source tool that intercepts package manager calls to block vulnerable installs before they execute, launched to address a structural gap in AI coding agent workflows. The tool installs 18 shim binaries co…
A systems researcher argues that AI-assisted coding has decoupled software development speed from importance, leading to frequent failures with wide blast radii in critical infrastructure. The author calls for 'slow soft…
A developer created PerformanceAgent, an open-source AI strength and conditioning coach that runs inside AI agent CLIs like Claude Code. The tool uses a deterministic Python engine for calculations and a verified local e…
A guide explains how to build a semantic memory system for AI agents using local vector databases and embedding pipelines, drawing on lessons from the Hermes Agent experiment. The system comprises three layers—storage, e…
Databricks announced the Public Preview of Feature Views, a managed framework for building, serving, and governing ML features within its platform. The feature allows data scientists to define feature logic once and auto…
OpenAI released GPT-5.6 Sol, along with Terra and Luna, after a limited launch. CEO Sam Altman told CNBC the model is 54% more token efficient on agentic coding tasks and performs as well or better than competitors. The …
Multiple critical vulnerabilities in Langflow and Dify AI agent platforms have enabled remote code execution and data exposure, with one Langflow flaw exploited within 20 hours of disclosure. Security experts warn that c…