Full-text search across 65148 articles. Combine with topic and date filters; results sorted by relevance.
Kotro, a single-binary local proxy for MCP-native agentic AI, claims to reduce upstream billed tokens by up to 99.3% in a benchmark by preserving request-shape stability for provider prefix caching, while blocking prompt…
A benchmark testing five AI models across 13 real Ruby codebases found that agents equipped with a structural code map achieved a mean cited recall lift of +0.26 for Claude Opus 4.8, with gains concentrated on hard depen…
A new open-source project, BillAI Bass, turns a Big Mouth Billy Bass toy into a real-time voice assistant using Strands Agents bidirectional streaming agents on a Raspberry Pi 5, streaming live audio to and from Amazon N…
OpenAI released GPT-5.6 with three tiers—Sol, Terra, and Luna—each offering different price-performance levels. The flagship Sol is 54% more token-efficient on AI coding tasks than previous models, and a new "ultra" mode…
A developer argues that tech companies' obsession with AI speed contradicts their interview demands for manual coding from memory. The developer claims that knowing how to read and understand code, rather than writing it…
Entire, an open-source distributed git tool for AI coding agents, launches to store full agent sessions—including prompts and tool calls—alongside code commits, enabling agents to trace decisions and avoid repeating mist…
Researchers have found that large language models (LLMs) can generate diverse software code, potentially reducing common-mode failures, but reliability improvements depend on programming language and generation settings.…
Researchers are exploring retrieval-augmented generation (RAG) and constrained decoding (CD) to improve large language models' ability to generate accurate web API integration code. While RAG reduces hallucinations but o…
Researchers have developed a reference-free evaluation framework for Vision-Language Models that converts flowchart images into code, using OCR and visual entailment to assess output quality without ground-truth data. Va…
OpenAI and Snowflake announced the private preview of OpenAI GPT 5.6 on Snowflake Cortex AI, making the latest frontier model available within Snowflake's secure perimeter for enterprise use. The GPT 5.6 series includes …
SpaceXAI launched Grok 4.5, its first model trained with AI company Cursor, claiming it excels at coding, agentic tasks, and knowledge work. The model is now the default for the Grok Build coding agent and is priced at $…
Researchers introduced agent data injection attacks (ADI), a new category of indirect prompt injection that disguises malicious data as trusted data to trick AI agents into executing unintended actions. The attacks bypas…
GitHub has made the open-weight Kimi K2.7 Code model available to Copilot Business and Enterprise plans as of July 1, 2026. The model, hosted on Microsoft Azure, offers a lower-cost option for coding workflows and is bil…
A developer created a Context Engineering Framework that treats the AI context window as a budget rather than a junk drawer. The framework, hosted in the ai-assistant-dot-files repo, defines canonical agents, skills, and…
Kennel 1.0.0, a native desktop app for managing multiple AI CLI agents side by side, has been released. The app allows users to run, organize, and persist sessions for tools like Claude Code and Kiro CLI, with sessions s…
A developer with 30 years of product experience released Mycelium, a plugin for coding agents that guides product development from purpose to market by validating ideas before writing code. The plugin aims to prevent bui…
A developer built Madame Minou, a French cat astrologer app, using Kiro and Amazon Bedrock during a Paris hackathon. The app computes a cat's sun sign deterministically in code, then uses AI to generate a reading based o…
Craig Riggins launched Ox, an AI agent that reviews code changes to catch technical debt before it is committed, aiming to prevent the explosion of tech debt from AI-generated code. The tool integrates via CLI or GitHub …
OpenAI announced its first hardware product, the Codex Micro, a macro pad built with Work Louder for users of its AI coding tool Codex. The device, teased on July 15, is a niche accessory for developers who code by chatt…
A developer explored loop engineering, a pattern where coding agents repeatedly execute tasks until a goal is met, and assessed its relevance for frontend and fullstack developers. The developer demonstrated the concept …