Full-text search across 63204 articles. Combine with topic and date filters; results sorted by relevance.
Val Town, a vibe coding platform, has implemented Dynamic Client Registration (DCR) and Client ID Metadata Documents (CIMD) to enable any app to dynamically authenticate and authorize any other app, solving the n² proble…
Aplexica, a new local open-source application, enables cross-agent state portability for AI coding agents, allowing users to switch between agents like Claude Code and Codex without losing memories, skills, tools, or con…
Kilo Code for JetBrains has launched a new multi-agent control room that allows developers to run multiple coding agents in parallel, each with its own isolated git worktree, and run results using existing Run Configurat…
A developer's analysis of three AI agent harnesses—Claude Code, OpenAI Codex, and Pi—reveals that despite differing codebases and languages, all implement the same five-step agent loop, with file sizes ranging from 794 t…
David Heinemeier Hansson, creator of the Ruby on Rails framework and CTO of 37signals, told Lex Fridman in a five-hour interview posted August 26 that AI agents wrote all the code shipped in Omarchy Quattro, the Arch Lin…
A new subscription tier list ranks OpenAI's ChatGPT as the top value for coding tasks, with Anthropic's Claude Code and Moonshot's k3 also scoring well, while DeepSeek offers the cheapest API pricing but lower intelligen…
Karan Kurani, an independent developer, introduced CareLoop, an experimental 'Third Party Agentic App' (TPAA) that runs inside AI agent harnesses like Claude Code and Codex, shifting app development from coding to defini…
Z.ai will release the full GLM-5.3 model weights on Hugging Face on August 28th, exactly two weeks after the Tsinghua-born AI lab introduced the coding and reasoning model, following a safety delay prompted by unexpected…
MotherDuck released a new CLI that lets users and AI agents create organizations, run queries, publish pipelines, and deploy dashboards directly from a terminal, with a single command enabling setup without a browser. Th…
A practitioner community for AI coding assistants can save developers roughly six hours per week in context-switching time and reduce downstream QA rework by an estimated 30%, according to a firsthand account comparing C…
GitHub spent seven and a half hours down on Monday, taking Pull Requests, Actions, and Copilot with it, while security firm Wiz claimed its autonomous 'Red Agent' broke into Snowflake's internal Jira through a bug it bla…
Together Compute's DeepSWE benchmark shows GLM-5.3 solving 87.6% of coding tasks for about $16, outperforming Fable 5's 69.7% at $21.63, though the GLM result came from four attempts. The Financial Times reported the sam…
Elastic, the Search AI Company, is hiring a Lead Salesforce Full Stack AI Engineer in Bangalore, India, for an on-site role that requires 12+ years of experience and daily use of AI-assisted coding tools such as Cursor, …
The Go programming language released version 1.27 on Wednesday, expanding generics to support methods and adding features to simplify work with structs and type inference, which may save developers time but could make co…
Ornith 1.5 9B, a 9-billion-parameter dense language model from ornith-ai, failed real-world agentic and coding tasks in a local test on a single Nvidia A100 GPU, despite benchmark claims that it rivals or beats Qwen 3.5 …
Anthropic's 2026 Agentic Coding Trends Report reveals that engineers use AI in roughly 60% of their work but can fully delegate only 0–20% of tasks, highlighting the need for AI agents to integrate with developer workflo…
GitKraken released GitLens 19 on August 14, transforming the Commit Graph from a read-only viewer into an interactive workbench with AI-powered features, including AI agent monitoring for Claude Code, AI-assisted merge c…
Loveyourclanker.org has published a guide cataloging five distinct patterns for interacting with AI coding agents, including Tab Completion, Full Vibing with Agent, Full Vibing in a Walled Garden, Plan Execute Check, and…
Anthropic has begun watermarking all text generated by its Claude models, applying the mark at the model level worldwide across all surfaces including the API, Claude Code, and third-party platforms like AWS Bedrock. The…
A developer replaced GitHub Copilot with a fully offline coding assistant running on a 16GB M4 Mac mini using Ollama and Qwen models. They found that a 7B parameter model is the sweet spot for chat and edits, while a 1.5…