Full-text search across 33542 articles. Combine with topic and date filters; results sorted by relevance.
Meta launched its first AI coding agent, Muse Spark 1.1, challenging Anthropic and OpenAI. The release aims to position Meta's Superintelligence Labs as a key player in the AI coding market, with new API accounts receivi…
A field report from OpenAI and academic partners shows AI coding agents can modernize neglected research software, achieving speedups of up to 60x, but the systems are 'eloquent, convincing, and confidently wrong in ways…
DeepSeek's V4-Flash-0731, a 284-billion-parameter Mixture-of-Experts model with about 13B active parameters per token, scored 50 on Artificial Analysis's Intelligence Index, one point below GLM-5.2 and GPT-5.6 Luna, and …
Supabase has open sourced Supabase Evals, a benchmark and framework for testing AI coding agents on real Supabase tasks, scoring agents such as Claude Code, Codex, and OpenCode on building schemas, debugging Edge Functio…
A software engineer who used AI extensively for coding reports that over-delegating to AI degraded his ability to write and reason about code, prompting him to build a Pong game from scratch using the Odin language and R…
A developer has built Telechat, an open-source, self-hosted alternative to Anthropic's Claude Code Channels for using Claude AI in messaging apps. Telechat supports Telegram, WhatsApp, Slack, and web chat, offers per-tok…
Agent-Manager, a terminal user interface that runs multiple AI coding agents side by side in tmux sessions, has been released by developer YoanWai. The tool supports Claude Code, Codex, OpenCode, and Grok Build out of th…
A developer has published a prompt that instructs coding agents like Claude Code to build a global skill that automatically generates short, on-brand 'what's new' product videos from UI changes in a work session. The ski…
An engineer built a system that lets them start coding tasks on Claude Code by speaking to an Amazon Alexa device. The main challenge was Alexa's eight-second response limit, which forced a design where the assistant ack…
Developer Pradipta released Wallfacer, a terminal session manager for Claude Code that indexes all AI coding sessions stored as untitled JSONL files under ~/.claude/projects/ into a local SQLite database, allowing users …
A new uncertainty-aware framework, OpenCoder, improves GPT selected-output correctness in repository-level code generation from 56.25% to 78.13% on the RepoExec-inline benchmark, according to a preprint on arXiv (2607.24…
A deep neural model combining multi-layer temporal convolution networks with label-wise attention improves medical coding accuracy, achieving a 9% increase in F-1 scores and a 28% increase in recall over the previous sta…
A developer at AgentsKit.io published a zero-dependency CLI called Agents Playbook that enforces coding rules for AI coding agents through executable gates rather than prose instructions. The tool allows teams to test in…
A new analysis of AI-coding agents finds they are isolating individual developers rather than aiding teamwork, with 79% of agentic pull requests reviewed and modified by the same person without a second set of eyes, acco…
ThinkFull, a Claude Code skill developed by SuperNotesOnline, activates 22 specialists in strategy, design, engineering, growth, and brand from a single markdown file without agents or pipelines. Users install the skill …
A developer released a 60-line PreToolUse hook that prevents Claude Code from editing protected files like .env, addressing the failure of prompt-based rules in CLAUDE.md to stop the AI from modifying sensitive files. Th…
A developer known as Skull Skills has released a framework called Skull that orchestrates multi-agent AI teams within a local environment using markdown files, without requiring API keys or external accounts. The system …
A developer's production SQL query generated by an LLM caused a performance death spiral, locking tables and spiking CPU to 98% due to a hallucinated index and a Cartesian product from a missing join condition. Benchmark…
Using AI coding tools like Claude Code or Cursor boosts development velocity but risks creating a 'decadent' workflow where developers skip architectural thinking, warns a developer. To counter this, the author advocates…
A new open-source tool called Qarinah reduces LLM coding agent context from over 442k tokens to about 5.6k tokens—a 98% reduction—by treating project knowledge as typed events with explicit relations like supersedes or b…