Full-text search across 61590 articles. Combine with topic and date filters; results sorted by relevance.
A developer built a small benchmark to compare LLMs for coding tasks across Python, C#, and Bash. All three models achieved 100% pass@3 on problems they were allowed to answer, but one model was content-filtered on four …
AI Arcade pits coding models against each other to build arcade games from identical prompts without human input, with results including a rune puzzle, a dashing game, Snake, and a meteor shooter. The initiative showcase…
Developer Theo reports that GPT-5.6 Ultra performs better in Anthropic's Claude Code than in OpenAI's Codex, expressing frustration over the discrepancy.
A developer built Draco AI, a full-stack, hardware-agnostic LLM system from scratch in pure Python and NumPy, eliminating heavy framework dependencies like PyTorch or HuggingFace. The system is 100% open-source across it…
MarkTechPost published a tutorial on building an autonomous data science agent using DeepAnalyze-8B, sandboxed code execution, and iterative analysis. The agent runs on a T4 GPU in Colab, processes e-commerce data, and g…
A promotional message about Fable 5 usage limits that was previously displayed in Claude Code has disappeared, according to a user report. The message had informed users that through July 12 they could use up to 50% of t…
A Hacker News user asks whether AI will make English more uniform, drawing a parallel to how Python standardized source code. The post questions if this uniformity would improve understandability and invites discussion o…
Meta is upgrading its Muse Spark AI model to compete with Anthropic and OpenAI in the AI coding market, led by AI chief Alexandr Wang.
Engineering teams are increasingly building in-house AI code review tools using large language models, but while prototyping is easy, operational challenges and hidden costs are significant.
JetBrains announced JetBrains AI for Teams and Organizations, a governance layer for AI coding tools that connects existing AI agents and CLIs with shared context, automations, and cost controls. The suite, rolling out i…
IBM Developer Advocate Rosemary Wang discusses the future of infrastructure-as-code as AI begins to write and deploy it, exploring how the role of IaC may evolve.
Atlases is a learning site featuring 16 interactive technical guides that run real code in the browser, including SQLite, CPython, and C++ compilers. Built by a developer using Claude as a pair programmer, the site offer…
A developer argues that reviewing AI-generated code line by line is impractical, comparing it to analyzing movies frame by frame, and suggests such approaches are doomed to fail.
A developer built a meaning-learning engine that uses 2-bit ternary values instead of LLMs or embeddings. The system learns purely from word co-occurrence, requires no hard-coded linguistic rules, and works across langua…
A Hacker News user asks whether renowned open-source software projects have begun allowing AI-generated pull requests, known as "vibe-coding," to be merged. The question references a rejected AI-generated PR to the OCaml…
Theo Browne published a guide for running GPT-5.5 as a subagent within Claude Code workflows, ranking models by cost, intelligence, and taste. The approach uses GPT-5.5 for bulk mechanical work via the Codex CLI, while r…
Alessio Fanelli, founder of Kernel Labs and co-host of Latent Space, demonstrates two AI workflows: an autonomous coding setup using OpenAI Symphony and Linear as an agent state machine, and a Codex-based system that aut…
A new leaderboard for AI coding models on WebDev Arena shows that only one of the top 18 models is not Chinese, highlighting China's dominance in front-end web development AI. The top-ranked model is Anthropic's Claude F…
A developer at Mattrx, a multi-tenant marketing-analytics SaaS built on .NET 9 and Azure, reports that adopting the Model Context Protocol (MCP) eliminated 14 point-to-point integrations by replacing them with 3 MCP serv…
A user named Maleeha Riaz reports a persistent DNS resolution error for api-inference.huggingface.co while attempting to complete the final coding quiz of Hugging Face's LLM course, preventing certification despite troub…