A developer has created a new LLM skill called 'pragmatic-context' that enables AI models to infer sarcasm, jokes, hyperbole, roleplay, and indirect intent from conversational context. The skill instr…
A developer's independent analysis of reasoning prefills on open models finds that Kimi K3 shows a significant accuracy increase on Humanity's Last Exam questions when prefilled with Opus 4.8 reasonin…
Lucid, a new output style for Claude Code, reduces jargon and rambling to make responses easier to understand in one pass, lowering the reader's cognitive load. The style keeps coding instructions int…
A developer contributed optimizations to llama.cpp for AMD's gfx1151 GPU, specifically targeting Qwen3.8 27B's SSM convolution input pattern. The patch introduces a fast LDS-transpose path for dim-0 c…
A developer released pi-ds-anchor.ts, an extension for the Pi coding agent that adds two commands—/new-ds-anchored-session and /ds-anchor—to send a tool-free 'who are you' probe with a minimal system …
A developer from the gilgeekify programming channel has published a tutorial on crafting prompts for ByteDance's Seedance 2.5 AI video model. The guide details a workflow for generating cinematic acti…
AgentRouter, a non-profit unified LLM API gateway, is offering developers $200 in free credits upon signup via referral links, with no credit card required. The platform provides a single API endpoint…
A developer benchmarked the Qwen3.8-27B model with NVFP4 quantization and multi-token prediction (MTP) on an RTX 5090, comparing tier configurations and sweeping spec-draft-n values at 64K context. Th…
A developer created review-with-me, a Claude Code skill that runs an automated code review in the background, quizzes the human on the diff, and then reconciles the findings with the human's answers b…
Developer Matt Pocock shares five agent skills he uses daily to enhance AI coding assistants like Codex, covering research, design review, React best practices, code simplification, and end-to-end tes…
A developer has released a clone-and-run launcher that runs LTX-2.5 text-to-video generation locally on Apple Silicon in a single command, with audio support and no need for ComfyUI or CUDA. The launc…
A developer created a bash script, claude-history.sh, that lists recent Claude Code sessions across all project directories, sorted by the last activity timestamp recorded inside each transcript rathe…
A developer has built an agent-maintained knowledge graph wiki using the Open Knowledge Format (OKF), extending Andrej Karpathy's LLM Wiki pattern. The system compiles typed subject-predicate-object t…
A developer has released 'the writing whip,' a Claude Code skill designed to eliminate AI writing tropes and response behaviors at the generation stage. The skill enforces strict rules against preambl…
Techartist, a developer on CodePen, has created a bioelectric consciousness engine using Three.js, WebGL, and GLSL. The interactive visualization allows users to click anywhere to trigger signals, whi…
A developer reconstructed a blueprint for a personal AgentOS from Danny Postma's talk on building an agent control plane using Anthropic's Claude Agent SDK. The system automates coding and operational…
Kunal Khatri documented a step-by-step guide for building a Kanban board for incidents in ServiceNow's UI Builder (Next Experience), using the Kanban Board component from the sn-vtb library. The board…
GenAI Foundations & Prompt Engineering for Developers is a technical session that teaches developers how to build with generative AI, covering prompt engineering techniques and foundational concepts. …
A developer shared a workflow for using AI agents to test software, emphasizing that AI must prove its work with raw evidence before marking tasks complete. The method involves creating a detailed tes…
A developer documented how to use opencodex models in T3 Code through Claude Code, resolving a misleading model-access error. The fix involves setting ANTHROPIC_BASE_URL and CLAUDE_CODE_ENABLE_GATEWAY…