GPT_Handover_Prompt.md
Christiane Wiemann published a two-step prompt workflow on frauwiemann.de for converting a ChatGPT conversation into a structured Markdown handover document. The first prompt casts the model as a proj…
Christiane Wiemann published a two-step prompt workflow on frauwiemann.de for converting a ChatGPT conversation into a structured Markdown handover document. The first prompt casts the model as a proj…
A developer built a kernel that keeps a running Lisp world alive while an external controller queries an OpenAI model for the next action to try. The model never edits memory directly; it proposes a s…
A developer outlined a blueprint for "Hermes," an operations copilot built on GitHub Copilot for a wood-interior design and fabrication studio, designed to convert customer inquiries into checked proj…
A developer published instructions for stripping OpenAI Codex's built-in confirmation layers on macOS, disabling the bundled computer-use skill, the Chrome plugin's confirmation and browser-safety doc…
A developer published a Python script that automates extracting Google Gemini activation links from Jio's OTT subscription flow, using the Jio recharge and login APIs to check numbers, send and verify…
A developer published a lightweight inter-agent coordination SOP that lets multiple Claude Code sessions running in separate Git worktrees exchange SHA-pinned handoffs, acknowledgments and review phas…
A developer built Wasteland Wire, a working Mad Max fan site that aggregates real headlines from public RSS feeds, using the Gas Town multi-agent orchestration CLI to dispatch a single Claude-powered …
Backend lead and architect Jawad Ul Hadi built Omni.io, a multi-tenant RAG customer-support engine on NestJS, PostgreSQL with row-level security and pgvector, BullMQ, Gemini and React, designed so tha…
A developer released YSH Terminal v8.1.4, a Java Swing-based command-line emulator that implements an in-memory file and folder system, a note-taking subsystem, LAN chat and file sharing over sockets …
A developer released caffeinate-ai, a zsh script that keeps macOS from idle-sleeping while monitored applications such as ChatGPT and Codex are running, targeting long agentic coding sessions. The too…
Developer ruvnet published a field guide to building Claude Code mods, plugins that hook the engine's events to block or rewrite tool calls, add slash commands and tools, and render custom UI such as …
A developer published AGENTS.md, a set of operating instructions for AI coding agents that emphasizes asking clarifying questions, preferring simple and maintainable solutions, and using retrieval-led…
A developer documented running two unlocked NVIDIA CMP 170HX mining cards (GA100, A100-class) for LLM inference on a single AMD EPYC 7443 / ASRock Rack ROMED8-2T host, unlocking them to 64 GB and 74 S…
A developer published a set of gcloud commands for adjusting BigQuery's generative AI token quotas, covering daily input and output token limits both per project and per user. The snippets use `gcloud…
A developer published guidance for configuring Codex subagents, instructing that both the model and reasoning effort be set explicitly at spawn time rather than inherited from the parent. The flow map…
A hands-on one-semester course walks students through building a machine-learning compiler from scratch, progressing from elementwise operations to training a real LLM on GPUs. Over roughly ten weeks,…
A developer has contributed a QEMU patch that lets the vmapple machine model boot macOS 14 and later guests, which previously stalled in the kernel's first instructions. The fix patches 19 "cbnz x0, .…
A developer documented a fix for ray tracing, path tracing, DLSS and frame generation in The Witcher 3: Wild Hunt version 5.0 under Proton on Linux, tracing the failures to a deliberate Wine-detection…
A developer published a set of design constraints intended for AGENTS.md or CLAUDE.md files to improve AI coding agents' C++ output, anchored on the GNUS C++ Coding Standards as the authoritative refe…
A developer known as @danisherror has published a self-directed M.Tech program in Networked Systems & Security for AI Infrastructure, a two-year, four-semester self-study curriculum of roughly 15 hour…