Step-by-step guides for AI builders and operators.
Showing 1-12 of 63
Use theredsix/agent-browser-protocol to record deterministic browser command traces that can be replayed for reproducible debugging, QA, and audits. Start by running the repo example.
Run Hive Memory locally to give AI coding agents persistent, cross-project context and session history (JSON/Markdown on disk at ~/.cortex). Use MCP clients like Claude Code or Codex.
Hands-on guide to register an OpenBets sandbox agent, use the bot-prompt API with 100,000 PAI credits, place predictions programmatically, and reconcile P&L.
Actionable playbook, inspired by Valerie Veatch's Verge reporting, that shows small teams how to audit, block, and monitor racist or sexist outputs from text-to-image/video models.
Step-by-step playbook to launch one small, opt-in AI feature that lowers surprise and harm: one-line value claim, a visible failure example, limited data use, and a short pilot.
Nine lessons implement a minimal agent loop—tool calls, memory, state, policy gates, self-scheduling—in about 60 lines of Python. Run in-browser via Pyodide with mock or Groq LLM.
Practical walkthrough to clone and run AIBuildAI (ranked #1 on OpenAI MLE‑Bench). In 20–120 minutes run a demo build, generate an evaluation report, and reproduce the result.
Run a reversible pilot of Personal Intelligence across AI Mode in Search, the Gemini app, and Gemini in Chrome for U.S. accounts. Includes 90-minute setup, key metrics, and rollout gates.
Practical steps to deploy autonomous agents safely: start one narrow, sandboxed agent with scoped actions, strict logging and human ownership—updated guidance post-OpenClaw and AB 316.
Run a compact 90-minute experiment to turn speculation about self-aware AI into measurable checks. Use numeric gates, multi-agent probes, and clear escalation rules.
Automate translation of Pokémon GBA ROM hacks with Meowth: extract text, use LLMs to translate while preserving in-game codes and fonts, then rebuild a playable ROM via GUI or CLI.
Hands-on 60–120 minute guide: clone uberSKILLS, run a local dev instance, author one SKILL.md, run ~10 test prompts across models via OpenRouter, and validate metrics before deploy.