Tailscale, tmux, mosh, and a mobile terminal let me steer long agent runs from my phone. Why that plain stack still outperforms Remote Control for me, for now.
Claude Code users approve 93% of permission prompts, so manual mode and bypass converge. What prevents catastrophe is the environment I run in, not the flag.
Karpathy's LLM wiki: point a coding agent at a markdown folder and let it maintain the knowledge base. What it is, why it earns its place, and how to set it up.
Karpathy's autoresearch runs an AI agent in a keep-or-discard loop. I examined its techniques, then applied the loop to parameter search where a grid stalls.
A maintained third-party reference to Claude Code: the agentic loop, built-in tools, context window behavior, environments, safety model, and extension layer.
A maintained third-party reference to OpenAI Codex: the CLI, IDE, cloud and app surfaces, AGENTS.md configuration, skills, MCP support, plans and access.
Fable 5 returned at double the price of Opus 4.8, with days-long autonomy as the headline capability. A comparison with Claude Code's /goal loop, sourced.
An honest Codex CLI vs Claude Code comparison from running both daily on one codebase: strengths, config interop, and the two-model workflow that emerged.