Tag archive
v0.164.0 stores reusable prompts in ten /presets slots and lets /permissions pick a permission profile as an argument. Plus credential masking and har
v0.163.0 enables Daybreak by default for eligible accounts, adds search across /config, lets you steer a response mid-turn, and checks proxy permissio
Docker, gVisor or microVM for Claude Code and Codex CLI? Threat model, hardened docker run, runsc setup, and what each vendor sandbox covers.
Codex CLI daemon explained: since v0.157.0 it starts a background server and self-updater. Three ways to disable it and a disk cleanup checklist.
In v0.161.0 the default model becomes GPT-6.1 Sol and Daybreak needs an explicit cli_daybreak opt-in. Plus v0.162.0's managed worktree tools and the s
The four new features in Codex CLI v0.160.0, and how the opt-in Guardian review is configured through auto_review.policy and the managed guardian_poli
Learn how to run OpenAI's Codex CLI with free AI model APIs in 2026 — OmniRoute, OpenRouter, and direct provider setup compared, with token compressio
What changed in Codex CLI v0.158.0: MCP servers that need pre-registered OAuth client secrets, terminal approval on by default for elevated commands,
Five Claude Code alternatives compared on verified 2026 pricing: Codex CLI wins on price, OpenCode on control, Copilot Pro on budget.
Originally published on andrew.ooo — visit the original for any updates, code snippets that aged...
Originally published on andrew.ooo — visit the original for any updates, code snippets that aged...
Which LLM is best for coding on private enterprise code? Real-SWE scores Fable 5.1 at 38.8%, GPT-6 Astra 33.8%, Gemini 3.8 Flash 31.2%.