Tell codex to maintain a scratch-log while it works on bigger refactors with decisions it had to make, tradeoffs, review fixes, so later on you can read through which tradeoffs the agent made, what you forgot to specify etc.
SOFTWARE
-
Refactoring subagents with autoreview running for 5 hours fixing issues
By
–
I'm refactoring an older part of the codebase (subagents) that touches a lot of code, and autoreview is running for 5h already and fixing tons of issues. https://
github.com/openclaw/agent
-skills/blob/main/skills/autoreview/SKILL.md
… -
Anticipation of GPT-5.6 release, hopes for better vibe
By
–
Looks like GPT-5.6 release is very close. Really looking forward to it. 5.5 already is an insanely good model. Hope it gets a bit better vibe tho
-
Added multiplayer and AI understood to be quiet
By
–
I added multiplayer and told codex to shut up, and it was smart enough to understand the situation. xD
-
Cloud codex runner using Cloudflare Firecracker and Ghostty
By
–
Still limited by compute, so I built a thing that runs codex in the cloud, powered by @Cloudflare firecracker boxes (and since that's not beefy enough for larger projects, tests are run via crabbox) Uses Ghostty ofc, via WebAssembly.
Codex replicated itself, basically. -
Are Linear ticket agents like OpenAI Symphony?
By
–
Agents from linear tickets, so like https://
github.com/openai/symphony ? -
Codex for building and debugging iPhone simulator end to end
By
–
Codex for building and debugging an iPhone simulator end to end: https://t.co/qA5WlK0OzA
— Greg Brockman (@gdb) 23 mai 2026Codex for building and debugging an iPhone simulator end to end:
-
llmfit CLI tool auto-detects hardware and ranks 206 models by VRAM
By
–
Stop guessing which models fit in your VRAM! llmfit is a CLI tool that auto-detects your hardware and ranks 206 models by what actually runs on your system. You download a 70B model and hope it fits. Or you estimate memory requirements across quantization levels and still end
-
FASTER: Reacting Quickly to Changing Environments
By
–
Why can't robots react instantly to fast-changing environments? Researchers from HKU and ACE Robotics introduce FASTER. Instead of running all sampling steps before any movement, it uses a Horizon-Aware Schedule to compress the immediate action into a single denoising step.
-
Defending Claude Code’s code as logical and elegant
By
–
Bullshit Nothing ugly about code Claude Code writes, it's logical and elegant