I open sourced some of the tools I wrote lately to keep codex in check. github.com/steipete/agent-sc… runner: auto-applies timeouts to terminal commands, moves long-running tasks into tmux. committer: dead-simple state-free committing so multiple agents don't run across with add/commit stages. docs: lists all md files in /docs and motivates the agent to read docs as-needed. You'll need to tweak them for your own setup, don't blindly copy them. Point your agents at them and discuss to build your own workflow.

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models huggingface.co/papers/2510.0…

“Polaris Alpha,” the presumed GPT-5.1, is performing remarkably well in early tests - with high rate limits. GPT-5 was particularly important for OpenAI at release because it’s an extremely efficient model. So it wouldn’t surprise me if GPT-5.1 is even more efficient; a win-win situation for OpenAI.Sam keeps repeating that compute constraints are the biggest issue—and will continue to be—so they’re buying compute wherever possible. A focus on greater efficiency is therefore only logical.