When a conversation with Codex approaches its context window limit, using `/new` erases all history. The `/compact` command is a better alternative. It instructs the LLM to summarize the current conversation into a shorter form, freeing up tokens while retaining essential context for continued work.
Related Insights
The all-caps `clod` file, created via the `init` command, stores project structure and user-defined rules. Unlike temporary in-chat instructions that get lost or degraded as the conversation continues, this file is referenced in every session, ensuring consistent behavior and enforcing project-wide guardrails.
Human developers may prefer longer files, but AI coding assistants process code in smaller chunks. App developer Terry Lynn intentionally keeps his files small (under 400 lines) to reduce the AI's context window usage, prevent it from getting lost, and improve the speed and accuracy of its code generation.
People struggle with AI prompts because the model lacks background on their goals and progress. The solution is 'Context Engineering': creating an environment where the AI continuously accumulates user-specific information, materials, and intent, reducing the need for constant prompt tweaking.
When an AI coding assistant gets off track, Tim McLear asks it to generate a summary prompt for another AI to take over. This "resume work" prompt forces the AI to consolidate the context and goal. This summary often reveals where the AI misunderstood the request, allowing him to correct the course and restart with a cleaner prompt.
When an AI model gives nonsensical responses after a long conversation, its context window is likely full. Instead of trying to correct it, reset the context. For prototypes, fork the design to start a new session. For chats, ask the AI to summarize the conversation, then start a new chat with that summary.
Long, continuous AI chat threads degrade output quality as the context window fills up, making it harder for the model to recall early details. To maintain high-quality results, treat each discrete feature or task as a new chat, ensuring the agent has a clean, focused context for each job.
Instead of manually rereading notes to regain context after a break, instruct a context-aware AI to summarize your own recent progress. This acts as a personalized briefing, dramatically reducing the friction of re-engaging with complex, multi-day projects like coding or writing.
Don't pass the full, token-heavy output of every tool call back into an agent's message history. Instead, save the raw data to an external system (like a file system or agent state) and only provide the agent with a summary or pointer.
Long conversations degrade LLM performance as attention gets clogged with irrelevant details. An expert workflow is to stop, ask the model to summarize the key points of the discussion, and then start a fresh chat with that summary as the initial prompt. This keeps the context clean and the model on track.
Codex lacks formal custom commands. You can achieve the same result by storing detailed prompts and templates in local files (e.g., meeting summaries, PRD structures). Reference these files with the '@' symbol in your prompts to apply consistent instructions and formatting to your tasks.