When NOT to use /goal in Codex
This transcript explains when not to use the /goal command in Codex, outlining three scenarios where it is inappropriate. It also defines the three key properties that make a goal well-suited for the tool: a durable objective, an evidence-based finish line, and a multi-turn path.
Summary
The speaker opens by cautioning that /goal is not a universal tool and should not be applied to simple, one-line edits. The reasoning is that /goal is designed for outcomes rather than outputs — it is too heavy a mechanism for trivial tasks.
The speaker then identifies vague or unmeasurable objectives as another poor fit for /goal. Examples given include 'make my customers happy' and 'refactor this code,' both of which lack a clear, definitive completion condition that can be reliably measured. Without measurability, there is no way to confirm the goal has been achieved.
Finally, the speaker outlines the three properties that make /goal most effective: (1) a durable objective that remains steady over time, (2) an evidence-based finish line that can be measured, and (3) a path that requires multiple turns of investigation to complete. When all three properties are present, /goal is the right tool for the job.
Key Insights
- The speaker argues that /goal is too large a tool for simple, one-line edits, emphasizing that it is designed for outcomes rather than outputs.
- The speaker claims that vague goals like 'make my customers happy' are poor candidates for /goal because they lack a reliable, definitive completion condition.
- The speaker identifies 'refactor this code' as a bad example for /goal, implying that goals without measurable endpoints are not appropriate for the tool.
- The speaker states that /goal works best when the objective is durable — meaning it stays steady over time rather than shifting during execution.
- The speaker argues that /goal is strongest when reaching the objective requires multiple turns of investigation, distinguishing it from tasks solvable in a single step.
Topics
Transcript
[0:00] Goals are not the right tool for every job. Do not use goal for something that is a very simple one-line edit. It is just too big of a tool for the job. Your goal wouldn't be like, "Make sure this line of code is removed." You really want an outcome, not an output, almost, for it to be a good goal. Also, don't use a goal when the finish line is vague. If you're like, "{slash}goal make my customers happy." I think that is just a very vague goal. It's very hard to measure, and there's no reliable, [0:30] definitive completion condition. And so, that's not very good. The other example they give is like, "Refactor this code."…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
What are channels in Claude Duet?
Claude Duet features a channels system inspired by Slack that allows users to organize conversations into separate subthreads within a main chat. This enables more structured collaboration by creating dedicated channels for specific projects, such as a sales channel for sales-related work.
Claude Duet needs multiplayer (please!)
The speaker argues that Claude and similar AI products are currently optimized for single-player use and lack proper multiplayer capabilities. Despite integrations like Claude tags and Slack, the speaker contends that sharing agents with their small team of five people remains problematic, preventing these tools from becoming part of their regular workflow.
Claude Duet is great, but SLOW
The speaker expresses frustration with the slowness of AI model Claude, which impacts their willingness to engage with it. They compare its responsiveness unfavorably against more responsive alternatives, despite acknowledging Claude's capabilities.
Claude Duet should be more annoying
The speaker emphasizes the need for agents like Claude Duet to be more engaging and proactive to avoid being forgotten in the competitive landscape of digital assistants. They critique the current methods of communication, such as morning briefings, as ineffective in attracting user interest.
A perfect TikTok cut from a one sentence prompt
Claude code automatically transforms a single sentence prompt into a polished, TikTok-ready short-form video with captions, jump cuts, and zooms in approximately 4 seconds with no manual editing required. The tool demonstrates AI's capability to understand and execute high-quality short-form video production autonomously.