Skip to main content
黯羽轻扬Keep Growing Daily

38 Failure Reflection: Large-Granularity Tasks Don't Equal Laziness

Paid1999-12-31

38 Failure Reflection: Large-Granularity Tasks Don't Equal Laziness Recently I've been trying to increase task granularity, handing bigger and more complex things to AI to handle However. Failed Here's roughly what happened, I told AI: Looking back, this time I made several typical major mistakes From the result perspective, the failure point was not understanding how to call Feishu API correctly, AI got completely tangled and couldn't get out, and incidentally tangled me up for 2 days... Reflection:

  1. Made the major taboo of wishful thinking: technical solutions can't be lazy, the requirement I wrote at best counts as technical direction, far from being a solution
  2. Made the major taboo of AI's weakness: Feishu multi-dimensional table, similar to HarmonyOS, too little corpus data, AI pre-training never saw this thing, relying solely on web search, far off, first step was wrong

38 Failure Reflection: Large-Granularity Tasks Don't Equal Laziness

Recently I've been trying to increase task granularity, handing bigger and more complex things to AI to handle

However. Failed

Here's roughly what happened, I told AI:

Looking back, this time I made several typical major mistakes

From the result perspective, the failure point was not understanding how to call Feishu API correctly, AI got completely tangled and couldn't get out, and incidentally tangled me up for 2 days...

Reflection:

  1. Made the major taboo of wishful thinking: technical solutions can't be lazy, the requirement I wrote at best counts as technical direction, far from being a solution

  2. Made the major taboo of AI's weakness: Feishu multi-dimensional table, similar to HarmonyOS, too little corpus data, AI pre-training never saw this thing, relying solely on web search, far off, first step was wrong

Purchase required to continue
This is a paid article. After signing in, your purchase will be unlocked automatically.
Buy now

Comments

No comments yet. Be the first to share your thoughts.

Leave a comment