Фото: John Turner / U.S. Air Force / AP
format!("{git_hash}-dirty-{secs}")，详情可参考立即前往 WhatsApp 網頁版
，这一点在谷歌中也有详细论述
If you make one mistake, you’ll most likely get a pass from your client because of the loyalty you built over time. But once this becomes a pattern, your customers will no longer believe in you and will leave. Even worse, they will tell others about their experience and that your word or that of your company doesn’t ring true, damaging your reputation. In today’s social media environment and the world of Google and Yelp reviews, it’s easy to knock a brand down.，详情可参考官网
Feedback loop is too slow and context is bloatedSome of the work I'm doing right now requires parsing some large files. There's bugs in that parsing logic that I'm trying to work through with the LLM. The problem is, every tweak requires re-parsing and it's a slow process. I liken it to a slot machine that takes 10 minutes to spin. To add insult to injury, some of these tasks take quite a bit of context to get rolling on a new experiment, and by the end of the parsing job, the LLM is 2% away from compaction. That then leads to either a very dumb AI or an AI that is pretending to know what's going on with the recent experiment once it's complete.