It's Not Just True, It's False

We’ve given in to using LLMs for writing at work. From emails and Slack comments to full-on documentation, everything is AI-generated. However, I’ve realized it only ever saves me time when I’m being lazy. That is, it’s great at converting meetings into transcripts, summarizing those transcripts into action items, and keeping information accessible. But it’s pretty bad because the result is ridden with invisible errors. But what counts as an error if you trust the LLM and never meticulously read the output? And how much time are you really saving if you end up spending that time proofreading? I went back to a meeting transcript after a developer struggled to turn my AI-generated summary into a coherent ticket. Looking through the source transcript, I noticed that at one point it recorded the word "embroidery." I mean, we work for a large telecom company, the chances of me using that word are slim to none. Nevertheless, the AI summarized the conversation and included "embroidery" as an…

Commenting on Bubbles has been removed. Why? If you want to talk about this post, write to the author, use the comments on their blog if it has them, or reply with a "RE:" post on your own blog. Suggestions? feedback@bubbles.town