There was a moment, not long ago, when “shadow AI” felt like a good-news story. Workers were sneaking ChatGPT and Claude past the IT department, using personal accounts to do what used to take hours in minutes. An MIT study published last year found that employees at more than 90% of companies were using personal chatbot accounts for daily tasks — often without approval — even as only 40% of those same companies had official LLM subscriptions. The shadow economy was booming. Management called it a governance problem. The workers called it getting the job done.
Now the data tells a different story. The tool that workers once raced to adopt covertly has become, for a large and growing share of the workforce, the tool they’ve stopped using altogether. Not because it doesn’t work. Because they’re afraid of what happens when it works too well.
