12
Last week my chatbot interview tool rejected a candidate for bad grammar when it was actually a typo in my prompt
I run a small recruiting agency in Austin and used an AI screener to filter applicants. It flagged someone as 'unfit' because their responses had short sentences, but when I looked closer the AI had misread the job requirements I typed in. How do you balance using automation with the risk of false negatives hurting real people?
2 comments
Log in to join the discussion
Log In2 Comments
lunakim16d ago
Oh man I feel this one in my bones. My cousin was job hunting last month and got auto rejected by a chatbot because she answered "yes ma'am" instead of "yes" - the system flagged it as unprofessional language. It's brutal how these tools can't catch context like a human would. You spend hours crafting the perfect prompt and one typo or weird phrasing can tank someone's chance at a job they really need. That candidate probably had no idea why they got passed over either which just adds insult to injury. I think the only way to balance it is to run a small test batch first like send 5 applicants through manually before trusting the automation with everybody.
4