Signal 11
also programmed for conversational english
NYC AI Chatbot Touted by [mayor] Adams Tells Businesses to Break the Law
In October, New York City announced a plan to harness the power of artificial intelligence to improve the business of government. The announcement included a surprising centerpiece: an AI-powered chatbot that would provide New Yorkers with information on starting and operating a business in the city.
Five months after launch, it’s clear that while the bot appears authoritative, the information it provides on housing policy, worker rights, and rules for entrepreneurs is often incomplete and in worst-case scenarios “dangerously inaccurate,” as one local housing policy expert told The Markup.
[...]
The bot, for example, said it was legal to lock out a tenant, and that “there are no restrictions on the amount of rent that you can charge a residential tenant.” [...] The bot said it was fine to take workers’ tips [...]
One small note on the page says that it “may occasionally produce incorrect, harmful or biased content,” but there’s no way for an average user to know whether what they’re reading is false. A sentence also suggests users verify answers with links provided by the chatbot, although in practice it often provides answers without any links.
[...]
A Microsoft spokesperson declined to comment or answer questions about the company’s role in building the bot.