Air Canada must honor refund policy invented by airline’s chatbot::Air Canada appears to have quietly killed its costly chatbot support.
Air Canada must honor refund policy invented by airline’s chatbot::Air Canada appears to have quietly killed its costly chatbot support.
This is the best summary I could come up with:
On the day Jake Moffatt’s grandmother died, Moffat immediately visited Air Canada’s website to book a flight from Vancouver to Toronto.
In reality, Air Canada’s policy explicitly stated that the airline will not provide refunds for bereavement travel after the flight is booked.
Experts told the Vancouver Sun that Moffatt’s case appeared to be the first time a Canadian company tried to argue that it wasn’t liable for information provided by its chatbot.
Last March, Air Canada’s chief information officer Mel Crocker told the Globe and Mail that the airline had launched the chatbot as an AI “experiment.”
“So in the case of a snowstorm, if you have not been issued your new boarding pass yet and you just want to confirm if you have a seat available on another flight, that’s the sort of thing we can easily handle with AI,” Crocker told the Globe and Mail.
It was worth it, Crocker said, because “the airline believes investing in automation and machine learning technology will lower its expenses” and “fundamentally” create “a better customer experience.”
The original article contains 906 words, the summary contains 176 words. Saved 81%. I’m a bot and I’m open source!
Not a good summary
Ironically, using an LLM AI would probably summarize it better.
It was at 0 votes and I felt bad for the bot, upvoted it, then started reading it. I quickly changed it to a downvote. Bad bot.
The summarizer could do better by just copying over the entire text of the article. This was incoherent. Its only utility is for people who can’t or don’t click through.
You know how they say an infinite amount of monkeys in an infinite amount of time could produce the works of Shakespeare?
This is five monkeys in fifteen minutes.
The irony is that this is one of the things that LLMs are really good at. You could run a small local cpu only model and get it to give a far better summary than this bot does.