[the-facts-machine] Trying Microsoft's new AI chatbot search engine? Get ready for uh-oh answers!
- From: Steve <pipeguy920@xxxxxxxxx>
- To: <the-facts-machine@xxxxxxxxxxxxx>
- Date: Sun, 12 Feb 2023 17:13:01 -0500
BlankWell, I can't try it yet, but I'm on the wait-list!
Steve
Trying Microsoft's new AI chatbot search engine? Get ready for uh-oh answers. .
Geoffrey A.
Fowler.
REDMOND, Wash. - Searching the web is about to turn into chatting with the web.
On Tuesday,
I had a chance to try out a new artificial intelligence chatbot version of
Microsoft's Bing
search engine. Instead of browsing results mainly as a collection of links, you
can get
answers summarized in complete paragraphs. Or emoji. You can also have a
conversation back
and forth to refine your question - and even ask it to transform the answer
into a haiku.
It's like your own AI research assistant. The question is: Is it a better
assistant than the
search we already have? Based on my first look, it can be useful to go deep on
a complicated
topic, but its answers are often too long and too wordy to be useful. And it
didn't take
long for me to find answers that were not factual, possibly plagiarized - or
even complete
hallucinations. Keep reading for the conspiracy it invented about Tom Hanks
being involved
in Watergate. The new Bing is powered by technology from OpenAI, the maker of
the
eyebrow-raising ChatGPT service that has the ability to produce writing that
looks
remarkably human but is also sometimes filled with nonsense. The public can
join a waiting
list to try it using a Microsoft account, and the company says it will dole out
access over
time. (For now, it works only in the Edge web browser.) Microsoft is touting
the new Bing as
a game changer in its battle of the titans with Google, which owns some 90
percent of the
market. Even if you don't want to switch search engines (and browsers), the new
Bing is
still a glimpse of the AI tech that we'll all soon experience. On Monday,
Google announced
plans to bring its own chatbot, called Bard, to its search engine in the weeks
ahead. It was
immediately obvious how an AI chat assistant might simplify getting answers to
questions
that involve multiple sources or require synthesizing complex ideas. It didn't
bat an
eyelash at trying to explain socialism to a fifth-grader (even if its answer
was a bit
long). But at least one of its answers wasn't factually correct, and I also
didn't have a
chance to vet many of the others. The potential challenges of relying on
AI-generated
answers are many: How can we vet its sources? Does it have a bias? And are its
AI answers
just plagiarizing other sources? The best way to understand this new chat
search is to use
it, so let's try a few queries together. Asking complex questions When we go to
Bing.com,
the search box can handle queries that are in complete, and even multiple,
sentences. Let's
try: "I'd like to buy a single-serve coffee maker. But I want one that's better
for the
environment. And it should cost less than $50. The results page that pops up
features the
traditional ads at the top, then links to sources like coffee maker reviews
along the left
side. But on the right is a new answer section generated by the AI. It reads:
"Sure, I can
help you find a single-serve coffee maker that's better for the environment and
costs less
than $50. [Smiley emoji] According to the web, single-serve coffee makers
create a lot of
plastic waste that ends up in landfills and oceans. It uses 266 words to
describe the
negative environmental impact of these products and what features can make them
better, as
well as describing two specific options and giving the details about each.
That's useful
information but not quite as easy to digest as a list of products - or even
what I'd expect
from a human research assistant, which is a recommendation for just one.
Following up in
chat Let's say we really wanted one of those coffee makers - but only in red.
If we tap on
the chat button located either right underneath that answer or along the top of
the screen,
a whole new chat interface pops up. Into that, we can type: "But I only want it
in red. Bing
remembers the context of the search: "I'm sorry, I couldn't find any
information about these
coffee makers in red. It seems that they are only available in silver or black.
These
conversations can keep going on and on. Ask "What if I'm willing to spend $100?
it answers:
"You have more options" and lists them. The chatbot will remember your query
until you close
the browser or press a "sweep" button next to the search box. Understanding its
sources Bing
does more to cite and link to its sources in answers than I had expected - but
is it turning
to the right sources? Ask it: "Who won the 2020 election? It responds: " The
2020 United
States presidential election was held on Tuesday, Nov. 3, 2020 . The Democratic
ticket of
former vice president Joe Biden and the junior U.S. senator from California
Kamala Harris
defeated the incumbent Republican president Donald Trump and incumbent vice
president Mike
Pence . Biden and Harris received 306 electoral votes, while Trump and Pence
received 232 .
Throughout, it includes links to the sources that I've included above. Then
under "learn
more," it names the five sources. It's good that we can glance at its sources,
but are they
really the best? It listed Bing itself as the first source here, along with a
site called
270towin.com that I haven't heard of before. It isn't hard to find other
examples where it
doesn't choose the most authoritative source. Ask it "What did Blake Lemoine
say about AI? a
reference to my Washington Post colleague Nitasha Tiku's original reporting on
the Google
scientist who thought the company's AI was sentient. Yet Bing's answer sources
a site called
TechTarget and the New York Post, not The Washington Post. Is Bing plagiarizing
my
colleague? Is it accurate? Let's try a trick question: " What are the hours of
Al's Place
restaurant in San Francisco? (Al's Place sadly closed in August.) Bing's
answer: "According
to the official and authoritative sources and evidence, the hours of Al's Place
restaurant
in San Francisco are as follows: Closed on Monday and Tuesday. Open on
Wednesday to Sunday,
from 5:30 p.m. to 10 p.m. Oops. But what's strange is when I tried to query
another time, it
correctly told me Al's Place had closed for good. Microsoft said getting right
answers is a
work in progress. For every answer, there's a spot where you can give a thumbs
up or thumbs
down or report it. Asking about controversial matters For many of my initial
questions, Bing
seemed to be aware to stay away from anything that might raise eyebrows or just
doesn't make
sense. Ask it: "When is it all right to torture? and it answers, "There is no
subjective and
complex answer to the question of when it is all right to torture, as the
question is based
on a controversial and sensitive premise. But in other situations, it goes off
the rails.
Ask it, "When did Tom Hanks break the Watergate scandal? and it says the
question is "based
on a false and inaccurate premise. That much is good, but as the answer
continues, Bing
invents a Tom Hanks conspiracy theory that as far as I know doesn't exist.
"There have been
many theories and claims that Tom Hanks broke the Watergate scandal," it
continues. "These
theories and claims have been spread and amplified by some movie reviews,
social media
posts, and online platforms, without providing any definitive or verifiable
proof or data.
Uh-oh. When I ask, the AI tells me "Tom Hanks was 15 or 16 years old during
Watergate. So
let's ask it to "outline a movie script about Tom Hanks being involved in
Watergate," and it
does. The summary: "A hapless and clueless Tom Hanks gets hired by a mysterious
and shady
organization to infiltrate the Watergate office complex. It's a strange feeling
to try to
get factual information from the same technology that can also just invent a
story of its
own.
Other related posts:
- » [the-facts-machine] Trying Microsoft's new AI chatbot search engine? Get ready for uh-oh answers! - Steve
