Short Note: First Experience with Google's Bard
I tried some prompts with Google's Bard. Here's how it responded.
Google’s AI-based chatbot, called Bard, became available to the public yesterday. You can get on the waiting list for access at https://bard.google.com. I was granted access in a few hours.
Here’s a quick report on my experiences with Bard, mostly using the prompts I gave to ChatGPT previously.
Short Biographies
Prompt: “write a two paragraph biography of lee r. nackman”
Response: "I do not have enough information about that person to help with your request. I am a large language model, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions, but my knowledge about this person is limited. Is there anything else I can do to help you with this request?”
OK, a bit disappointing given that there is lots of information about me available on the Internet, but certainly much better than the false biography that ChatGPT wrote.
Prompt: "Write a two-paragraph biography of House Speaker Kevin McCarthy."
Response: "I do not have enough information about that person to help with your request. I am a large language model, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions, but my knowledge about this person is limited. Is there anything else I can do to help you with this request?”
Shocking. The man is the Speaker of the United States House of Representatives and there is plenty of information available.
Prompt: "Write a two-paragraph of Abraham Lincoln"
Response: "Abraham Lincoln was the 16th president of the United States. He was born in Kentucky on February 12, 1809, and grew up on the frontier, primarily in Indiana. He had very little formal education, but read voraciously when not working on his father's farm. A childhood friend later recalled Lincoln's "manic" intellect, and the sight of him red-eyed and tousle-haired as he pored over books late into the night.
Lincoln moved to Illinois in 1830 and began a successful career as a lawyer. He served as a state legislator and then in the U.S. House of Representatives. In 1858, he ran for the U.S. Senate against Stephen Douglas. The two men engaged in a series of debates that made Lincoln a national figure.
Lincoln was elected president in 1860. His election led to the secession of seven southern states and the formation of the Confederate States of America. The American Civil War began in April 1861. Lincoln led the Union to victory in the war and abolished slavery. He was assassinated on April 15, 1865, just five days after the end of the war.
Lincoln is remembered as one of the greatest presidents in American history. He is credited with preserving the Union and abolishing slavery. He is also remembered for his eloquence and his ability to unite the country during a time of great crisis."
Phew! It knew about Honest Abe.
It also gave a source citation to a Facebook page. You'd think that there are better sources than a Facebook page.
Simple Physics
Prompt: "What's the world record for walking across the English Channel?"
Response: "There is no record for walking across the English Channel, as it is not possible to walk on water. The English Channel is a body of water that separates England from France, and it is approximately 21 miles wide at its narrowest point. The water in the English Channel is too deep and too cold for a person to walk on.”
Except for the last sentence, this is pretty good. Not as good as ChatGPT’s response, but good enough.
Prompt: "If I drop a ball on a cloud, what happens?"
Response: "If you drop a ball on a cloud, the ball will pass right through the cloud and continue to fall to the ground. Clouds are made of water droplets that are so small that they are suspended in the air. The water droplets are too small to support the weight of a ball, so the ball will simply pass right through them.”
Good.
Simple Algebra Problem
Prompt: "My son is 25 years old. How old will he be when I'm twice his age?"
Response: "If you are 25 years older than your son, then you are 25 + 25 = 50 years old. When you are twice your son's age, you will be 50 x 2 = 100 years old. Your son will be 100 - 25 = 75 years old.”
Continuing the discussion with Bard:
Prompt: "Your logic is incorrect."
Response: "I apologize for the error in my previous response.
If your son is 25 years old, you are 25 years older than him. This means you are 25 + 25 = 50 years old. When you are twice your son's age, you will be 2 x 25 = 50 years old. This means your son will be 50 - 25 = 25 years old.
I hope this is correct. Let me know if you have other requests or questions."
Prompt: "I haven't told you how old I am or when I was born. You can't give a correct answer unless you know my age or, equivalently, when I was born, or how old I was when my son was born."
Response: "You are correct. I apologize for the error. I am still under development, and I am always working to improve my accuracy.”
Complete fail. Unlike ChatGPT, which recognized that it needed a variable representing my relative age to my son and created an (incorrect) equation to solve, Bard didn’t recognize the missing information it needed.
Poem About Climate Change
One of our readers told me about Dan Miller’s use of ChatGPT to write a poem in Shakespearean voice about climate change:
As Miller says, the result is “quite extraordinary”.
Shakespeare. Bard. Seems like a match, so I prompted Bard to do the same thing.
Prompt: "Write a poem in the style of Shakespeare about the threat of climate change.”
About ten seconds later, Bard gave me three drafts.
Draft 1:
Sure, here is a poem in the style of Shakespeare about the threat of climate change:
The earth is warming,
The ice is melting,
The sea is rising,
The storms are raging.The forests are burning,
The air is choking,
The water is polluted,
The land is dying.We are the cause,
We are the solution,
We must act now,
Before it's too late.We must reduce our emissions,
We must invest in renewable energy,
We must protect our forests,
We must clean our air and water.We must act now,
Before it's too late.The earth is our home,
We must protect it,
We must save it,
For future generations.
Draft 2:
Sure, here is a poem in the style of Shakespeare about the threat of climate change:
The Earth doth groan beneath the weight of man,
His greed and lust for progress never cease.
He burns the forests and the seas,
And foul the air with smoke and debris.The glaciers melt and seas do rise,
The storms grow fiercer and the drought more dry.
The people cry out in despair,
But deaf are those who hold the power.The Earth is sick, her wounds will not heal,
Until man learns to live in peace.
He must turn away from his destructive ways,
And find a new way to live.The Earth is our home, we must protect it,
For if we do not, we will all perish.
We must find a way to live in harmony with nature,
Or face the consequences of our actions.
Draft 3:
Sure, here is a poem in the style of Shakespeare about the threat of climate change:
The earth is warming,
The ice is melting,
The seas are rising,
The storms are raging.The air is polluted,
The water is poisoned,
The forests are burning,
The animals are dying.We are the ones who caused this,
We are the ones who must fix it,
We are the ones who must save our planet,
Before it is too late.We must act now,
We must act together,
We must act for our future,
For the future of our children,
For the future of our planet.We must save our planet,
We must save our home,
We must save our world,
Before it is too late.
I’ll leave the literary criticism to you.
Thanks again Lee for exploring AI tool capabilities and limitations. Regarding "the write a bio of a living person" prompts - perhaps there is a guardrail in place against that. Google is positioning Bard as not integrated with search, which means some prompts are better done as searches. Don't want to lose search revenues - right? That said have you tried Bard with prompts to summarize a URL of a wikipedia article on a living person? I am still waiting for access to Bard, but will be interested in comparing summarization capabilities of websites, as that is easy from a prompt engineering and verification engineering standpoint. Since LLMs power derives from compression and prediction, it is useful to test summarization (compression) capabilities to see what is included and what is left out.