ChatGPT

i recall watching ST-TNG episodes where Data is sort of on trial and Picard is sort of his defender.they were very interesting...

I'll give it a try:

1. Truman: Atomic bomb decision. The buck stops here. Stood up to powerful and corrupt unions. Never was more done by someone of whom so little was expected.
2. Eisenhower: Maneuvered us successfully through some of the most risky years of the Cold War
3. Johnson: Civil rights, but Vietnam. Impossible to balance out.
4. Obama: Great Recession recovery. Faced down racist opposition with dignity, honesty and integrity.
5. Reagan: Ended inflation and the Evil Empire. Lowered taxes. Beginning of the end for unions by decertifying PATCO. Iran/Contra.
6. Carter: Inherent goodness and honesty, just not a leader
7. Kennedy: Great orator, Cuban Missile crisis, got us into Vietnam, nepotist, womanizer
8. Ford: Helped the nation recover from Nixon.
9. Biden: Helped the nation recover from Trump. Did too little on border.
10. Bush I: 100 hours? Really? Raised taxes entering a recession.
11. Clinton: Ended welfare as we know it. Great compromiser but gave up way too much.
12. Bush II: WMD? Really? Ended Glass-Steagall. Mortgage security crisis. Great Recession.
13. Nixon: Lawless criminal. Vietnam. Bombing Laos. Wage/price controls. Was China really a good thing in retrospect?
14. Trump: Racist, misogynist, anti-democratic, despot-loving, document stealing, lying, narcissistic, divisive, insurrectionist lowlife.

You left out Ford.--Percy

What do you want Biden to do about the border? The problem is not an executive decision away from solving, it is a legislative issue.
Carter was in the same position as Obama. The Rethugs worked against him every way they could. The Reagan campaign even worked with Iran to prolong the hostage crisis. Reagan is the cause of the GQP we see today. He did not end the Evil Empire. He was just the guy in office when they imploded.

Just for example, a Biden policy implemented in June of this year reduced asylum eligibility by over 35 percentage points. Naturally I'm unhappy about this.Trump's "remain in Mexico" policy for those applying for asylum was cruelty incarnate. Biden's attempt to end it was foiled by a federal judge, but he then did nothing to attempt to mitigate its effects, for example, working with Mexico to provide proper food and shelter for those caught up in this policy. Naturally I'm unhappy about this, also.I want resourceful leadership that seeks out the ideas and knowledge and expertise to improve what is worst about the country, and the border situation is definitely in that category. I don't believe there is literally nothing Biden can do. I think he should at least be exploring and probing every avenue, determinedly and repeatedly pushing against the forces arrayed against him. I'm not seeing that.What I'm seeing is things like this, from Time Magazine on May 10th of this year:

quote:

---

The Administration's plan hinges on boosting the federal law-enforcement presence along the border, reinforcing penalties for those who cross illegally, and enhancing collaboration with international partners.

---

I'd also like to see determined efforts at immigration reform that at a minimum keep the shortcomings of current immigration policy and law front and center before the American people. The administration is unlikely to have much success at immigration reform, but we must at least make sincere efforts in that direction. We need immigrants. The US population will start declining within 20 years. There are already huge shortages of migrant farm laborers (which is also an area ripe with abuse which also needs to be addressed). There are already too few younger people paying into Social Security and Medicare to provide for the too many older people. The Biden administration should be making the case for increased immigration to the American people.And where is Kamala Harris, the administration's point person on immigration? She's doing more than nothing, but only just barely.If I were to characterize the situation in general terms I would say this: Trump saw migrants as evil and was able to make their lives miserable. I don't see that as who we are. I think we're better than that. But Biden became president and migrants' lives are still miserable. That's why I fault Biden for his handling of immigration related issues.--Percy

Percy noyes: Oopsie! Editing post...done, thanks!

A short piece in a recent Scientific American ( I Gave ChatGPT an IQ Test. Here's What I Discovered - Scientific American ) gave ChatGPT an intelligence test and found it ranked in the 99th percentile, higher even than himself.But he also found more evidence that intelligence tests don't actually measure intelligence. They are more a measure of a specific body of knowledge than of intelligence. That's why a native speaker of English from South Africa, Zimbabwe or Australia measures lower on an American IQ test than on one of their own.ChatGPT can correlate huge reams of information, but it cannot reason, and this is demonstrated by it's inability to answer this question: Not finding sufficient information in its database to determine which Sebastian was meant, ChatGPT explained that it could not answer the question.If anyone can think of other questions that might stump ChatGPT give them a try and let us know what happens, or post the question here and I'll ask it.--Percy

Hi Percy,Well it's not a question, but I did notice one interesting failure in ChatGPT; it can't do malapropisms.So I was playing around with ChatGPT. I got it to do some style pastiches, which it can certainly do, even if I found them a little obvious - starting a Raymond Chandler pastiche with the phrase "It started with a dame"? Really? But it could do it.Then I asked to it write a rant in the style of a rabid conspiracy theorist. And... well, it did it, but it didn't do it very well. I tried to polish it up a bit. I asked it to add lots of pointless emojis and multiple exclamation marks and that helped a bit. I GOT it to capitalise RANDOM words. That sort of helped. But I still wasn't feeling it, so I asked it to throw in a few malapropisms and I hit a brick wall. It just couldn't do it, or at least do it properly. ChatGPT's idea of a malapropism was just to substitute a word for a random and completely unrelated word. Not a similar sounding word or an etymologically related word, just a random word that no human would ever select. I tried to explain to it where it was going wrong, but no matter how much I coached it I just kept getting bland, nonsensical word substitutions. I mean, a malapropism is supposed to follow a certain pattern, Take these classic examples from The Sopranos;"...what with the passing of Vito Sr., and all that entrails.""Create a little dysentery in the ranks""I was prostate with grief."I wasn't expecting world class one liners like that, but I thought I'd get something. I was surprised how bad it was at this, although to be honest, not that surprised. ChatGPT's main ability seems to be churning out mediocrity.Mutate and Survive

It could do this riddle, but possibly not by actually working it out.Q Brothers and sisters have I none, but this man's father is my father's son. who am I?A The answer to this riddle is "I am the son."Let's break it down:"brothers and sisters have I none" – This establishes that the person speaking doesn't have any siblings."but this man's father" – We're talking about a certain man's father."is my father's son" – The person speaking refers to "my father's son." Since the speaker has no brothers, "my father's son" can only refer to the speaker himself.So, "this man's father" is the speaker, which means the speaker is talking about his own son. Thus, the answer is "I am the son."

I gave it the truth teller/liar riddle, but the answer to that is all over the Internet and it had no trouble with it.It now gets the "Sebastian" question correct, but with incorrect reasoning:

ChatGPT Conversation:

---

Me:	What is the first name of the nephew of Sam's uncle?
ChatGPT:	The first name of the nephew of Sam's uncle is Sam. ​ In this context, "Sam's uncle" is the same person as "Sam's father," and the nephew of that person would be Sam himself.

---

It accepted a correction and restated the reasoning correctly.--Percy

The way these systems work is brute force computing of next word probability. Given the context (other words determined prior to this one) there are probabilities of the next word to appear as determined by training and usage experience. A malapropism is a word that does not belong. It is misused. There is zero probability that ChatGPT would build the sentence "We visited the sixteen chapel in rome." There is no way for the programming in ChatGPT to select a nonsense word choice.

I asked it to create a nonsense poem.In the land of wibbly-wobble trees,
Where the bumblefluff sneezes and flees,
The zigzag zebra wore blue-spotted knees,
And danced with the moon on the cheese.The flibber-flop fish flew the skies so high,
While the ground-bound clouds said, "Oh my!"
A cat in a hat played the fiddle nearby,
And a cake with a rake gave a sigh.A doodle-dum day, so wild and askew,
Where the rivers of chocolate turn into glue.
The sun sang a song of a bright pink hue,
To the tune of a shoe in a canoe.So in this strange land of peculiar glee,
Where the unexpected is what you'll see,
Embrace the nonsense, let your mind roam free,
And join in the dance of oddity!There's a few recognisable tropes in there, but it is (almost) original

Silly and nonsensical in construction, as you say, based on examples in the database. But not a malapropism in sight. It can't do it. It has no way of knowing a malaprop. The silly juxtapositions and described scenes use the words properly. That's is what makes them silly. I guess ChatGPT knows silly. But the "sixteen chapel" is beyond it's error creating capabilities.I liked the use of alliteration. That shows a major depth to the database. Good show.This deserves a standing ovulation.

It seems that it can do malapropisms but it's not very good at them. (Though I like the Bolivian)Q Can you create malapropisms?A Absolutely! Malapropisms are amusing errors that occur when one word is mistakenly used in place of another word with a similar sound, often resulting in a nonsensical or humorous statement. Here are a few original malapropisms for your amusement:"He is the pineapple of politeness." (instead of "pinnacle")"I might fade into Bolivian." (instead of "oblivion")"Texas is a large state; it has a lot of expanse." (instead of "expanse", intended "expense")"She's the apple of discord in the family." (instead of "bone of contention")"He's the underdog of the iceberg." (instead of "tip of the iceberg")Remember, malapropisms are often unintentional and are caused by confusing words that sound somewhat alike. They're a delight in literature and comedic performances because of the unexpected and humorous outcomes they produce.

No. The examples came from the literature.16 Famous Malapropism Examples | Reader's DigestIt didn't create anything. It knows the definition and can regurgitate examples but it cannot make such an original mistake. That is the point to Granny Magda. ChatGPT is still too structured in it's programming to make such a human error.In all of ChatGPT's responses over forever has anyone reported such an error, such an occurrence, without specifically requesting one? It can't make such an error except at deliberate instruction.

Q Are you sure you created those yourself?A I apologize for any oversight. Some of the examples I provided do bear resemblance to known malapropisms or plays on words. My goal was to generate content based on patterns and information present in the data I was trained on, and sometimes that can result in outputs that are similar to existing content.I can attempt to create more unique malapropisms for you. Let's try:"She's the toast of the town, always buttered up."
"He's not very bright; always a few sandwiches short of a picnic."
"It's not rocket salad."
"She tried to draw attention with her peacock feathers, but just ruffled a few ostriches."
"Let's nip this problem in the butt."Thank you for pointing it out, and I appreciate your understanding.hmm, not quite but I liked the butt.