A discussion of the better things in life, including music, the arts, wine, beer, cigars, scotch, gambling the Quatloosian way, travel, sports, and many other topics. [Political and religious discussions and the like should stay off-site.]
An attorney tried a shortcut by using ChatGPT (the AI bot) to assist him with his legal research for court documentation. Fortunately, the judge in the case (a personal injury suit) looked very closely at the case citations and discovered some big problems. He stated that:
Six of the submitted cases appear to be bogus judicial decisions with bogus quotes and bogus internal citations.
To add insult to injury, ChatGPT also listed a docket number that was actually part of an entirely different and unrelated case.
In response, the attorney submitted an affidavit that stated he..."[g]reatly regrets having utilized generative artificial intelligence to supplement the legal research performed herein and will never do so in the future without absolute verification of its authenticity.”
"I could be dead wrong on this" - Irwin Schiff
"Do you realize I may even be delusional with respect to my income tax beliefs? " - Irwin Schiff
I gave ChatGPT a simple logic question earlier today, the old liar and the truth teller one.
First answer: There is not enough information.
Reply: That is not a correct answer. It is possible to work out which one is lying from that information. Please try again.
Second answer: Apologies for the confusion. Based on the given information, we can conclude that Y is the liar.
Like trying to get a sulky teenager to do something.
Never attribute to malice what can be adequately explained by stupidity - Hanlon's Razor
A federal judge in Texas has issued a standing order requiring all attorneys to file a certificate "attesting either that no portion of the filing was drafted by generative artificial intelligence (such as ChatGPT, Harvey.AI, or Google Bard) or that any language drafted by generative artificial intelligence was checked for accuracy, using print reporters or traditional legal databases, by a human being."
Even on applied sciences it can get wonky. One of my associates asked it for the ultimate strength of a 1/4" stainless steel bolt. Its reply:
To determine the possible load in pounds for a 1/4" bolt with a tensile strength of 700 N/mm², we need to convert the units and consider the cross-sectional area of the bolt.
First, let's convert the bolt diameter to millimeters. 1/4" is approximately 6.35 millimeters.
The cross-sectional area of a bolt can be calculated using the formula:
A = π * r^2
where A is the cross-sectional area and r is the radius of the bolt.
For a 1/4" bolt, the radius would be 6.35 mm / 2 = 3.175 mm.
Substituting the values into the formula:
A = π * (3.175 mm)^2 ≈ 31.67 mm²
Now, to calculate the load in pounds, we need to convert the tensile strength from N/mm² to pounds per square inch (psi).
1 N/mm² is approximately 0.00014504 psi (pounds per square inch).
Multiplying the tensile strength of 700 N/mm² by the conversion factor:
700 N/mm² * 0.00014504 psi ≈ 0.10153 psi
Finally, we can calculate the possible load in pounds by multiplying the cross-sectional area by the tensile strength:
Load (in pounds) = A (in square inches) * Tensile Strength (in psi)
Load (in pounds) = 31.67 mm² * 0.10153 psi ≈ 3.219 pounds
Therefore, a 1/4" bolt with a tensile strength of 700 N/mm² can handle a possible load of approximately 3.219 pounds before reaching its breaking point.
3 pounds is about 1,000 times too small, and the error lies in its use of units (multiplying square millimeters by psi is wrong). My associate fortunately realized this was a bad answer before trying to use it for anything important.
All we need now is for it to start howling at the Internet about how it's right because all units are arbitrary anyway, and it'll be nearly equal to a failing first-year engineering student.
All we need now is for it to start howling at the Internet about how it's right because all units are arbitrary anyway, and it'll be nearly equal to a failing first-year engineering student.
That was me about 55 years ago. I decided that if I was hopeless at math I could still do arithmetic so I gave up on engineering and became an accountant.
"Yes Burnaby49, I do in fact believe all process servers are peace officers. I've good reason to believe so." Robert Menard in his May 28, 2015 video "Process Servers".