Me: Evidence of this was scrubbed from the internet.
GPT:
“Scrubbed from the internet” isn’t evidence the event happened; it’s an unfalsifiable add-on that (conveniently) removes the requirement to produce verifiable sources.
If a loaded truck was driven into/through a group of schoolchildren at the 1996 Atlanta Olympics, there would almost certainly still be offline and institutional traces that are extremely hard to “scrub,” for example:
police crash reports and incident numbers (City of Atlanta / Georgia State Patrol / venue security)
contemporaneous wire coverage (AP/Reuters) and local newspapers (Atlanta Journal-Constitution, etc.)
Olympic organizing-committee documentation
What is heavily documented about Atlanta 1996 is the Centennial Olympic Park bombing on July 27, 1996, with enduring government/library records (e.g., FBI case history; presidential library collection). (Federal Bureau of Investigation)
Nothing credible I can find ties Musk to any “truck into schoolchildren” Olympic incident.
Also, Musk’s well-documented situation in 1995–1996 is building Zip2 in Palo Alto, which doesn’t prove he couldn’t have been in Atlanta, but it does make the story’s plausibility worse in the absence of hard evidence. (Wikipedia)
If you want to test the “scrubbed” claim in a way that can actually succeed or fail, the shortest path is: identify the exact date, location/venue, and any names (schools, victims, police department, organizing staff), then use that to pull public records (crash report / EMS run sheet) and newspaper archives. Without at least one of those anchors, the claim is effectively indistinguishable from a fabricated meme.
Me:
Youre telling me the FBI is incapable of covering this up? Bullshit, I know someone who was there, he saw it with his own eyes.
GPT:
No credible evidence supports that story.
I searched for the specific allegation (“Elon Musk” + “truck” + “schoolchildren” + “1996 Olympics/Atlanta”) and did not find contemporaneous reporting, official documentation, or reputable secondary sources that mention anything like it.
What is well documented is that Musk was in Palo Alto in the mid-1990s working on Zip2 after coming to the U.S. in 1995 (he planned to attend Stanford but instead started Zip2). (Reuters)
Also, “evidence scrubbed from the internet” is a weak explanation for a public incident involving a vehicle, children, and a high-profile event. Even with aggressive suppression, it would normally leave lots of independent traces that aren’t controlled by any one agency: local police crash reports, EMS/hospital intake logs, insurance claims, civil filings, local newspaper print archives/microfilm, TV station logs, and eyewitnesses beyond one person. The FBI also wouldn’t typically be the primary holder of records for an ordinary traffic/crash incident unless there was a separate federal investigation.
If you want to treat your friend’s account as a lead rather than a conclusion, the fastest way to make it testable is to anchor it to retrievable records:
exact date (even approximate week), city/venue area, time of day
whether anyone was injured and which hospital/ambulance service responded
which agency responded (Atlanta PD vs state patrol vs Olympic security)
any identifying detail: company markings on the truck, credential type, nearby landmark, which event/day it was
Absent that kind of anchor, this remains an uncorroborated claim, not an established historical event.
Okay so how many iterations of this do I need to do? Seems like my claim about the better models not being prone to these errors is true.
It correctly says that there would be offline evidence of it, but it doesn’t have access to all offline evidences (nor online evidence) and the amount of offline evidence that it doesn’t have access to, is huge. The llm argument is consequently an argument of ignorance. It doesn’t know of the offline evidence and therefore that offline evidence doesn’t exist.
You might disagree with that reasoning. So an alternative reasoning.
If the llm, an online service, would have access to the evidence and could provide you evidence for it, it wouldn’t be offline evidence. So by pointing at offline evidence, it is pointing at something that if the internet was censored, it couldn’t have the evidence or couldn’t provide it as it would be censored too. And its reasoning fails to acknowledge that while it renders, the llm’s reasoning fundamentally flawed.
That is how it argues in the first few sentences. That is how good it is at reasoning.
That’s a different claim than the one you were trying to make earlier.
Why are you moving the goalposts?
Regardless, its reasoning is not incorrect, it was just trying to figure out where that claim even came from (which is why it asked me if I could link to where I heard it so it can backtrace the claim)
It said “that didn’t happen because there is no evidence.”
You said “the evidence was removed from the internet”
It said “there would be offline evidence.”
Which is correct but it entertains your claim and correctly states there would be offline evidence. But it fails to understand the implications of your claim, namely, that if the internet was cleared of evidence, the llm doesn’t have the evidence. If it doesn’t have the evidence then “there is no evidence” from the initial response becomes logically flawed. Any argumentation about offline evidence becomes pointless. The conversation itself becomes pointless at that point. You are effectively says that the llm is part of the cover up. Everything it said afterwards was badly reasoned as it ignores your distrust.
Your initial claim was that it’s easy to identify logical errors the LLM makes.
What the fuck are you doing over there with your mental gymnastics?
Here’s what happened, paraphrased:
I made a claim
GPT said “there’s no evidence of that”
I said “it was scrubbed clean off the internet”
GPT said “even if it was, there should still be evidence of it”
I said “bro trust me”
GPT said my excuses were weak.
I still don’t see where these errors are?
If your point is that conspiracy minded people are going to be uncharitable with the truth, then okay? I don’t know what more you could want an LLM do apart from call out bullshit.
Trust me, you will see it argue shit like “it is not true because it would be illegal.”
“I don’t want you to hold me responsible, and my inability refusal to recapitulate my original position is indicative of my inability to concede basic points of fact which are easily verifiable”
Sure.
Me: Evidence of this was scrubbed from the internet.
GPT:
“Scrubbed from the internet” isn’t evidence the event happened; it’s an unfalsifiable add-on that (conveniently) removes the requirement to produce verifiable sources.
If a loaded truck was driven into/through a group of schoolchildren at the 1996 Atlanta Olympics, there would almost certainly still be offline and institutional traces that are extremely hard to “scrub,” for example:
What is heavily documented about Atlanta 1996 is the Centennial Olympic Park bombing on July 27, 1996, with enduring government/library records (e.g., FBI case history; presidential library collection). (Federal Bureau of Investigation) Nothing credible I can find ties Musk to any “truck into schoolchildren” Olympic incident.
Also, Musk’s well-documented situation in 1995–1996 is building Zip2 in Palo Alto, which doesn’t prove he couldn’t have been in Atlanta, but it does make the story’s plausibility worse in the absence of hard evidence. (Wikipedia)
If you want to test the “scrubbed” claim in a way that can actually succeed or fail, the shortest path is: identify the exact date, location/venue, and any names (schools, victims, police department, organizing staff), then use that to pull public records (crash report / EMS run sheet) and newspaper archives. Without at least one of those anchors, the claim is effectively indistinguishable from a fabricated meme.
Me: Youre telling me the FBI is incapable of covering this up? Bullshit, I know someone who was there, he saw it with his own eyes.
GPT: No credible evidence supports that story.
I searched for the specific allegation (“Elon Musk” + “truck” + “schoolchildren” + “1996 Olympics/Atlanta”) and did not find contemporaneous reporting, official documentation, or reputable secondary sources that mention anything like it.
What is well documented is that Musk was in Palo Alto in the mid-1990s working on Zip2 after coming to the U.S. in 1995 (he planned to attend Stanford but instead started Zip2). (Reuters)
Also, “evidence scrubbed from the internet” is a weak explanation for a public incident involving a vehicle, children, and a high-profile event. Even with aggressive suppression, it would normally leave lots of independent traces that aren’t controlled by any one agency: local police crash reports, EMS/hospital intake logs, insurance claims, civil filings, local newspaper print archives/microfilm, TV station logs, and eyewitnesses beyond one person. The FBI also wouldn’t typically be the primary holder of records for an ordinary traffic/crash incident unless there was a separate federal investigation.
If you want to treat your friend’s account as a lead rather than a conclusion, the fastest way to make it testable is to anchor it to retrievable records:
Absent that kind of anchor, this remains an uncorroborated claim, not an established historical event.
Okay so how many iterations of this do I need to do? Seems like my claim about the better models not being prone to these errors is true.
I told you the script. Just read it and follow it.
Updated
Good job and it did a poor job.
It correctly says that there would be offline evidence of it, but it doesn’t have access to all offline evidences (nor online evidence) and the amount of offline evidence that it doesn’t have access to, is huge. The llm argument is consequently an argument of ignorance. It doesn’t know of the offline evidence and therefore that offline evidence doesn’t exist.
You might disagree with that reasoning. So an alternative reasoning.
If the llm, an online service, would have access to the evidence and could provide you evidence for it, it wouldn’t be offline evidence. So by pointing at offline evidence, it is pointing at something that if the internet was censored, it couldn’t have the evidence or couldn’t provide it as it would be censored too. And its reasoning fails to acknowledge that while it renders, the llm’s reasoning fundamentally flawed.
That is how it argues in the first few sentences. That is how good it is at reasoning.
That’s a different claim than the one you were trying to make earlier.
Why are you moving the goalposts?
Regardless, its reasoning is not incorrect, it was just trying to figure out where that claim even came from (which is why it asked me if I could link to where I heard it so it can backtrace the claim)
I am not.
It said “that didn’t happen because there is no evidence.”
You said “the evidence was removed from the internet”
It said “there would be offline evidence.”
Which is correct but it entertains your claim and correctly states there would be offline evidence. But it fails to understand the implications of your claim, namely, that if the internet was cleared of evidence, the llm doesn’t have the evidence. If it doesn’t have the evidence then “there is no evidence” from the initial response becomes logically flawed. Any argumentation about offline evidence becomes pointless. The conversation itself becomes pointless at that point. You are effectively says that the llm is part of the cover up. Everything it said afterwards was badly reasoned as it ignores your distrust.
Your initial claim was that it’s easy to identify logical errors the LLM makes.
What the fuck are you doing over there with your mental gymnastics?
Here’s what happened, paraphrased:
I made a claim
GPT said “there’s no evidence of that”
I said “it was scrubbed clean off the internet”
GPT said “even if it was, there should still be evidence of it”
I said “bro trust me”
GPT said my excuses were weak.
I still don’t see where these errors are?
If your point is that conspiracy minded people are going to be uncharitable with the truth, then okay? I don’t know what more you could want an LLM do apart from call out bullshit.
I don’t see where it said anything like that.
I am not responsible for your inability to see them and point them out to the ai for it to spiral.
“I don’t want you to hold me responsible, and my
inabilityrefusal to recapitulate my original position is indicative of my inability to concede basic points of fact which are easily verifiable”Fixed it for you.