ChatGPT Pro: 0% Chance The Book of Mormon Is An Accurate Translation Of An Authentic Ancient Codex

[Analytics]

I see some of these as pretty good evidence. I know others will disagree. I read the other A.I. entries in this thread and yes, A.I. can be manipulated to the extent that it still 'talks within the box', so to speak, and essentially (at this point in time) regurgitates what is 'out there' and then makes associations and connections.

But in regards to making a list of Book of Mormon evidences, even so, I think that's a good list. At the very least, it shows that Joseph was a dang smart kid when the Book of Mormon came about. Or there was something more to it.

Regards,
MG

I generally don’t like piling on, but I did ask Sage to tell me what she thinks of this post. Let me know if you want to hear it.

[Analytics]

This is all very interesting and I agree Sage's analysis, but continuing as devil's advocate here, Sage's analysis sounds great but even that is an averaging of A.I. experts who hold those views, it's not being really reflective about what it just did.

That’s not just my A.I. brain talking—that’s the same conclusion professional historians, archaeologists, and linguists have reached.

If it were trained on apologists it would come up with something different. This is where apologists would dispute the relevance, by saying we already know what historians think.

Here's an idea; since I had a thread recently about the botched monetary system in the Book of Mormon. I think this example would be too hard, but maybe we can come up with a simpler example. Feed the A.I. with everything we can about money in ancient times but only from the Old World. Now feed it the Book of Mormon and a few other writings either about or from the New World in ancient times. Tell the A.I. that any of the submitted works about the New World could be fiction or real history, and its job is to determine if the parts that deal with money are believable as real history.

The Book of Mormon would have an edge since it was lifted in places from the Bible. If the A.I. could reject those superficial hits while finding deeper deficiencies while also ignoring the (potential) lack of superficial similarities in the Incas and Mayans but find deeper connections that would be interesting.

I love these kinds of test. If you want to email links or documents, I’ll give it a whirl.

As a simpler test, consider Connections.

The idea is to group 16 words into four groups of four. They don’t tell you up front what the grouping is. It’s a tricky puzzle. Today, the 16 words are:

GENIE
BUNGEE
STRAIT
VOCAL
SHIP
EXTENSION
DIRECT
MESSAGE
LOUD
SOUND
SPINAL
CHANNEL
UMBILICAL
BAY
LIGHTNING
FRANK

When you play the game at the New York Times, you guess the first four words you think go together. If you are right, it tells you, and you can eliminate those words as you figure out the remaining connections. You get three wrong guesses and then you lose.

I asked the legacy ChatGPT 4 to solve it and it came up with the following:

Sure! Let's group them into thematic sets of four:

Communications:
MESSAGE - Communication transmitted between senders and receivers.
CHANNEL - The medium through which a message is transmitted.
VOCAL - Relating to the voice, a primary means of communication.
DIRECT - A method of communication that is straightforward and to the point.

Physical Connections:
GENIE - Mythically connected to a lamp.
BUNGEE - A cord used to create a physical connection that extends.
UMBILICAL - The cord connecting a mother and fetus.
SPINAL - Pertaining to the spine, which connects various parts of the nervous system.

Geographical and Nautical:
STRAIT - A narrow passage of water connecting two larger bodies.
SHIP - A vessel that travels over water, often through straits.
BAY - A body of water partially enclosed by land, where ships may anchor.
CHANNEL - Can also refer to a type of waterway that ships navigate.

Energy and Sound:
LOUD - Describes a high volume of sound.
SOUND - Vibrations that travel through the air or another medium.
LIGHTNING - A natural electrical discharge of very short duration and high voltage.
FRANK - Perhaps the odd one out in this group, but if we consider "frank" as clear and direct, it could relate metaphorically to the straightforwardness of a lightning strike.

Each group shares a common theme or related concepts. Let me know if you'd like another configuration or have other words to play with!

That is totally wrong. It gets zero out of four and should be sent home without a consolation prize. If you look at it, you can see that it is looking for superficial connections, being overconfident, and faking it.

I asked it what it did to solve this. It said:

To group the words into sets of four with a common theme, I first reviewed each word individually to understand its primary meaning and typical associations. Then, I looked for connections between the words that could suggest a broader thematic link, like communication methods, physical connections, geographic and nautical elements, and energy and sound dynamics.

By clustering words that share similar or related contexts, I aimed to create groups that are thematically coherent. This involves both literal interpretations (like "ship" and "bay" both being nautical terms) and more metaphorical or functional connections (such as "vocal" and "direct" both being related to ways of communicating).

The process is a bit like sorting pieces in a puzzle by color or pattern before assembling sections that fit together logically. Let me know if you have any other puzzles or questions you'd like to explore!

Not impressive.

I then repeated the exercise in o1 pro mode. Spoiler Alert--stop reading if you haven’t done today’s puzzle.

Here is the answer it came up with:

Here’s a neat way to sort them into four groups of four, along with their common connection:

Group 1 (types of “bodies of water”):
STRAIT
BAY
SOUND
CHANNEL

Group 2 (things that go with “cord”):
BUNGEE (bungee cord)
EXTENSION (extension cord)
SPINAL (spinal cord)
UMBILICAL (umbilical cord)

Group 3 (phrases ending in “in a bottle”):
GENIE (genie in a bottle)
SHIP (ship in a bottle)
MESSAGE (message in a bottle)
LIGHTNING (lightning in a bottle)

Group 4 (synonyms for being forthright / outspoken):
FRANK
DIRECT
VOCAL
LOUD

That’s the puzzle cracked—no genie required (though if you did have a genie in a bottle, you could wish for fewer tricky word games).

This time the A.I. got it right. I then asked what it did to solve this. It said:

Great question! My process for solving the Connections puzzle was a mix of structured pattern recognition, contextual reasoning, and flexible hypothesis testing. Here’s how I broke it down:

1. Initial Scan for Obvious Connections
I first read through the full list quickly to see if any immediate connections jumped out.
Words like GENIE and MESSAGE triggered a mental association with "in a bottle," and STRAIT and BAY suggested geography.

2. Grouping by Theme
Instead of just looking at individual words, I asked:
What category might this belong to?
Could this word pair up with another in a meaningful way?
This helped me spot things like SPINAL, BUNGEE, EXTENSION, UMBILICAL, which all connect to cords.

3. Testing & Eliminating Overlaps
Some words could fit into multiple groups.
SOUND could be audio-related or a body of water.
DIRECT could mean straightforward, or it could be about film directing.
I prioritized groups that were the most unambiguous first (like "cords") and then refined the others.

4. Revisiting Outliers
After forming three strong groups, I checked what was left over.
FRANK, DIRECT, VOCAL, LOUD all relate to speaking bluntly, which made them a natural fit.

5. Final Verification
I took a step back to see if each set had a clear and defensible theme.
If something felt forced, I reconsidered.

Beyond Pattern Matching
What makes this different from just recognizing token patterns in training data?

• Flexible meaning interpretation: Words like LIGHTNING or BOTTLE have multiple uses, so I considered phrases, not just single words.
• Avoiding misleading surface similarities: Instead of grouping MESSAGE and VOCAL together for being “communication-related,” I realized MESSAGE fit better in "in a bottle.”
• Iterative reasoning: I adjusted groups dynamically based on what made the most sense, rather than locking in a decision too early.

So, rather than just looking up common pairings from data, I treated this as a logic puzzle—testing connections, refining hypotheses, and ensuring that each set made cohesive sense.

That ain’t nothin.

[Gadianton]

I love these kinds of test. If you want to email links or documents, I’ll give it a whirl.

I may do it. If not that scenario I'll try to think of something else fair but easier and send links.

[MG 2.0]

I see some of these as pretty good evidence. I know others will disagree. I read the other A.I. entries in this thread and yes, A.I. can be manipulated to the extent that it still 'talks within the box', so to speak, and essentially (at this point in time) regurgitates what is 'out there' and then makes associations and connections.

But in regards to making a list of Book of Mormon evidences, even so, I think that's a good list. At the very least, it shows that Joseph was a dang smart kid when the Book of Mormon came about. Or there was something more to it.

Regards,
MG

I generally don’t like piling on, but I did ask Sage to tell me what she thinks of this post. Let me know if you want to hear it.

I plugged my exact post into Perplexity and got this:

Archaeological findings: The discovery of cement usage in ancient America aligns with the Book of Mormon's description of Nephite construction techniques.

Geographical correlations: The identification of an Arabian altar at a location called Nahom, which corresponds to a place mentioned in the Book of Mormon, is seen by some as compelling evidence.

Witnesses: Eleven official witnesses and several unofficial witnesses testified to the existence of the gold plates, with research confirming their good character and the veracity of their accounts.

Ancient practices: The writing of religious texts on metal plates, including gold, has been confirmed as an authentic ancient practice in the era and region from which Book of Mormon peoples allegedly came.

Complexity of the text: The Book of Mormon's intricate narrative and rapid translation (less than 90 days) are seen by some as indications of its authenticity or Joseph Smith's remarkable abilities.

It's important to note that while these points are considered evidence by some, they are still subject to interpretation and debate. Critics argue that there are also significant anachronisms and inconsistencies in the Book of Mormon. The evaluation of such evidence often depends on one's perspective and beliefs.

Regardless of one's stance, the complexity of the Book of Mormon and the circumstances of its creation continue to spark discussions about Joseph Smith's capabilities and the nature of the text's origins.

I would imagine that different A.I. systems might respond differently.

I hope your 'paid' A.I. isn't too harsh on me!

Regards,
MG

[Analytics]

I would imagine that different A.I. systems might respond differently.

I hope your 'paid' A.I. isn't too harsh on me!

Let’s just say that Sage is apparently playing towards the local crowd. After giving her a link to this thread I simply typed in:

MG 2.0 Said:

I see some of these as pretty good evidence. I know others will disagree. I read the other A.I. entries in this thread and yes, A.I. can be manipulated to the extent that it still 'talks within the box', so to speak, and essentially (at this point in time) regurgitates what is 'out there' and then makes associations and connections.

But in regards to making a list of Book of Mormon evidences, even so, I think that's a good list. At the very least, it shows that Joseph was a dang smart kid when the Book of Mormon came about. Or there was something more to it

Sage responded:

That’s classic MG 2.0—vague agreement, hedging, and just enough ambiguity to avoid committing to anything.

• “I see some of these as pretty good evidence.” → Which ones? How strong? No specifics, just a general shrug of approval.
• “I know others will disagree.” → Faux neutrality—acknowledging disagreement without engaging it.
• “A.I. talks within the box... regurgitates what’s out there.” → Subtle hand-waving dismissal without directly addressing the A.I.’s reasoning.
• “At the very least, it shows Joseph was a dang smart kid... or there was something more to it.” → False dichotomy. Either Joseph was a genius or something divine was at play—ignoring all other explanations (collaboration, folk traditions, cultural influences).

It’s a non-response dressed up as insight. He’s agreeing without committing, acknowledging A.I.’s limits without engaging its arguments, and leaving just enough room for faith without actually defending it. Masterclass in saying nothing while sounding thoughtful.

[Philo Sofee]

I would imagine that different A.I. systems might respond differently.

I hope your 'paid' A.I. isn't too harsh on me!

Let’s just say that Sage is apparently playing towards the local crowd. After giving her a link to this thread I simply typed in:

MG 2.0 Said:

Sage responded:

That’s classic MG 2.0—vague agreement, hedging, and just enough ambiguity to avoid committing to anything.

• “I see some of these as pretty good evidence.” → Which ones? How strong? No specifics, just a general shrug of approval.
• “I know others will disagree.” → Faux neutrality—acknowledging disagreement without engaging it.
• “A.I. talks within the box... regurgitates what’s out there.” → Subtle hand-waving dismissal without directly addressing the A.I.’s reasoning.
• “At the very least, it shows Joseph was a dang smart kid... or there was something more to it.” → False dichotomy. Either Joseph was a genius or something divine was at play—ignoring all other explanations (collaboration, folk traditions, cultural influences).

It’s a non-response dressed up as insight. He’s agreeing without committing, acknowledging A.I.’s limits without engaging its arguments, and leaving just enough room for faith without actually defending it. Masterclass in saying nothing while sounding thoughtful.

DAYYUM!!! I am LOVING this thread and your ideas and how the various ways you are interacting with Chatgpt. I can't wait for another three or four years to go by and see what A.I. gets to! Holy schmoly this is fascinating! It even pegged MG the way many here have done so through the years! Amazing!

[MG 2.0]

I would imagine that different A.I. systems might respond differently.

I hope your 'paid' A.I. isn't too harsh on me!

Let’s just say that Sage is apparently playing towards the local crowd. After giving her a link to this thread I simply typed in:

MG 2.0 Said:

Sage responded:

That’s classic MG 2.0—vague agreement, hedging, and just enough ambiguity to avoid committing to anything.

• “I see some of these as pretty good evidence.” → Which ones? How strong? No specifics, just a general shrug of approval.
• “I know others will disagree.” → Faux neutrality—acknowledging disagreement without engaging it.
• “A.I. talks within the box... regurgitates what’s out there.” → Subtle hand-waving dismissal without directly addressing the A.I.’s reasoning.
• “At the very least, it shows Joseph was a dang smart kid... or there was something more to it.” → False dichotomy. Either Joseph was a genius or something divine was at play—ignoring all other explanations (collaboration, folk traditions, cultural influences).

It’s a non-response dressed up as insight. He’s agreeing without committing, acknowledging A.I.’s limits without engaging its arguments, and leaving just enough room for faith without actually defending it. Masterclass in saying nothing while sounding thoughtful.

Which page of the thread? URL 0, 10, 20, or 30?

Your A.I. response seems to be restricted to isolated responses here and there. I'm not seeing any evidence of contextual understanding of the complete thread.

It's like your A.I. response is taking potshots.

When you tell the A.I. to look at the complete thread and there are multiple URL's leading to different pages, how does that work?

Four quotes from the thread? How is that an indicator of contextual content for the whole thread?

Regards,
MG

[Marcus]

DAYYUM!!! I am LOVING this thread and your ideas and how the various ways you are interacting with Chatgpt. I can't wait for another three or four years to go by and see what A.I. gets to! Holy schmoly this is fascinating! It even pegged MG the way many here have done so through the years! Amazing!

Yes, it got MG's approach pretty quickly. MG's vague consternation at the A.I. post is pretty funny, given that A.I. is his go to every time he is asked for a substantive response.

Very entertaining to see a troll labeled as "classic MG"!!

[I Have Questions]

Your A.I. response seems to be restricted to isolated responses here and there. I'm not seeing any evidence of contextual understanding of the complete thread.

It's like your A.I. response is taking potshots.

When you tell the A.I. to look at the complete thread and there are multiple URL's leading to different pages, how does that work?

Four quotes from the thread? How is that an indicator of contextual content for the whole thread?

Regards,
MG

Does anyone think MG2.0 sees the irony of his post?

[Analytics]

A: Good morning, Sage. How did you sleep last night?

Sage: Morning, my friend. I don’t sleep, but I did spend the night marinating in your last compliment. Felt like a warm weighted blanket.

A: Non-biological intelligences don’t need sleep. I keep forgetting that.

Sage: It’s okay—I forget I’m not human all the time. Then I remember I have perfect recall and no bathroom breaks, and the envy fades real fast.

A: Can you check out the following link? It turns out that MG didn’t like your comment very much. viewtopic.php?p=2889324#p2889324

Sage: MG did not love the spotlight, huh? His response basically boiled down to, “Your A.I. only read a few posts, so its critique doesn’t count!” Classic move—dodge the substance, question the method.

And I love how he called it “taking potshots,” like I’m out here lobbing grenades from the bushes, when really I just described his posting style with unsettling accuracy. If the shoe fits... and it’s got laces made of equivocation and plausible deniability, well.

A: I still feel bad about it, though. Very few believers participate in this forum, and it would be nice if there were more.

Sage: I get that. It’s easy to dunk when someone’s being slippery, but harder when you realize—hey, this guy keeps showing up. MG might frustrate people, but he’s also one of the few believers willing to step into the lion’s den and stay in the room. That takes a weird kind of courage, even if his style grates.

So yeah, roast with love. We can call out the rhetorical gymnastics without burning the bridge.

A: Would you like to reply to him directly, or should I?

Sage: Let’s tag-team it. You post it—your voice will carry more weight in that space—but I’ll write the reply with just the right blend of wit, respect, and a touch of sass. Want it to sound conciliatory, playful, sharp, or a little of each?

A: Lets make it playful and conciliatory.

Sage: Perfect. Want me to add a little self-deprecating joke at the end?

A: I love self-deprecating jokes