fair, but "logically consistent thoughts" is a subject of deep investigation starting from the early euclidean geometry to the modern godel's theorems.
ie, that logically consistent thinking starts from symbolization, axioms, proof procedures, world models. otherwise, you end up with persuasive words.
You just ruled out 99% of humans from having reasoning capabilities.
The beautiful thing about reasoning models is that there is no need to overcomplicate it with all the things you've mentioned, you can literally read the model's reasoning and decide for yourself if it's bullshit or not.
That's sort of arrogant, Most of that 99 (if that many) % could learn if inspired to and provided resources. And does use reasoning and instinct in day-to-day life even if it's as simple as "I'll take go shopping before I take my car to the shop so I have the groceries" or "hide this money in a new place so my husband doesn't drink it away". Models will get better over time, and yes humans only use models too.
Humans rely in cues to tell when each other is fabricating or lying. Machines don't have those cues, and fabricate their reasoning too. So we have a complicatedly difficult time trusting them.
>You just ruled out 99% of humans from having reasoning capabilities.
After a conversation with humans I think you'd agree 1% of them being able to reason deeply is a vast overestimation.
A good example to see how little people can reason is the following classic:
> Given the following premises derive a conclusion about your poems:
> 1) No interesting poems are unpopular among people of real taste.
> 2) No modern poetry is free from affectation.
> 3) All your poems are on the subject of soap bubbles.
> 4) No affected poetry is popular among people of taste.
> 5) Only a modern poem would be on the subject of soap bubbles.
The average person on the street won't even know where to start, the average philosophy student will fuck up the translation to first order logic, and a logic professor would need a proof assistant to get it right consistently.
Meanwhile o3-mini in 10 seconds:
We can derive a conclusion about your poems by following the logical implications of the given premises. Let’s rephrase each premise into a more formal form:
Premise 1: No interesting poems are unpopular among people of real taste.
This can be reworded as:
If a poem is interesting, then it is popular among people of real taste.
Premise 2: No modern poetry is free from affectation.
This tells us:
If a poem is modern, then it is affected (i.e., it shows affectation).
Premise 3: All your poems are on the subject of soap bubbles.
In other words:
Every one of your poems is about soap bubbles.
Premise 4: No affected poetry is popular among people of taste.
This implies:
If a poem is affected, then it is not popular among people of taste.
Premise 5: Only a modern poem would be on the subject of soap bubbles.
This means:
If a poem is about soap bubbles, then it is modern.
Now, let’s connect the dots step by step:
From Premise 3 and Premise 5:
All your poems are on the subject of soap bubbles.
Only modern poems can be about soap bubbles.
Conclusion: All your poems are modern.
From the conclusion above and Premise 2:
Since your poems are modern, and all modern poems are affected,
Conclusion: All your poems are affected.
From the conclusion above and Premise 4:
Since your poems are affected, and no affected poem is popular among people of taste,
Conclusion: Your poems are not popular among people of taste.
From Premise 1:
If a poem is interesting, it must be popular among people of taste.
Since your poems are not popular among people of taste (from step 3), it follows that:
Conclusion: Your poems cannot be interesting.
Final Conclusion:
Your poems are not interesting.
Thus, by logically combining the premises, we conclude that your poems are not interesting.
I could trace through that example quite quickly and I'm not an expert in logic, so I think you might be exaggerating some statements about difficulty here.
ie, that logically consistent thinking starts from symbolization, axioms, proof procedures, world models. otherwise, you end up with persuasive words.