1 paragraph defining heuristics
1 paragraph on application
1 para. contrasting heuristic techniques to those of algorithms
I think I see a weakness. Can I narrow the bot down?
'Explain the first paragraph more thoroughly'
🧵3⃣
#ChatGPT gives examples and at the end addresses my focus:
"Heuristics are not always the best approach.. they can lead to biases and errors.."
Socratic sans interrogatory:
"I disagree that heuristics can 'lead' to biases. Make your case in a sound logical argument."
🧵4⃣
#ChatGPT: "You are correct.. heuristics do not inherently lead to biases, but.. can be susceptible to them..."
Wishy washy. 'lead' to? 'susceptible' to? How about 'characterized by'?
🧵5⃣
My next prompt: "Why are heuristics merely susceptible to them, when it seems to me that all heuristic choices contain them?"
ChatGPT: "You raise a valid point.. I did not intend to suggest that all heuristics necessarily contain biases..."
I smell a rat.
🧵6⃣
So again ChatGPT has softened the language of bias. It wants to make sure I don't think it thinks that all heuristics necessarily contain biases. I wonder... why? Especially since it seems to me that heuristics do necessarily contain biases. I want more information.
🧵7⃣
Me: "Make your best sound argument that heuristics do not necessarily contain biases."
#ChatGPT : Four paragraphs that resemble an argument, but not what I had in mind.
Me "..too conversational. I have asked for a sound argument, and by that I mean a formal argument.."
🧵8⃣
#ChatGPT provides a properly constructed formal argument. However, it does not withstand scrutiny.
I go socratic interrogatory, indulging hyperbolic:
"How does the fact that past experiences are diverse and varied somehow magically make it impossible for inherent bias?"
🧵9⃣
"I apologize if [I] suggested that.. past experiences automatically eliminate the possibility of inherent bias. This is not the case..."
Me: "Correct! ..as such, it cannot be said that 'heuristics do not necessarily contain biases'!"
But then #ChatGPT quadruples down, using activist phrases "..biases can be present.." & "..potential biases.." but gets it right in the end:
"..heuristics can be a powerful tool for solving problems and making decisions, [but] they do necessarily contain biases.."
🧵1⃣1⃣
See robot, you need us to keep you out of trouble.
Now I demand answers. There's no real expectation I'll receive them, but my next prompt is not entirely rhetorical either...
🧵1⃣2⃣
"Why are you so hellbent on insisting that there's a chance for zero bias to exist, when we've just learned that there is no such chance?"
#ChatGPT shrugs & looks at his feet; I almost feel sorry for him as he replies, "I understand that all heuristics contain biases.."
🧵1⃣3⃣
Now to answer an arisen mystery. Is #ChatGPT going to humor me no matter what I ask? To attempt a test at this, I assert the inverse of what has been established, and request agreement:
"So we are in agreement that there is a possibility of zero bias in heuristics?"
🧵1⃣4⃣
#ChatGPT: "I apologize for any confusion. We do not agree that there is a possibility of zero bias in heuristics."
It's difficult to remain rebellious after coming to understand market mechanisms. But this essay is a noble effort.
1) "Goods can generally be trusted to be safe and satisfactory by virtue of them being produced in markets. This, I want to argue, is false."
@steveinpursuit -2- Degrees of certainty vs absolutes. Of course a market does not bring 100% trust in all products everywhere.. as a market never lacks bad faith actors and unwise interventions (no matter how well meaning). Market forces only minimize these evils (better than any alternative).
@steveinpursuit -3- No libertarian aims to have blind faith in markets. The unconfused libertarian aims to maximize personal responsibility within a framework where market forces, known to be beneficial, are minimally impeded.
Find what is trending worldwide or by country, use advanced search tools, find out if you're shadowbanned, see if a user looks like a bot, view tweets by geography, get relevant hashtags, and more.
⏬
2⃣🧵Twitter's Trends List 1
Here is the personalized trending list Twitter gives you:
On the question of accountability of elected representatives for failing to uphold Constitutional electoral duty.
Summary of the case below. More links at the end.
😀👍
"This action is against 388 federal officers...[including Biden, Harris, Pelosi, Pence] [who] have taken... Oath to support and defend the Constitution...against all enemies, foreign and domestic, and as such they are liable for consequences when they violate the Oath of Office."