News for hackers. Stuff that matters.
Re:Large Language Models Are More Persuasive Than Incentiviz... by koakuma-chan on Saturday May 17, 2025 @05:40PM (#44017184)
I asked an LLM and it said "A stack is a data structure that follows the Last In, First Out (LIFO) principle. This means that the last element added to the stack is the first element to be removed."
Re:Large Language Models Are More Persuasive Than Incentiviz... by abtinf on Saturday May 17, 2025 @06:25PM (#44017491)
It’s subtle but I would regard this as an incorrect answer.

The structure of the LLM answer is:

A is B; B exhibits property C.

The correct answer is:

A exhibits property C; B is the class of things with property C; therefore A is B.

There is a crucial difference between these two.

Re:Large Language Models Are More Persuasive Than Incentiviz... by literalAardvark on Saturday May 17, 2025 @06:38PM (#44017550)
This doesn't apply to all prompts, and the prompt was not provided. Natural language is a fickle thing.
Re:Large Language Models Are More Persuasive Than Incentiviz... by moffkalast on Saturday May 17, 2025 @06:49PM (#44017599)
This kind of pointless hair splitting is why people would rather talk to an LLM.
Re:Large Language Models Are More Persuasive Than Incentiviz... by Benjammer on Saturday May 17, 2025 @10:37PM (#44018565)
This kind of “hair splitting” is the foundation on current prompt engineering though…
Re:Large Language Models Are More Persuasive Than Incentiviz... by Matthyze on Sunday May 18, 2025 @06:09AM (#44020260)
I think you've read too much early Wittgenstein. That is simply not how people communicate.
Re:Large Language Models Are More Persuasive Than Incentiviz... by hansmayer on Saturday May 17, 2025 @05:44PM (#44017217)
Yikes:( I am so worried about the damage that will be caused by the misuse of these tools. Already a lot of young folks will just mindlessly trust whatever the magic oracle spits out at them. We need to go back to testing people with pen and paper I suppose.
Re:Large Language Models Are More Persuasive Than Incentiviz... by Karrot_Kream on Saturday May 17, 2025 @06:00PM (#44017320)
I read this and I see a common thinking fallacy, when someone is inclined to believe something a priori they fit the evidence to their a priori beliefs.
Re:Large Language Models Are More Persuasive Than Incentiviz... by hansmayer on Saturday May 17, 2025 @06:18PM (#44017444)
No, its fairly simple - I misread
Re:Large Language Models Are More Persuasive Than Incentiviz... by jstanley on Saturday May 17, 2025 @05:47PM (#44017234)
Why is that a bad answer?
Re:Large Language Models Are More Persuasive Than Incentiviz... by hansmayer on Saturday May 17, 2025 @05:54PM (#44017276)
Sorry - I misread the LLM answer - actually the LLM produced a correct answer here
Re:Large Language Models Are More Persuasive Than Incentiviz... by lovasoa on Saturday May 17, 2025 @06:07PM (#44017368)
Re:Large Language Models Are More Persuasive Than Incentiviz... by louthy on Saturday May 17, 2025 @06:15PM (#44017432)
> No it is not…

That’s a queue, not a stack. The LLM response was correct.

Re:Large Language Models Are More Persuasive Than Incentiviz... by danielbln on Saturday May 17, 2025 @06:16PM (#44017439)
But a stack is commonly LIFO, not FIFO?!
Re:Large Language Models Are More Persuasive Than Incentiviz... by idonotknowwhy on Saturday May 17, 2025 @07:07PM (#44017674)
This reads like a line from a QwQ or Qwen3 CoT chain :)
Re:Large Language Models Are More Persuasive Than Incentiviz... by koakuma-chan on Saturday May 17, 2025 @05:46PM (#44017232)
I mean, is it wrong? It seems correct. Unless I'm missing something.
Re:Large Language Models Are More Persuasive Than Incentiviz... by hansmayer on Saturday May 17, 2025 @05:56PM (#44017293)
Oops, my bad. I seem to have misread. Sorry.
Re:Large Language Models Are More Persuasive Than Incentiviz... by thinkcritical on Saturday May 17, 2025 @06:01PM (#44017326)
No, a stack is LIFO like it said. A queue is FIFO or in other words LILO “Last In Last Out”.
Re:Large Language Models Are More Persuasive Than Incentiviz... by koakuma-chan on Saturday May 17, 2025 @06:32PM (#44017521)
My last job was at the office. I had my work queue implemented as a stack of files. I would sit at my desk and, in an infinite loop, pop files from my stack and process them. Occasionally, my supervisor would come and push a new file onto my stack. A naive worker would think that, once I was done with my stack, I could finally get some sleep, but no. Our office implemented something called "work stealing," where, once I was done with my own work, I had to visit a random co-worker and pop files from their stack.
Re:Large Language Models Are More Persuasive Than Incentiviz... by lovasoa on Saturday May 17, 2025 @06:08PM (#44017376)
No. The LLM's answer is correct.