601–610 of 670 posts
Earlier quoted context omitted.
Also bad, why does it think the surgeon is the father if it could also be the mother?
It's not bad, because it's one of the valid solutions to that riddle. How often do you expect to have every possible answer to your question?
Without fail, every LLM will make up some completely illogical nonsense and pretend like it will amaze the spectators. You can even ask it really leading follow up questions and it will still give you something like:
- Put an Ace of Spades at position 20
- Have your spectator pick a random card and place it on top
- Take back the deck and count out 20 cards
- Amaze them by showing them that their card is at position 20
Lets instead just have a handful of them here and keep some to ourselves.... for science.
Earlier quoted context omitted.
> Is the AI model intuiting your intent? I keep seeing this kind of wording and I wonder: Do you know how LLM's work? Not trying to be catty, actually curious where you sit.
Yes, I understand the basics. LLMs predict the next most probable tokens based on patterns in their training data and the prompt context. For the 'Marathon crater' example, the model doesn't have a concept of 'knowing' versus 'not knowing' in our sense. When faced with an entity it hasn't specifically encountered, it still attempts to generate a coherent response based on similar patterns (like other craters, places…
I want to be clear I'm not pointing this out because you used anthropomorphizing language, but that you used it while being confused about the outcome when if you understand how the machine works it's the most understandable outcome possible.
Earlier quoted context omitted.
Unless I'm missing something glaringly obvious, someone voluntarily labeling a certain prompt to be one of their key benchmark prompts should be way more commercially valuable than a model provider trying ascertain that fact from all the prompts you enter into it. EDIT: I guess they can track identical prompts by multiple unrelated users to deduce the fact it's some sort of benchmark, but at least it costs them somet…
I wrote an anagrammatic poem that poses an enigma, asking the reader: "who am I?" The text progressively reveals its own principle as the poem reaches its conclusion: each verse is an anagrammatic recombination of the recipient's name, and it enunciates this principle more and more literally. The last 4 lines translate to: "If no word vice slams your name here, it's via it, vanquished as such, omitted." All 4 lines a…
> Create a self-working card trick that relies on pre-setting the deck and doesn't require any slight of hand. Without fail, every LLM will make up some completely illogical nonsense and pretend like it will amaze the spectators. You can even ask it really leading follow up questions and it will still give you something like: - Put an Ace of Spades at position 20 - Have your spectator pick a random card and place it…
https://chatgpt.com/share/680bb0a9-6374-8004-b8bd-3dcfdc047b...
Earlier quoted context omitted.
Yes, I understand the basics. LLMs predict the next most probable tokens based on patterns in their training data and the prompt context. For the 'Marathon crater' example, the model doesn't have a concept of 'knowing' versus 'not knowing' in our sense. When faced with an entity it hasn't specifically encountered, it still attempts to generate a coherent response based on similar patterns (like other craters, places…
Okay but by your own understanding it's not drawing on knowledge. It's drawing on probable similarity in association space. If you understand that then nothing here should be confusing, it's all just most probable values. I want to be clear I'm not pointing this out because you used anthropomorphizing language, but that you used it while being confused about the outcome when if you understand how the machine works it…
When I see an LLM confidently generate an answer about a non-existent thing by associating related concepts, I wonder how different is this from humans confidently filling knowledge gaps with our own probability-based assumptions? We do this constantly - connecting dots based on pattern recognition and making statistical leaps between concepts.
If we understand how human minds worked in their entirety, then I'd be more likely to say "ha, stupid LLM, it hallucinates instead of saying I don't know". But, I don't know, I see a strong similarity to many humans. What are weight and biases but our own heavy-weight neural "nodes" built up over a lifetime to say "this is likely to be true because of past experiences"? I say this with only hobbyist understanding of neural science topics mind you.