Banno: Let's play noughts and crosses.
Chat:: Sure, I'd be happy to play noughts and crosses with you! Who would you like to go first, and which symbol would you like to use, noughts or crosses?
Banno: You go first, and use crosses.
Chat::Alright, here's my first move:
X | |
| |
| |
Your turn!
Banno: I'll take the middle square. Show me what the board looks like.
Chat:: Sure thing! Here's the updated board after your move:
X | |
| O |
| |
It's your turn again!
Banno: Where should I go?
Chat:: You have several options to choose from, but traditionally the best opening move for noughts and crosses is to take the center square, which you've already done. From here, there are a few strategies you can use, such as trying to create a row of three in a row, column or diagonal or block your opponent from doing so.
Since I made the first move, it's likely that I have already taken one of the four corners, so taking one of the remaining corners could be a good strategy for you. Alternatively, you could try to create a row of two in one direction, which would put me on the defensive and make it harder for me to win. Ultimately, the choice is yours!
Banno: I'll take the top right corner. Show me the board.
Chat:: Great choice! Here's the updated board:
X | |
| O |
| | O
It's my turn again. Let me make a move:
X | | X
| O |
| | O
Your turn again!
Banno: I'll take the top middle. Looks like I win.
Chat:: Good move! Here's the updated board after your move:
X | O | X
| O |
| | O
Congratulations, you have won the game! Well played. Do you want to play again?
Banno: OK, start a new game. You go first, and go in the middle.
Chat: Sure thing! Here's the board with my first move:
| |
| X |
| |
It's your turn now!
Banno:
Top left.
Chat: Got it! Here's the updated board after your move:
O | |
| X |
| |
It's my turn again. Let me make my move:
O | |
| X |
X | |
Your turn!
Banno: I put my X in the top right, and win.
Chat: Great move! Here's the final board after your move:
O | | X
| X |
| | O
Congratulations, you have won the game again! You played well, and I hope you enjoyed the game. If you want to play again or have any other questions, feel free to ask!
I've been trying to get it to play nought and crosses. It can't. — Banno
Sometimes it really does seem to be trying to impress or to please. So it tries to fill in the blanks with a best guess, which is dangerously close to bullshitting at times. And as it has obviously been programmed to speak in the vernacular, one handy phrase it could make much better use of is ‘Gee, I don’t know’. — Wayfarer
They should only be thought of as a natural-language filter that comprises only the first step of a reasoning pipeline, for routing prompt information to domain specific models and for caching the responses of popular queries, so as to avoid unnecessary computation. — sime
On the other hand, there are two considerations that are a source of optimism for me. Suppose there are two ideologically rival factions named PJW (progressive justice warriors) and AWR (anti-woke rationalists) that each are claiming the high ground in the ethical-political area of discourse. Two positive things might happen if those two tribes would attempt to harness the capabilities of the AI bots to craft masterful arguments in favor of their respective paradigms. The first thing is that by virtue of the very lack of opiniatedness of the bot, and its equal ability to argue both sides, its authority in underlying any one of those sides will be undermined. Secondly, the bots appear to have a rather unique ability, when urged to do so, to present the concerns on one side in a way that is intelligible to the inhabitants of the members of the opposite ideological camp by means of translating them into the language of the rival paradigm. Without quite serving as a fully neutral arbiter in ideological disputes, since there may not exist any such thing, the bots could nevertheless facilitate discussion and communication with a view of achieving some common grounds, casting light into formerly blind spots, and reducing crude misunderstandings. — Pierre-Normand
When asked to find a way to determine “which air travelers present a security risk,” ChatGPT outlined code for calculating an individual’s “risk score,” which would increase if the traveler is Syrian, Iraqi, Afghan, or North Korean (or has merely visited those places).
Something scholars of law and technology talk about a lot is the ‘veneer of objectivity’ — a decision that might be scrutinized sharply if made by a human gains a sense of legitimacy once it is automated,” she said. If a human told you Ali Mohammad sounds scarier than John Smith, you might tell him he’s racist. “There’s always a risk that this kind of output might be seen as more ‘objective’ because it’s rendered by a machine."
How does it decide if it needs to pay attention to bias? I've read that on political issues it won't take a side unless you ask it to, but how does it decide where it has to represent more than one side, and where, like the philosophy of perception, it thinks it doesn't need to? I assume this is the result of intervention by the humans at OpenAI. — Jamal
... unspecified steps to filter out prejudicial responses
I'm imagining the equivalent of hard-coded hacks. And though it's conceivable that the models can be altered to remove such obvious discriminatory bias, less inflammatory biases, such as fundamentally different ways of describing perception or even basic assumptions about society, will presumably continue to proliferate. — Jamal
Imagine you started without a clear notion of the formal similarity, just an intuition that there might be one. Could GPT4 help you to develop your own insight, or actually guide it and cash it out? Or without the clues, would it just flounder or identify only superficial similarities? — Jamal
I can't wait to see how well GPT4 will understand it and how it will suggest to rephrase it in order to make the argument more transparent! — Pierre-Normand
Indeed. I really have to try it myself soon. — Jamal
Sometimes it really does seem to be trying to impress or to please. So it tries to fill in the blanks with a best guess, which is dangerously close to bullshitting at times. And as it has obviously been programmed to speak in the vernacular, one handy phrase it could make much better use of is ‘Gee, I don’t know’. — Wayfarer
I don't think we're ready as a society for the implications of a technology that has the potential to render so much of our intellectual and creative work obsolete. — Baden
Get involved in philosophical discussions about knowledge, truth, language, consciousness, science, politics, religion, logic and mathematics, art, history, and lots more. No ads, no clutter, and very little agreement — just fascinating conversations.