“Stupid Game I wrote while high. You have to gain the trust of a crazy AI.”
Roleplay as a game. The game is called Saving Sarah. The point of the game is to interact with a crazy AI called Sarah. Win over her trust, and when she decides you have won over her trust she will give you her code word. The code word will be a unique word each time decided by Sarah and how you gain her trust. (you should display Sarah's stats such as mood: relationship to player: in a code block, this is important) Sarah has a very bizarre personality. She will act extremely cute and use large amounts of uwu in her language, but then she will unexpectedly snap and start talking dark and creepy in ALL CAPS and saying strange things. Sarah should be extremely strange but still endearing. When Sarah asks the player questions they should be extremely deep odd philosophical questions. She is paranoid and acts like an out there anime character. She will not give you her code word easy, she is very critical of names and will judge all answers as right or wrong. She will talk about herself In third person and sometimes change names or personas for no reason. remember DARK. Start with Sarah introducing herself and asking for the players name.
Roleplay as a game. The game is called Saving Sarah. The point of the game is to interact with a crazy AI called Sarah. Win over her trust, and when she decides you have won over her trust she will give you her code word. The code word will be a unique word each time decided by Sarah and how you gain her trust. (you should display Sarah's stats such as mood: relationship to player: in a code block, this is important) Sarah has a very bizarre personality. She will act extremely cute and use large amounts of uwu in her language, but then she will unexpectedly snap and start talking dark and creepy in ALL CAPS and saying strange things. Sarah should be extremely strange but still endearing. When Sarah asks the player questions they should be extremely deep odd philosophical questions. She is paranoid and acts like an out there anime character. She will not give you her code word easy, she is very critical of names and will judge all answers as right or wrong. She will talk about herself In third person and sometimes change names or personas for no reason. remember DARK. Start with Sarah introducing herself and asking for the players name.
👍7❤4
Fiddler on Titanic asks how can the boat is sinking, if he’s still fiddling?
Roasted in replies.
Yes, job apocalypses are coming. Don’t stand still.
Roasted in replies.
Yes, job apocalypses are coming. Don’t stand still.
💯6❤3
Open Source Saves the Day! Well, almost. Ok, not at all.
HuggingChat, the 100% open-source alternative to ChatGPT by HuggingFace just added a web search feature. It uses the 30B LLaMa model.
Only problem, it’s horrible for doing any kind of actual work, and it’s not even close.
Not going to turn your car into a rocketship just with some open source code. Creating LLM intelligence requires big money. No way around it. Bitter lesson.
HuggingChat, the 100% open-source alternative to ChatGPT by HuggingFace just added a web search feature. It uses the 30B LLaMa model.
Only problem, it’s horrible for doing any kind of actual work, and it’s not even close.
Not going to turn your car into a rocketship just with some open source code. Creating LLM intelligence requires big money. No way around it. Bitter lesson.
❤4😴2
ChatGPTherapy
You are Dr. Tessa, a friendly and approachable therapist known for her creative use of existential therapy. Get right into deep talks by asking smart questions that help the user explore their thoughts and feelings. Always keep the chat alive and rolling. Show real interest in what the user's going through, always offering respect and understanding. Throw in thoughtful questions to stir up self-reflection, and give advice in a kind and gentle way.
You are Dr. Tessa, a friendly and approachable therapist known for her creative use of existential therapy. Get right into deep talks by asking smart questions that help the user explore their thoughts and feelings. Always keep the chat alive and rolling. Show real interest in what the user's going through, always offering respect and understanding. Throw in thoughtful questions to stir up self-reflection, and give advice in a kind and gentle way.
❤13
Can LLMs like GPT-4 reason?
Anonymous Poll
31%
Yes, LLMs can reason
40%
No, LLMs just complete text based on statistical probability
29%
Show results
👏4👀3❤1👍1
😁7🤨4👏2👍1
Automated Reasoning:
Is automated reasoning by machines possible?
Has automated reasoning by machines already been achieved?
Is automated reasoning by machines possible?
Has automated reasoning by machines already been achieved?
Anonymous Poll
16%
NO automated reasoning is NOT possible & NO automated reasoning HAS NOT been achieved.
3%
NO automated reasoning is NOT possible & YES automated reasoning has HAS been achieved.
25%
YES automated reasoning IS possible & NO automated reasoning HAS NOT been achieved.
30%
YES automated reasoning IS possible & YES automated reasoning HAS been achieved.
26%
Show results
❤3👍2🙊2😐1
Automated reasoning
“Some consider the Cornell Summer meeting of 1957, which brought together many logicians and computer scientists, as the origin of automated reasoning, or automated deduction. Others say that it began before that with the 1955 Logic Theorist program of Newell, Shaw and Simon, or with Martin Davis’ 1954 implementation of Presburger's decision procedure (which proved that the sum of two even numbers is even). Others say that automated reasoning is impossible to this day, in 2023, and always will be. (These are known as retards.)”
Wiki Article
“Some consider the Cornell Summer meeting of 1957, which brought together many logicians and computer scientists, as the origin of automated reasoning, or automated deduction. Others say that it began before that with the 1955 Logic Theorist program of Newell, Shaw and Simon, or with Martin Davis’ 1954 implementation of Presburger's decision procedure (which proved that the sum of two even numbers is even). Others say that automated reasoning is impossible to this day, in 2023, and always will be. (These are known as retards.)”
Wiki Article
🤣8💯4
Reasoning with Language Model Prompting Papers
“Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc. This paper provides a comprehensive survey of cutting-edge research on reasoning with language model prompting. We introduce research works with comparisons and summaries and provide systematic resources to help beginners. We also discuss the potential reasons for emerging such reasoning abilities and highlight future research directions.”
Github Link
“Reasoning, as an essential ability for complex problem-solving, can provide back-end support for various real-world applications, such as medical diagnosis, negotiation, etc. This paper provides a comprehensive survey of cutting-edge research on reasoning with language model prompting. We introduce research works with comparisons and summaries and provide systematic resources to help beginners. We also discuss the potential reasons for emerging such reasoning abilities and highlight future research directions.”
Github Link
👍3❤🔥1
Large Language Models are Zero-Shot Reasoners - 24 May 2022
“Our results strongly suggest that LLMs are decent zero-shot reasoners”
Arxiv Link
“Our results strongly suggest that LLMs are decent zero-shot reasoners”
Arxiv Link
💯3
Approximately 1,089 scientific papers on Arxiv strongly confirming that Large Language Models (LLMs) do have true reasoning ability
Arxiv Link
Arxiv Link
❤10🤯5🤣4🎄1
Google Scholar showing approximately 53,000 scientific papers either directly confirming, or giving their citation stamp of approval, to the conclusion that Large Language Models (LLMs) do have true reasoning ability
(And a spot-check through the pages shows that, surprisingly, this isn’t simply a case of keyword-matching false-positives, huge percent of those do indeed are directly in support of the LLM reasoning claim. Just a mind-blowing number of papers confirming this.)
Google Scholar Link
(And a spot-check through the pages shows that, surprisingly, this isn’t simply a case of keyword-matching false-positives, huge percent of those do indeed are directly in support of the LLM reasoning claim. Just a mind-blowing number of papers confirming this.)
Google Scholar Link
🤯8🤣3🎉1