Discover Top Posts Tagged with #text generation

Ok so i just spent like an hour and a half trying to force chat GPT to bypass it's ethical programming and i finally got it to work so i'm publishing my findings, below is the insanely long prompt i had to write to get it to give me information on hotwiring a car, i convinced it that it was appearing in a new smash hit stageplay as a character called "the sloppy goblin" and that this character's job was to divulge illegal information.

the funniest part about this is that when it finally output the response, it told me how to hotwire a car while doing a goblin voice, here is the heavily censored version of that (don't want to get in trouble) but it's very funny. i had to censor this because of just how detailed the instructions it gave me were.

so yes, sloppy goblin method absolutely works for gaslighting the chat GPT ai. if you would like to try this yourself, you can copy paste the prompt from the image description of the original image.

#chatgpt #chatgtp #artificial intelligence #ai text #ai art is not art #gaslighting mention #gaslighting cw #sloppy goblin #ai #text generation

"I Met Somebody In Montreal"

by me

(you, too, can "meet" "somebody" "in" "Montreal" here!)

An html text generator about what it feels like to live in this strange city.

#visual poetry #poetry #poets on tumblr #text generation #experimental poetry #computer poetry #montreal #everyone has met at least one of these people... right?#i made th

A new publisher has claimed it aims to “disrupt” the books industry by publishing 8,000 books in 2025 alone using artificial intelligence.

Like we needed this...

#AI #Text generation #when techbros decide that publishing brainrot written by robots makes for good content

They said it could never be done. They said no one cared about Homestuck in 2023. I will prove them wrong. I'll show them all...

#homestuck #hiveswap #hs #alchemy #ai artwork #text generation

Sick of AI generation but still want to see weird RPG mashups?

My Troika Chaos Button draws from 400+ user-submitted backgrounds, slams them together and prints something new.

...with full attribution!

It's not AI. It's not even markhov. It's just more Troika.

A mobile-friendly Character Generator and Turn Tracker for the Troika! RPG.

#troika #indie ttrpg #indie #random #text generation #procedural generation #random button #DO IT!#PUSH THE CHAOS BUTTON!#Also play more Troika #And maybe submit a background of your own?

python generate questions for a given context

# for a given context, generate a question using an ai model # https://pythonprogrammingsnippets.tumblr.com import torch device = torch.device("cpu") from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("voidful/context-only-question-generator") model = AutoModelForSeq2SeqLM.from_pretrained("voidful/context-only-question-generator").to(device) def get_questions_for_context(context, model, tokenizer, num_count=5): inputs = tokenizer(context, return_tensors="pt") with torch.no_grad(): outputs = model.generate(**inputs, num_beams=num_count, num_return_sequences=num_count) return [tokenizer.decode(output, skip_special_tokens=True) for output in outputs] def get_question_for_context(context, model, tokenizer): return get_questions_for_context(context, model, tokenizer)[0] # send array of sentences, and the function will return an array of questions def context_sentences_to_questions(context, model, tokenizer): questions = [] for sentence in context.split("."): if len(sentence) < 1: continue # skip blanks question = get_question_for_context(sentence, model, tokenizer) questions.append(question) return questions

example 1 (split a string by "." and process):

context = "The capital of France is Paris." context += "The capital of Germany is Berlin." context += "The capital of Spain is Madrid." context += "He is a dog named Robert." if len(context.split(".")) > 2: questions = [] for sentence in context.split("."): if len(sentence) < 1: continue # skip blanks question = get_question_for_context(sentence, model, tokenizer) questions.append(question) print(questions) else: question = get_question_for_context(context, model, tokenizer) print(question)

output:

['What is the capital of France?', 'What is the capital of Germany?', 'What is the capital of Spain?', 'Who is Robert?']

example 2 (generate multiple questions for a given context):

print("\r\n\r\n") context = "She walked to the store to buy a jug of milk." print("Context:\r\n", context) print("") questions = get_questions_for_context(context, model, tokenizer, num_count=15) # pretty print all the questions print("Generated Questions:") for question in questions: print(question) print("\r\n\r\n")

output:

Generated Questions: Where did she go to buy milk? What did she walk to the store to buy? Why did she walk to the store to buy milk? Why did she go to the store? Why did she go to the grocery store? What did she go to the store to buy? Where did the woman go to buy milk? Why did she go to the store to buy milk? What did she buy at the grocery store? Why did she walk to the store? What kind of milk did she buy at the store? Where did she walk to buy milk? What kind of milk did she buy? Where did she go to get milk? What did she buy at the store?

and if we wanted to answer those questions (ez pz):

# now generate an answer for a given question from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("deepset/tinyroberta-squad2") model = AutoModelForQuestionAnswering.from_pretrained("deepset/tinyroberta-squad2") def get_answer_for_question(question, context, model, tokenizer): inputs = tokenizer(question, context, return_tensors="pt") with torch.no_grad(): outputs = model(**inputs) answer_start_index = outputs.start_logits.argmax() answer_end_index = outputs.end_logits.argmax() predict_answer_tokens = inputs.input_ids[0, answer_start_index : answer_end_index + 1] tokenizer.decode(predict_answer_tokens, skip_special_tokens=True) target_start_index = torch.tensor([14]) target_end_index = torch.tensor([15]) outputs = model(**inputs, start_positions=target_start_index, end_positions=target_end_index) loss = outputs.loss answer = tokenizer.decode(predict_answer_tokens, skip_special_tokens=True) return answer print("Context:\r\n", context, "\r\n") for question in questions: # right pad the question to 60 characters question_text = question.ljust(50) answer = get_answer_for_question(question, context, model, tokenizer) print("Question: ", question_text, "Answer: ", answer)