Datasets:

andrewbai
/

databricks-dolly-10k

Dataset card Data Studio Files Files and versions Community

Split (2)

train · 10k rows

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.

category stringclasses 8 values	messages listlengths 2 2	prompt stringlengths 5 23.6k
classification	[ { "content": "Classify each of these car manufacturers as either French, German, American, Japanese, or other: Audi, Peugeot, Aston Martin, Ssangyong, Chevrolet, BMW", "role": "user" }, { "content": "French: Peugeot\nGerman: Audi, BMW\nAmerican: Chevrolet\nJapanese:\nother: Aston Martin, Ssangyong", "role": "assistant" } ]	Classify each of these car manufacturers as either French, German, American, Japanese, or other: Audi, Peugeot, Aston Martin, Ssangyong, Chevrolet, BMW
classification	[ { "content": "Identify which instrument is string or percussion: Cuica, Kokles", "role": "user" }, { "content": "Kokles is string, Cuica is percussion.", "role": "assistant" } ]	Identify which instrument is string or percussion: Cuica, Kokles
brainstorming	[ { "content": "Is Killing is Sin ? Is it ture", "role": "user" }, { "content": "Killing a human being should not be sin because same goes to any animal. So either both are sin or any one of it is not should not be accepted.", "role": "assistant" } ]	Is Killing is Sin ? Is it ture
general_qa	[ { "content": "What and how should you feed your baby?", "role": "user" }, { "content": "What to feed your baby depends on a number of factors ranging from their age, their health and your preferences. Typically, until your baby is 6 months old, their diet consists exclusively of breast milk or formula. Around 6 months old your baby may be able to start solids. You should consult your physician before modifying the diet of your baby. Some people choose to introduce solids with soft, mushy and simple foods like mashed bananas, avocados or rice cereal. Others will introduce whatever food is being served to the adults — this could be complex foods with spices such as fajitas, curries and hamburgers. Although young babies will rarely have teeth, their gums are very hard and can mash food. For example, a common early food is mini cucumber, which also may alleviate pains with teething. For how to feed your baby, there are two main categories with many variations in between 1/ Baby-led weaning 2/ Spoon fed. Baby-led does what it sounds like — the baby leads their own feeding. This is often done by the caregiver laying out a few foods (Soft, Mashable, Age-appropriate and safe — void of choking hazards) and letting the baby choose which foods to pick up and eat and how much. Spoon-fed means the caregiver is selecting the foods and feeding the baby. There is no right or wrong way to feed your baby. Consult a physician for tips and safety recommendations.", "role": "assistant" } ]	What and how should you feed your baby?
information_extraction	[ { "content": "The North Atlantic Treaty Organization (NATO, /ˈneɪtoʊ/; French: Organisation du traité de l'Atlantique nord, OTAN), also called the North Atlantic Alliance, is an intergovernmental military alliance between 31 member states – 29 European and two North American. Established in the aftermath of World War II, the organization implemented the North Atlantic Treaty, signed in Washington, D.C., on 4 April 1949. NATO is a collective security system: its independent member states agree to defend each other against attacks by third parties. During the Cold War, NATO operated as a check on the perceived threat posed by the Soviet Union. The alliance remained in place after the dissolution of the Soviet Union and has been involved in military operations in the Balkans, the Middle East, South Asia, and Africa. The organization's motto is animus in consulendo liber (Latin for \"a mind unfettered in deliberation\").\n\nNATO's main headquarters are located in Brussels, Belgium, while NATO's military headquarters are near Mons, Belgium. The alliance has targeted its NATO Response Force deployments in Eastern Europe, and the combined militaries of all NATO members include around 3.5 million soldiers and personnel. Their combined military spending as of 2020 constituted over 57 percent of the global nominal total. Moreover, members have agreed to reach or maintain the target defence spending of at least two percent of their GDP by 2024.\n\nNATO formed with twelve founding members and has added new members nine times, most recently when Finland joined the alliance in April 2023. Following the acceptance of its application for membership in June 2022, Sweden is anticipated to become the 32nd member, with its Accession Protocol to the North Atlantic Treaty now in the process of being ratified by the existing members. In addition, NATO currently recognizes Bosnia and Herzegovina, Georgia, and Ukraine as aspiring members. Enlargement has led to tensions with non-member Russia, one of the twenty additional countries participating in NATO's Partnership for Peace programme. Another nineteen countries are involved in institutionalized dialogue programmes with NATO. List all the aspiring members of NATO.", "role": "user" }, { "content": "Bosnia and Herzegovina, Georgia, and Ukraine", "role": "assistant" } ]	The North Atlantic Treaty Organization (NATO, /ˈneɪtoʊ/; French: Organisation du traité de l'Atlantique nord, OTAN), also called the North Atlantic Alliance, is an intergovernmental military alliance between 31 member states – 29 European and two North American. Established in the aftermath of World War II, the organization implemented the North Atlantic Treaty, signed in Washington, D.C., on 4 April 1949. NATO is a collective security system: its independent member states agree to defend each other against attacks by third parties. During the Cold War, NATO operated as a check on the perceived threat posed by the Soviet Union. The alliance remained in place after the dissolution of the Soviet Union and has been involved in military operations in the Balkans, the Middle East, South Asia, and Africa. The organization's motto is animus in consulendo liber (Latin for "a mind unfettered in deliberation"). NATO's main headquarters are located in Brussels, Belgium, while NATO's military headquarters are near Mons, Belgium. The alliance has targeted its NATO Response Force deployments in Eastern Europe, and the combined militaries of all NATO members include around 3.5 million soldiers and personnel. Their combined military spending as of 2020 constituted over 57 percent of the global nominal total. Moreover, members have agreed to reach or maintain the target defence spending of at least two percent of their GDP by 2024. NATO formed with twelve founding members and has added new members nine times, most recently when Finland joined the alliance in April 2023. Following the acceptance of its application for membership in June 2022, Sweden is anticipated to become the 32nd member, with its Accession Protocol to the North Atlantic Treaty now in the process of being ratified by the existing members. In addition, NATO currently recognizes Bosnia and Herzegovina, Georgia, and Ukraine as aspiring members. Enlargement has led to tensions with non-member Russia, one of the twenty additional countries participating in NATO's Partnership for Peace programme. Another nineteen countries are involved in institutionalized dialogue programmes with NATO. List all the aspiring members of NATO.
classification	[ { "content": "Classify each of the following as either a state or a city", "role": "user" }, { "content": "Virginia, Houston, Florida, Los Angeles, Chicago, Phoenix, California", "role": "assistant" } ]	Classify each of the following as either a state or a city
open_qa	[ { "content": "Who was the first country to win the cricket world cup in their home soil", "role": "user" }, { "content": "India was the first country to win Cricket World Cup on home soil in 2011.The Indian cricket team are two times World Champions they also won the 1983 Cricket World Cup beating then world champion West Indies.", "role": "assistant" } ]	Who was the first country to win the cricket world cup in their home soil
closed_qa	[ { "content": "The Hatfield–McCoy feud, also described by journalists as the Hatfield–McCoy conflict, involved two rural American families of the West Virginia–Kentucky area along the Tug Fork of the Big Sandy River in the years 1863–1891. The Hatfields of West Virginia were led by William Anderson \"Devil Anse\" Hatfield, while the McCoys of Kentucky were under the leadership of Randolph \"Ole Ran'l\" McCoy. Those involved in the feud were descended from Joseph Hatfield and William McCoy (born c. 1750). The feud has entered the American folklore lexicon as a metonym for any bitterly feuding rival parties. From the following description of the Hatfield-McCoy feud, identify the person condidered the leader of the Hatfields.", "role": "user" }, { "content": "William Anderson Hatfield, also known as \"Devil Anse\", was considered the leader of the Hatfield clan.", "role": "assistant" } ]	The Hatfield–McCoy feud, also described by journalists as the Hatfield–McCoy conflict, involved two rural American families of the West Virginia–Kentucky area along the Tug Fork of the Big Sandy River in the years 1863–1891. The Hatfields of West Virginia were led by William Anderson "Devil Anse" Hatfield, while the McCoys of Kentucky were under the leadership of Randolph "Ole Ran'l" McCoy. Those involved in the feud were descended from Joseph Hatfield and William McCoy (born c. 1750). The feud has entered the American folklore lexicon as a metonym for any bitterly feuding rival parties. From the following description of the Hatfield-McCoy feud, identify the person condidered the leader of the Hatfields.
information_extraction	[ { "content": "Breaking Bad is an American neo-Western crime drama television series created and produced by Vince Gilligan for AMC. Set and filmed in Albuquerque, New Mexico, the series follows Walter White (Bryan Cranston), an underpaid, overqualified, and dispirited high-school chemistry teacher who is struggling with a recent diagnosis of stage-three lung cancer. White turns to a life of crime and partners with a former student, Jesse Pinkman (Aaron Paul), to produce and distribute methamphetamine to secure his family's financial future before he dies, while navigating the dangers of the criminal underworld. Breaking Bad premiered on AMC on January 20, 2008, and concluded on September 29, 2013, after five seasons consisting of 62 episodes. What is \"Breaking Bad\"?", "role": "user" }, { "content": "Breaking Bad is an American neo-Western crime drama television series created and produced by Vince Gilligan for AMC. Set and filmed in Albuquerque, New Mexico, the series follows Walter White (Bryan Cranston), an underpaid, overqualified, and dispirited high-school chemistry teacher who is struggling with a recent diagnosis of stage-three lung cancer. White turns to a life of crime and partners with a former student, Jesse Pinkman (Aaron Paul), to produce and distribute methamphetamine to secure his family's financial future before he dies, while navigating the dangers of the criminal underworld. Breaking Bad premiered on AMC on January 20, 2008, and concluded on September 29, 2013, after five seasons consisting of 62 episodes.\n\nAmong the show's co-stars are Anna Gunn and RJ Mitte as Walter's wife Skyler and son Walter Jr., and Betsy Brandt and Dean Norris as Skyler's sister Marie Schrader and her husband Hank, a DEA agent. Others include Bob Odenkirk as Walter's and Jesse's lawyer Saul Goodman, Jonathan Banks as private investigator and fixer Mike Ehrmantraut, and Giancarlo Esposito as drug kingpin Gus Fring. The final season introduces Jesse Plemons as the criminally ambitious Todd Alquist, and Laura Fraser as Lydia Rodarte-Quayle, a cunning business executive secretly managing Walter's global meth sales for her company.\n\nBreaking Bad's first season received generally positive reviews, while the rest of its run received unanimous critical acclaim, with praise for the performances, direction, cinematography, screenplay, story, and character development. Since its conclusion, the show has been lauded by critics as one of the greatest television series of all time. It had fair viewership in its first three seasons, but the fourth and fifth seasons saw a moderate rise in viewership when it was made available on Netflix just before the fourth season premiere. Viewership increased more drastically upon the premiere of the second half of the fifth season in 2013. By the time that the series finale aired, it was among the most-watched cable shows on American television. The show received numerous awards, including 16 Primetime Emmy Awards, eight Satellite Awards, two Golden Globe Awards, two Peabody Awards, two Critics' Choice Awards, and four Television Critics Association Awards. Cranston won the Primetime Emmy Award for Outstanding Lead Actor in a Drama Series four times, while Aaron Paul won the Primetime Emmy Award for Outstanding Supporting Actor in a Drama Series three times; Anna Gunn won the Primetime Emmy Award for Outstanding Supporting Actress in a Drama Series twice. In 2013, Breaking Bad entered the Guinness World Records as the most critically acclaimed TV show of all time.\n\nThe series gave rise to the larger Breaking Bad franchise. Better Call Saul, a prequel series featuring Odenkirk, Banks, and Esposito reprising their Breaking Bad roles, as well as many others in guest and recurring appearances, debuted on AMC on February 8, 2015, and concluded on August 15, 2022. A sequel film, El Camino: A Breaking Bad Movie, starring Paul was released on Netflix and in theaters on October 11, 2019.", "role": "assistant" } ]	Breaking Bad is an American neo-Western crime drama television series created and produced by Vince Gilligan for AMC. Set and filmed in Albuquerque, New Mexico, the series follows Walter White (Bryan Cranston), an underpaid, overqualified, and dispirited high-school chemistry teacher who is struggling with a recent diagnosis of stage-three lung cancer. White turns to a life of crime and partners with a former student, Jesse Pinkman (Aaron Paul), to produce and distribute methamphetamine to secure his family's financial future before he dies, while navigating the dangers of the criminal underworld. Breaking Bad premiered on AMC on January 20, 2008, and concluded on September 29, 2013, after five seasons consisting of 62 episodes. What is "Breaking Bad"?
brainstorming	[ { "content": "Name few motivation tips and techniques for learning", "role": "user" }, { "content": "Set clear goals: Provide someone with clear and specific goals that are challenging but achievable. This can give them a sense of purpose and direction, and help them stay focused on what they need to accomplish.\n\nOffer feedback and recognition: Regularly provide feedback and recognition to let someone know that their efforts are noticed and appreciated. This can help boost their confidence and morale, and motivate them to continue performing at a high level.\n\nProvide opportunities for growth and development: Offer someone opportunities to learn new skills, take on new challenges, and grow professionally. This can help them stay engaged and motivated, and feel like they are progressing in their career.\n\nCreate a positive work environment: Foster a positive work environment that is supportive, collaborative, and respectful. This can help someone feel valued and connected to their work, and motivated to contribute to the team's success.\n\nProvide autonomy and trust: Give someone the autonomy and trust they need to make decisions and take ownership of their work. This can help them feel empowered and invested in their work, and motivated to take on new challenges.\n\nOffer incentives and rewards: Provide someone with incentives and rewards, such as bonuses, promotions, or other perks, to recognize and reward their hard work and achievements.\n\nEncourage teamwork and collaboration: Foster a culture of teamwork and collaboration, where people are encouraged to work together and support one another. This can help build camaraderie and motivation, and create a sense of shared purpose.", "role": "assistant" } ]	Name few motivation tips and techniques for learning
open_qa	[ { "content": "What is the difference between a resume and a cv?", "role": "user" }, { "content": "The CV presents a complete history of various credentials like, academic, professional career, training, etc., so the length of the document can vary in some instances. In contrast, a resume is much more concise and primarily highlights specific skills and relevant qualifications for the particular job application. Henceforth, the length of the resume is relatively short.", "role": "assistant" } ]	What is the difference between a resume and a cv?
closed_qa	[ { "content": "Lester D. Menke (December 16, 1918 – March 5, 2016) was a state Representative from the Iowa's 5th and 7th Districts. He served in the Iowa House of Representatives from 1973 to 1985, serving as Speaker pro Tempore from 1981 to 1985. After he served in the Iowa House, Menke served as a liaison between Governor Terry Branstad and the legislature for two years. Menke has a B.A. from Morningside College, where he later served as a member of the board of directors, and attended The University of Iowa College of Law for one year. He worked as a farm owner and for an insurance agency. He served on various school boards and served as president of the Iowa Association of School Boards and State Board of Public Instruction and as director of the National Association of State Boards of Education, as well as serving on the Iowa Educational Radio and Television Facilities Board. Menke received Morningside College's Distinguished Alumni award in 1975. Who was Lester Menke", "role": "user" }, { "content": "Lester D. Menke (December 16, 1918 – March 5, 2016) was a state Representative from the Iowa's 5th and 7th Districts. He served in the Iowa House of Representatives from 1973 to 1985, serving as Speaker pro Tempore from 1981 to 1985. \n\nAfter he served in the Iowa House, Menke served as a liaison between Governor Terry Branstad and the legislature for two years. Menke has a B.A. from Morningside College, where he later served as a member of the board of directors, and attended The University of Iowa College of Law for one year. He worked as a farm owner and for an insurance agency.\n\nHe served on various school boards and served as president of the Iowa Association of School Boards and State Board of Public Instruction and as director of the National Association of State Boards of Education, as well as serving on the Iowa Educational Radio and Television Facilities Board. Menke received Morningside College's Distinguished Alumni award in 1975.", "role": "assistant" } ]	Lester D. Menke (December 16, 1918 – March 5, 2016) was a state Representative from the Iowa's 5th and 7th Districts. He served in the Iowa House of Representatives from 1973 to 1985, serving as Speaker pro Tempore from 1981 to 1985. After he served in the Iowa House, Menke served as a liaison between Governor Terry Branstad and the legislature for two years. Menke has a B.A. from Morningside College, where he later served as a member of the board of directors, and attended The University of Iowa College of Law for one year. He worked as a farm owner and for an insurance agency. He served on various school boards and served as president of the Iowa Association of School Boards and State Board of Public Instruction and as director of the National Association of State Boards of Education, as well as serving on the Iowa Educational Radio and Television Facilities Board. Menke received Morningside College's Distinguished Alumni award in 1975. Who was Lester Menke
open_qa	[ { "content": "What are the four ingredients for beer?", "role": "user" }, { "content": "Water, Barley, Yeast and Hops", "role": "assistant" } ]	What are the four ingredients for beer?
open_qa	[ { "content": "Approx. how many nurses were enrolled in World War 2?", "role": "user" }, { "content": "More than 100,000 nurses were enrolled to the Red Cross during WW2", "role": "assistant" } ]	Approx. how many nurses were enrolled in World War 2?
brainstorming	[ { "content": "Think of a bunch of ways that you could clean a house.", "role": "user" }, { "content": "You can use a Vacuum or bring in a rug cleaner. You could dust extensively. You could powerwash the outside of the house. You could clean the bathrooms with bleach. You could scrub down all of the kitchen with cleaning supplies. You could paint the walls.", "role": "assistant" } ]	Think of a bunch of ways that you could clean a house.
open_qa	[ { "content": "What is the difference between a guitar and a ukulele?", "role": "user" }, { "content": "While a ukulele might be thought of as a small guitar, there are actually numerous differences between the two instruments:\n1. A ukulele has 4 strings while a guitar has 6 strings or sometimes 12\n2. A ukulele's 4 strings are tuned differently from any consecutive series of a guitar's 4 strings", "role": "assistant" } ]	What is the difference between a guitar and a ukulele?
closed_qa	[ { "content": "A large language model (LLM) is a language model consisting of a neural network with many parameters (typically billions of weights or more), trained on large quantities of unlabelled text using self-supervised learning. LLMs emerged around 2018 and perform well at a wide variety of tasks. This has shifted the focus of natural language processing research away from the previous paradigm of training specialized supervised models for specific tasks.\n\nProperties\nThough the term large language model has no formal definition, it often refers to deep learning models having a parameter count on the order of billions or more. LLMs are general purpose models which excel at a wide range of tasks, as opposed to being trained for one specific task (such as sentiment analysis, named entity recognition, or mathematical reasoning). The skill with which they accomplish tasks, and the range of tasks at which they are capable, seems to be a function of the amount of resources (data, parameter-size, computing power) devoted to them, in a way that is not dependent on additional breakthroughs in design.\n\nThough trained on simple tasks along the lines of predicting the next word in a sentence, neural language models with sufficient training and parameter counts are found to capture much of the syntax and semantics of human language. In addition, large language models demonstrate considerable general knowledge about the world, and are able to \"memorize\" a great quantity of facts during training.\n\nHallucinations\nMain article: Hallucination (artificial intelligence)\nIn artificial intelligence in general, and in large language models in particular, a \"hallucination\" is a confident response that does not seem to be justified by the model's training data.\n\nEmergent abilities\n\nOn a number of natural language benchmarks involving tasks such as question answering, models perform no better than random chance until they reach a certain scale (in this case, measured by training computation), at which point their performance sharply increases. These are examples of emergent abilities.\nUnpredictable abilities that have been observed in large language models but that were not present in simpler models (and that were not explicitly designed into the model) are usually called \"emergent abilities\". Researchers note that such abilities \"cannot be predicted simply by extrapolating the performance of smaller models\". These abilities are discovered rather than programmed-in or designed, in some cases only after the LLM has been publicly deployed. Hundreds of emergent abilities have been described. Examples include multi-step arithmetic, taking college-level exams, identifying the intended meaning of a word, chain-of-thought prompting, decoding the International Phonetic Alphabet, unscrambling a word’s letters, identifying offensive content in paragraphs of Hinglish (a combination of Hindi and English), and generating a similar English equivalent of Kiswahili proverbs.\n\nArchitecture and training\nLarge language models have most commonly used the transformer architecture, which, since 2018, has become the standard deep learning technique for sequential data (previously, recurrent architectures such as the LSTM were most common). LLMs are trained in an unsupervised manner on unannotated text. A left-to-right transformer is trained to maximize the probability assigned to the next word in the training data, given the previous context. Alternatively, an LLM may use a bidirectional transformer (as in the example of BERT), which assigns a probability distribution over words given access to both preceding and following context. In addition to the task of predicting the next word or \"filling in the blanks\", LLMs may be trained on auxiliary tasks which test their understanding of the data distribution such as Next Sentence Prediction (NSP), in which pairs of sentences are presented and the model must predict whether they appear side-by-side in the training corpus.\n\nThe earliest LLMs were trained on corpora having on the order of billions of words. The first model in OpenAI's GPT series was trained in 2018 on BookCorpus, consisting of 985 million words. In the same year, BERT was trained on a combination of BookCorpus and English Wikipedia, totalling 3.3 billion words. In the years since then, training corpora for LLMs have increased by orders of magnitude, reaching up to hundreds of billions or trillions of tokens.\n\nLLMs are computationally expensive to train. A 2020 study estimated the cost of training a 1.5 billion parameter model (1-2 orders of magnitude smaller than the state of the art at the time) at $1.6 million.\n\nA 2020 analysis found that neural language models' capability (as measured by training loss) increased smoothly in a power law relationship with number of parameters, quantity of training data, and computation used for training. These relationships were tested over a wide range of values (up to seven orders of magnitude) and no attenuation of the relationship was observed at the highest end of the range (including for network sizes up to trillions of parameters).\n\nApplication to downstream tasks\nBetween 2018 and 2020, the standard method for harnessing an LLM for a specific natural language processing (NLP) task was to fine tune the model with additional task-specific training. It has subsequently been found that more powerful LLMs such as GPT-3 can solve tasks without additional training via \"prompting\" techniques, in which the problem to be solved is presented to the model as a text prompt, possibly with some textual examples of similar problems and their solutions.\n\nFine-tuning\nMain article: Fine-tuning (machine learning)\nFine-tuning is the practice of modifying an existing pretrained language model by training it (in a supervised fashion) on a specific task (e.g. sentiment analysis, named entity recognition, or part-of-speech tagging). It is a form of transfer learning. It generally involves the introduction of a new set of weights connecting the final layer of the language model to the output of the downstream task. The original weights of the language model may be \"frozen\", such that only the new layer of weights connecting them to the output are learned during training. Alternatively, the original weights may receive small updates (possibly with earlier layers frozen).\n\nPrompting\nSee also: Prompt engineering and Few-shot learning (natural language processing)\nIn the prompting paradigm, popularized by GPT-3, the problem to be solved is formulated via a text prompt, which the model must solve by providing a completion (via inference). In \"few-shot prompting\", the prompt includes a small number of examples of similar (problem, solution) pairs. For example, a sentiment analysis task of labelling the sentiment of a movie review could be prompted as follows:\n\nReview: This movie stinks.\nSentiment: negative\n\nReview: This movie is fantastic!\nSentiment:\n\nIf the model outputs \"positive\", then it has correctly solved the task. In zero-shot prompting, no solve examples are provided. An example of a zero-shot prompt for the same sentiment analysis task would be \"The sentiment associated with the movie review 'This movie is fantastic!' is\".\n\nFew-shot performance of LLMs has been shown to achieve competitive results on NLP tasks, sometimes surpassing prior state-of-the-art fine-tuning approaches. Examples of such NLP tasks are translation, question answering, cloze tasks, unscrambling words, and using a novel word in a sentence. The creation and optimisation of such prompts is called prompt engineering.\n\nInstruction tuning\nInstruction tuning is a form of fine-tuning designed to facilitate more natural and accurate zero-shot prompting interactions. Given a text input, a pretrained language model will generate a completion which matches the distribution of text on which it was trained. A naive language model given the prompt \"Write an essay about the main themes of Hamlet.\" might provide a completion such as \"A late penalty of 10% per day will be applied to submissions received after March 17.\" In instruction tuning, the language model is trained on many examples of tasks formulated as natural language instructions, along with appropriate responses. Various techniques for instruction tuning have been applied in practice. OpenAI's InstructGPT protocol involves supervised fine-tuning on a dataset of human-generated (prompt, response) pairs, followed by reinforcement learning from human feedback (RLHF), in which a reward function was learned based on a dataset of human preferences. Another technique, \"self-instruct\", fine-tunes the language model on a training set of examples which are themselves generated by an LLM (bootstrapped from a small initial set of human-generated examples).\n\nhttps://en.wikipedia.org/wiki/Large_language_model Given these paragraphs about Large language models, what are some examples of emergent abilities?", "role": "user" }, { "content": "Examples include multi-step arithmetic, taking college-level exams, identifying the intended meaning of a word, chain-of-thought prompting, decoding the International Phonetic Alphabet, unscrambling a word’s letters, identifying offensive content in paragraphs of Hinglish (a combination of Hindi and English), and generating a similar English equivalent of Kiswahili proverbs.", "role": "assistant" } ]	A large language model (LLM) is a language model consisting of a neural network with many parameters (typically billions of weights or more), trained on large quantities of unlabelled text using self-supervised learning. LLMs emerged around 2018 and perform well at a wide variety of tasks. This has shifted the focus of natural language processing research away from the previous paradigm of training specialized supervised models for specific tasks. Properties Though the term large language model has no formal definition, it often refers to deep learning models having a parameter count on the order of billions or more. LLMs are general purpose models which excel at a wide range of tasks, as opposed to being trained for one specific task (such as sentiment analysis, named entity recognition, or mathematical reasoning). The skill with which they accomplish tasks, and the range of tasks at which they are capable, seems to be a function of the amount of resources (data, parameter-size, computing power) devoted to them, in a way that is not dependent on additional breakthroughs in design. Though trained on simple tasks along the lines of predicting the next word in a sentence, neural language models with sufficient training and parameter counts are found to capture much of the syntax and semantics of human language. In addition, large language models demonstrate considerable general knowledge about the world, and are able to "memorize" a great quantity of facts during training. Hallucinations Main article: Hallucination (artificial intelligence) In artificial intelligence in general, and in large language models in particular, a "hallucination" is a confident response that does not seem to be justified by the model's training data. Emergent abilities On a number of natural language benchmarks involving tasks such as question answering, models perform no better than random chance until they reach a certain scale (in this case, measured by training computation), at which point their performance sharply increases. These are examples of emergent abilities. Unpredictable abilities that have been observed in large language models but that were not present in simpler models (and that were not explicitly designed into the model) are usually called "emergent abilities". Researchers note that such abilities "cannot be predicted simply by extrapolating the performance of smaller models". These abilities are discovered rather than programmed-in or designed, in some cases only after the LLM has been publicly deployed. Hundreds of emergent abilities have been described. Examples include multi-step arithmetic, taking college-level exams, identifying the intended meaning of a word, chain-of-thought prompting, decoding the International Phonetic Alphabet, unscrambling a word’s letters, identifying offensive content in paragraphs of Hinglish (a combination of Hindi and English), and generating a similar English equivalent of Kiswahili proverbs. Architecture and training Large language models have most commonly used the transformer architecture, which, since 2018, has become the standard deep learning technique for sequential data (previously, recurrent architectures such as the LSTM were most common). LLMs are trained in an unsupervised manner on unannotated text. A left-to-right transformer is trained to maximize the probability assigned to the next word in the training data, given the previous context. Alternatively, an LLM may use a bidirectional transformer (as in the example of BERT), which assigns a probability distribution over words given access to both preceding and following context. In addition to the task of predicting the next word or "filling in the blanks", LLMs may be trained on auxiliary tasks which test their understanding of the data distribution such as Next Sentence Prediction (NSP), in which pairs of sentences are presented and the model must predict whether they appear side-by-side in the training corpus. The earliest LLMs were trained on corpora having on the order of billions of words. The first model in OpenAI's GPT series was trained in 2018 on BookCorpus, consisting of 985 million words. In the same year, BERT was trained on a combination of BookCorpus and English Wikipedia, totalling 3.3 billion words. In the years since then, training corpora for LLMs have increased by orders of magnitude, reaching up to hundreds of billions or trillions of tokens. LLMs are computationally expensive to train. A 2020 study estimated the cost of training a 1.5 billion parameter model (1-2 orders of magnitude smaller than the state of the art at the time) at $1.6 million. A 2020 analysis found that neural language models' capability (as measured by training loss) increased smoothly in a power law relationship with number of parameters, quantity of training data, and computation used for training. These relationships were tested over a wide range of values (up to seven orders of magnitude) and no attenuation of the relationship was observed at the highest end of the range (including for network sizes up to trillions of parameters). Application to downstream tasks Between 2018 and 2020, the standard method for harnessing an LLM for a specific natural language processing (NLP) task was to fine tune the model with additional task-specific training. It has subsequently been found that more powerful LLMs such as GPT-3 can solve tasks without additional training via "prompting" techniques, in which the problem to be solved is presented to the model as a text prompt, possibly with some textual examples of similar problems and their solutions. Fine-tuning Main article: Fine-tuning (machine learning) Fine-tuning is the practice of modifying an existing pretrained language model by training it (in a supervised fashion) on a specific task (e.g. sentiment analysis, named entity recognition, or part-of-speech tagging). It is a form of transfer learning. It generally involves the introduction of a new set of weights connecting the final layer of the language model to the output of the downstream task. The original weights of the language model may be "frozen", such that only the new layer of weights connecting them to the output are learned during training. Alternatively, the original weights may receive small updates (possibly with earlier layers frozen). Prompting See also: Prompt engineering and Few-shot learning (natural language processing) In the prompting paradigm, popularized by GPT-3, the problem to be solved is formulated via a text prompt, which the model must solve by providing a completion (via inference). In "few-shot prompting", the prompt includes a small number of examples of similar (problem, solution) pairs. For example, a sentiment analysis task of labelling the sentiment of a movie review could be prompted as follows: Review: This movie stinks. Sentiment: negative Review: This movie is fantastic! Sentiment: If the model outputs "positive", then it has correctly solved the task. In zero-shot prompting, no solve examples are provided. An example of a zero-shot prompt for the same sentiment analysis task would be "The sentiment associated with the movie review 'This movie is fantastic!' is". Few-shot performance of LLMs has been shown to achieve competitive results on NLP tasks, sometimes surpassing prior state-of-the-art fine-tuning approaches. Examples of such NLP tasks are translation, question answering, cloze tasks, unscrambling words, and using a novel word in a sentence. The creation and optimisation of such prompts is called prompt engineering. Instruction tuning Instruction tuning is a form of fine-tuning designed to facilitate more natural and accurate zero-shot prompting interactions. Given a text input, a pretrained language model will generate a completion which matches the distribution of text on which it was trained. A naive language model given the prompt "Write an essay about the main themes of Hamlet." might provide a completion such as "A late penalty of 10% per day will be applied to submissions received after March 17." In instruction tuning, the language model is trained on many examples of tasks formulated as natural language instructions, along with appropriate responses. Various techniques for instruction tuning have been applied in practice. OpenAI's InstructGPT protocol involves supervised fine-tuning on a dataset of human-generated (prompt, response) pairs, followed by reinforcement learning from human feedback (RLHF), in which a reward function was learned based on a dataset of human preferences. Another technique, "self-instruct", fine-tunes the language model on a training set of examples which are themselves generated by an LLM (bootstrapped from a small initial set of human-generated examples). https://en.wikipedia.org/wiki/Large_language_model Given these paragraphs about Large language models, what are some examples of emergent abilities?
open_qa	[ { "content": "What are some things that would cause the velocity of money within an economy to increase?", "role": "user" }, { "content": "The velocity of money is a macro economics term referring to the speed with which money changes hands, which can be determined by dividing the annual aggregate economic output (also called gross domestic product) of a country by the applicable money supply. The velocity of money can be impacted by many things. Growing optimism and confidence among consumers and businesses can increase velocity, whereas a decline in velocity can occur when people and companies become gloomier or more uncertain of their financial futures. Enhancements in technology that make transactions more efficient can also increase velocity.", "role": "assistant" } ]	What are some things that would cause the velocity of money within an economy to increase?
closed_qa	[ { "content": "Sushi (すし, 寿司, 鮨, 鮓, pronounced [sɯɕiꜜ] or [sɯꜜɕi]) is a Japanese dish of prepared vinegared rice (鮨飯, sushi-meshi), usually with some sugar and salt, accompanied by a variety of ingredients (ねた, neta), such as seafood, often raw, and vegetables. Styles of sushi and its presentation vary widely, but the one key ingredient is \"sushi rice\", also referred to as shari (しゃり), or sumeshi (酢飯).\n\nThe inventor of modern sushi is believed to be Hanaya Yohei, who invented nigiri-zushi, a type of sushi most known today, in which seafood is placed on hand-pressed vinegared rice, around 1824 in the Edo period (1603–1867). It was the fast food of the chōnin class in the Edo period.\n\nSushi is traditionally made with medium-grain white rice, though it can be prepared with brown rice or short-grain rice. It is very often prepared with seafood, such as squid, eel, yellowtail, salmon, tuna or imitation crab meat. Many types of sushi are vegetarian. It is often served with pickled ginger (gari), wasabi, and soy sauce. Daikon radish or pickled daikon (takuan) are popular garnishes for the dish.\n\nSushi is sometimes confused with sashimi, a similar dish in Japanese cuisine that consists of thinly sliced raw fish or occasionally meat. What is a Japanese dish of prepared rice, usually with some sugar and salt, accompanied by a variety of ingredients, such as seafood, often raw, and vegetables?", "role": "user" }, { "content": "Sushi is the answer to the question.", "role": "assistant" } ]	Sushi (すし, 寿司, 鮨, 鮓, pronounced [sɯɕiꜜ] or [sɯꜜɕi]) is a Japanese dish of prepared vinegared rice (鮨飯, sushi-meshi), usually with some sugar and salt, accompanied by a variety of ingredients (ねた, neta), such as seafood, often raw, and vegetables. Styles of sushi and its presentation vary widely, but the one key ingredient is "sushi rice", also referred to as shari (しゃり), or sumeshi (酢飯). The inventor of modern sushi is believed to be Hanaya Yohei, who invented nigiri-zushi, a type of sushi most known today, in which seafood is placed on hand-pressed vinegared rice, around 1824 in the Edo period (1603–1867). It was the fast food of the chōnin class in the Edo period. Sushi is traditionally made with medium-grain white rice, though it can be prepared with brown rice or short-grain rice. It is very often prepared with seafood, such as squid, eel, yellowtail, salmon, tuna or imitation crab meat. Many types of sushi are vegetarian. It is often served with pickled ginger (gari), wasabi, and soy sauce. Daikon radish or pickled daikon (takuan) are popular garnishes for the dish. Sushi is sometimes confused with sashimi, a similar dish in Japanese cuisine that consists of thinly sliced raw fish or occasionally meat. What is a Japanese dish of prepared rice, usually with some sugar and salt, accompanied by a variety of ingredients, such as seafood, often raw, and vegetables?
open_qa	[ { "content": "What kind of milk is Vietnamese coffee often served with?", "role": "user" }, { "content": "Vietnamese coffee is often brewed over sweetened condensed milk.", "role": "assistant" } ]	What kind of milk is Vietnamese coffee often served with?
open_qa	[ { "content": "is a career in enterprise software a good was to go?", "role": "user" }, { "content": "yes", "role": "assistant" } ]	is a career in enterprise software a good was to go?
open_qa	[ { "content": "What is ClassRanked?", "role": "user" }, { "content": "ClassRanked is an American educational technology company based in Salt Lake City, UT that offers higher education enterprise software (SaaS) solutions for course evaluation, reporting, and survey management.\n\nThe company was founded at Duke University as a data-centric platform aiding students with course registration and subsequently shifted focus to building software for colleges and universities in 2022.", "role": "assistant" } ]	What is ClassRanked?
information_extraction	[ { "content": "Fanny Patton was a stern-wheel driven steamboat that operated on the Willamette River, in Oregon, starting in August 1865. This steamer operated from 1865 to 1880 for various owners, and was a considered a profitable vessel. The steamer was named for the daughter of businessman Edwin N Cook, Frances Mary \"Fannie\" Cooke (1837–1886). Edwin N. Cook was one of the principals of the People's Transportation Company What was the Fannie Patton steamboat", "role": "user" }, { "content": "The Fannie Patton was a steamboat operated in 1865. It was named after the daughter of businessman Edwin Cook and Frances Mary \"Fannie\" Cooke. It was operated on the Willamette River in Oregon", "role": "assistant" } ]	Fanny Patton was a stern-wheel driven steamboat that operated on the Willamette River, in Oregon, starting in August 1865. This steamer operated from 1865 to 1880 for various owners, and was a considered a profitable vessel. The steamer was named for the daughter of businessman Edwin N Cook, Frances Mary "Fannie" Cooke (1837–1886). Edwin N. Cook was one of the principals of the People's Transportation Company What was the Fannie Patton steamboat
closed_qa	[ { "content": "In 2004, Nintendo released the Nintendo DS, which featured such innovations as dual screens – one of which being a touchscreen – and wireless connectivity for multiplayer play. Throughout its lifetime, more than 154 million units were sold, making it the most successful handheld console and the second best-selling console in history. In 2005, Nintendo released the Game Boy Micro, the last system in the Game Boy line. Sales did not meet Nintendo's expectations, with 2.5 million units being sold by 2007. In mid-2005, the Nintendo World Store was inaugurated in New York City. Given this paragraph about video game consoles, when was the Nintendo DS released?", "role": "user" }, { "content": "2004", "role": "assistant" } ]	In 2004, Nintendo released the Nintendo DS, which featured such innovations as dual screens – one of which being a touchscreen – and wireless connectivity for multiplayer play. Throughout its lifetime, more than 154 million units were sold, making it the most successful handheld console and the second best-selling console in history. In 2005, Nintendo released the Game Boy Micro, the last system in the Game Boy line. Sales did not meet Nintendo's expectations, with 2.5 million units being sold by 2007. In mid-2005, the Nintendo World Store was inaugurated in New York City. Given this paragraph about video game consoles, when was the Nintendo DS released?
open_qa	[ { "content": "What is the difference between American Football and European Football?", "role": "user" }, { "content": "Prior to American Football coming into existence, European Football was played throughout the world as an athletic sport that entailed kicking a round ball into an opponent's goal. European Football is typically played on a grass turf surface called a pitch. European Football was actually first called soccer before its adoption by the entire world and ended up settling on the name football. This is where the common confusion surrounds European Football and American Football. American Football, created much later than European Football, is played with a pig skin with a prolate shape on a grass turf surface, much like European Football. In American Football, instead of using their feet, players use their hands to pass the ball to one another through the air or hand the ball off to one another and attempt to run into the opponent's endzone. When European Football eventually came to the United States, the moniker soccer remained with the sport. This is why European Football is the same as American Soccer and American Football is not the same as European Football.", "role": "assistant" } ]	What is the difference between American Football and European Football?
open_qa	[ { "content": "“Social Distancing” refers to keeping a safe distance of", "role": "user" }, { "content": "About 3 to 6 feet from others", "role": "assistant" } ]	“Social Distancing” refers to keeping a safe distance of
open_qa	[ { "content": "Whats the name of the person who wrote the US declaration of independence?", "role": "user" }, { "content": "Thomas Jefferson", "role": "assistant" } ]	Whats the name of the person who wrote the US declaration of independence?
general_qa	[ { "content": "What is the meaning of life?", "role": "user" }, { "content": "The world is a vast, beautiful and complex place. The meaning of life is to find loved ones to join us on this journey; to be present in the short time we have on the earth. The meaning of life is to experience living. To lay in a dark field, watching the stars glow. To stand in the pouring rain, feeling giant drops drip down your chin. To watch a lightning storm and let the thunder rumble through your chest. To witness a child throw their head back with peels of laughter. The meaning of life is to wonder. To gaze upon the great abyss and ask the \"how\" and \"why\" of the universe. The meaning of life is to leave the earth the same, or slightly better than you were given. To stand up for injustice. To protect children. To make the day slightly easier for someone. Meaning can be found in any moment in your time here on earth; go live it!", "role": "assistant" } ]	What is the meaning of life?
classification	[ { "content": "Is this hockey, baseball, or both?", "role": "user" }, { "content": "Puck, Ball, Ice, Dirt, Skates, Cleats, Gloves, Glove, Bat, Stick, Pads, Helmet", "role": "assistant" } ]	Is this hockey, baseball, or both?
general_qa	[ { "content": "What is the Shy Plant?", "role": "user" }, { "content": "The scientific name of the shy plant also known as the shame plant is Mimosa pudica, which means shy, bashful, and sensitive. The structures of the shy plant are interesting; it has an herbaceous stem. As well as a dicot on a monocot stem. It has beautiful flowers and leaves that are green, and they are thigmotropism negative. When the shy plant's leaves are touched, they curl up. The Shy plant needs direct sunlight, and 70 to 80 degrees indoors is a good place for it. When the need to water comes, the soil must be 50% dry. The medical value of the Shy plant is great. It helps with Hemorrhoids, infections, sores, and sinuses.", "role": "assistant" } ]	What is the Shy Plant?
open_qa	[ { "content": "What is the current best TV show?", "role": "user" }, { "content": "Ted Lasso because of it's heart wrenching plot, amazingly developed characters & an overall positive message. It also provides example of relatability in the characters to your own personal life.", "role": "assistant" } ]	What is the current best TV show?
brainstorming	[ { "content": "Give me a list of the top ten movies, according to IMDb ratings.", "role": "user" }, { "content": "1. The Shawshank Redemption (1994), 9.2 points\n2. The Godfather (1972) 9.2 points\n3. The Dark Knight (2008), 9.0 points\n4. The Godfather Part II (1974), 9.0 points\n5. 12 Angry Men (1957), 9.0 points\n6. Schindler's List (1993), 8.9 points\n7. The Lord of the Rings: The Return of the King (2003), 8.9 points\n8. Pulp Fiction (1994), 8.8 points\n9. The Lord of the Rings: The Fellowship of the Ring (2001), 8.8 points\n10. The Good, the Bad and the Ugly (1966), 8.8 points", "role": "assistant" } ]	Give me a list of the top ten movies, according to IMDb ratings.
summarization	[ { "content": "In physics, gravity (from Latin gravitas 'weight') is a fundamental interaction which causes mutual attraction between all things with mass or energy. Gravity is, by far, the weakest of the four fundamental interactions, approximately 10^38 times weaker than the strong interaction, 10^36 times weaker than the electromagnetic force and 10^29 times weaker than the weak interaction. As a result, it has no significant influence at the level of subatomic particles. However, gravity is the most significant interaction between objects at the macroscopic scale, and it determines the motion of planets, stars, galaxies, and even light. What is gravity?", "role": "user" }, { "content": "Gravity can be described as the fundamental interaction which causes mutual attraction between all objects with mass or energy. While it is considered the weakest of the four fundamental forces (electromagnetic, strong interaction, and weak interaction), it is most significant force at the macroscopic scale and can influence the motion of planets, stars, galaxies, and light.", "role": "assistant" } ]	In physics, gravity (from Latin gravitas 'weight') is a fundamental interaction which causes mutual attraction between all things with mass or energy. Gravity is, by far, the weakest of the four fundamental interactions, approximately 10^38 times weaker than the strong interaction, 10^36 times weaker than the electromagnetic force and 10^29 times weaker than the weak interaction. As a result, it has no significant influence at the level of subatomic particles. However, gravity is the most significant interaction between objects at the macroscopic scale, and it determines the motion of planets, stars, galaxies, and even light. What is gravity?
summarization	[ { "content": "The most critical and controversial provision in the treaty was: \"The Allied and Associated Governments affirm and Germany accepts the responsibility of Germany and her allies for causing all the loss and damage to which the Allied and Associated Governments and their nationals have been subjected as a consequence of the war imposed upon them by the aggression of Germany and her allies.\" The other members of the Central Powers signed treaties containing similar articles. This article, Article 231, became known as the War Guilt clause. The treaty required Germany to disarm, make ample territorial concessions, and pay reparations to certain countries that had formed the Entente powers. In 1921 the total cost of these reparations was assessed at 132 billion gold marks (then $31.4 billion or £6.6 billion, roughly equivalent to US$442 billion or UK£284 billion in 2023). Because of the way the deal was structured, the Allied Powers intended Germany would only ever pay a value of 50 billion marks. What were the key points of the Treaty of Versailles?", "role": "user" }, { "content": "The Treaty of Versailles was a peace treaty to end World War I. The critical point in the treaty between the Germans and the Allied powers was that Germany accepted full responsibility for the loss and damage incurred to the Allies. Germany was required to disarm and pay reparations estimated at $31.4 billion in 1921.", "role": "assistant" } ]	The most critical and controversial provision in the treaty was: "The Allied and Associated Governments affirm and Germany accepts the responsibility of Germany and her allies for causing all the loss and damage to which the Allied and Associated Governments and their nationals have been subjected as a consequence of the war imposed upon them by the aggression of Germany and her allies." The other members of the Central Powers signed treaties containing similar articles. This article, Article 231, became known as the War Guilt clause. The treaty required Germany to disarm, make ample territorial concessions, and pay reparations to certain countries that had formed the Entente powers. In 1921 the total cost of these reparations was assessed at 132 billion gold marks (then $31.4 billion or £6.6 billion, roughly equivalent to US$442 billion or UK£284 billion in 2023). Because of the way the deal was structured, the Allied Powers intended Germany would only ever pay a value of 50 billion marks. What were the key points of the Treaty of Versailles?
general_qa	[ { "content": "What is a Series I-Bond?", "role": "user" }, { "content": "An I-Bond is a savings bond you can purchase from treasury direct that helps protect you from inflation. An I-Bond earns interest at both a fixed rate and the inflation rate, which is determined by the treasury department and is adjusted twice a year. You can purchase up to $10,000 of electronic I-Bonds per calendar year.", "role": "assistant" } ]	What is a Series I-Bond?
classification	[ { "content": "Which characters belong to DC or Marvel Universe? Red Hood, Bucky Barnes", "role": "user" }, { "content": "Red Hood is DC, Bucky Barnes is Marvel", "role": "assistant" } ]	Which characters belong to DC or Marvel Universe? Red Hood, Bucky Barnes
general_qa	[ { "content": "Explain the Fibonacci sequence", "role": "user" }, { "content": "The Fibonacci sequence is a sequence of numbers, where each number is the sum of the two numbers before that number. The Fibonacci sequence usually starts with zero followed by one. The next number in the sequence is then the sum of the preceding numbers, one and zero, which is one again. The following number is the sum of one and one: two. According to the same logic, the first ten numbers of the Fibonacci sequence are: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34.", "role": "assistant" } ]	Explain the Fibonacci sequence
closed_qa	[ { "content": "King Field (alternately, Kingfield) is a neighborhood in the Southwest community in Minneapolis, Minnesota. Its boundaries are 36th Street to the north, Interstate 35W to the east, 46th Street to the south, and Lyndale Avenue to the west. King Field, within the King Field neighborhood is a park named after Martin Luther King Jr.\n\nThis was farm country in the 2nd half of the 19th century. Transportation was by horse and buggy. Fewer than 20 farms had been established by 1874. C.C. Garvey owned a dairy farm near 44th Street and Grand Ave. George Bichnell farmed 18 acres (73,000 m2) of land from Lyndale to Pleasant, 42nd to 43rd Streets. Hiram Van Nest farmed 28 acres (110,000 m2) of land from 40th to 42nd, Pleasant to Lyndale. The Farmsworth farm occupied 57 acres (230,000 m2) south of 47th Street and East of Nicollet. Were cars used for transportation in the 19th century in King Field?", "role": "user" }, { "content": "No, transportation was by horse and buggy", "role": "assistant" } ]	King Field (alternately, Kingfield) is a neighborhood in the Southwest community in Minneapolis, Minnesota. Its boundaries are 36th Street to the north, Interstate 35W to the east, 46th Street to the south, and Lyndale Avenue to the west. King Field, within the King Field neighborhood is a park named after Martin Luther King Jr. This was farm country in the 2nd half of the 19th century. Transportation was by horse and buggy. Fewer than 20 farms had been established by 1874. C.C. Garvey owned a dairy farm near 44th Street and Grand Ave. George Bichnell farmed 18 acres (73,000 m2) of land from Lyndale to Pleasant, 42nd to 43rd Streets. Hiram Van Nest farmed 28 acres (110,000 m2) of land from 40th to 42nd, Pleasant to Lyndale. The Farmsworth farm occupied 57 acres (230,000 m2) south of 47th Street and East of Nicollet. Were cars used for transportation in the 19th century in King Field?
classification	[ { "content": "Which films contain Tom Cruise and which do not contain Tom Cruise: \"Trading Places\", \"Risky Business\", \"The Hunt for Red October\", \"Top Gun\", \"The Hangover\", \"Born on the 4th of July\", \"Saving Private Ryan\", and \"Reds\"", "role": "user" }, { "content": "The films which contain Tom Cruise are: \"Risky Business\", \"Top Gun\", and \"Born on the 4th of July.\" The films which do not contain Tom Cruise are: \"Trading Places\", \"The Hunt for Red October\",\"The Hangover\", \"Saving Private Ryan\", and \"Reds.\"", "role": "assistant" } ]	Which films contain Tom Cruise and which do not contain Tom Cruise: "Trading Places", "Risky Business", "The Hunt for Red October", "Top Gun", "The Hangover", "Born on the 4th of July", "Saving Private Ryan", and "Reds"
brainstorming	[ { "content": "What steps can I take to avoid getting hit by a falling window from a skyscraper while walking about in downtown during high winds?", "role": "user" }, { "content": "Here are some steps you can take to avoid getting hit by falling windows detached from tall building by strong winds from cyclones or tornadoes: \n1. The space area close to a doorway or near windows is most likely to be affected by falling items, and it is best to stay away from buildings, trees and tall electric or telephone poles. Find an open space, far away from these objects and stay low to the ground to reduce your chances of being hit by debris.\n2. One of the safest places to avoid getting hit by falling objects is underground in a basement with no windows. Try to find underground spaces in downtown like the lower levels of buildings and malls, or the subway. \n3. If you absolutely need to be outside and close to tall buildings, try to stay alert and keep an eye out for falling debris. \n4. You might think that being inside a car would be a safe option, but vehicles are notoriously dangerous places to be in during high winds because of their susceptibility to being blown over or blown away or for their windows to explode.", "role": "assistant" } ]	What steps can I take to avoid getting hit by a falling window from a skyscraper while walking about in downtown during high winds?