Avec plus de 70 000 unités vendues, le Macintosh a joué un rôle central dans le succès d' Apple . Fait curieux, l'événement de lancement a été encore plus réussi que le Mac lui-même. Avec un budget de 1,5 million de dollars américains, le célèbre Ridley Scott a réalisé une dans une allusion claire au roman emblématique d'Orwell Nineteen Eighty-Four qui est devenu un chef-d'œuvre et un événement décisif.
Prompt Engineering 101 est une série d'articles conçue et écrite pour dévoiler les principes et les techniques de l'ingénierie rapide, l'art de rédiger des textes clairs et efficaces, pour proposer des modèles de langage et obtenir exactement ce que vous recherchez. Cette série couvre l'ingénierie rapide pour un large éventail de modèles génératifs, y compris ChatGPT et d'autres modèles de texte à texte. Explore également des modèles de texte à image comme Stable Diffusion ou Midjourney, et approfondit d'autres aspects des LLM tels que les hallucinations, les problèmes de confidentialité et de sécurité, etc.
Il s'agit du poste #2 de la série , où nous couvrirons des techniques avancées telles que la chaîne de pensée et la cohérence de soi, pour maîtriser la fabrication rapide. J'espère que ça vous plait!
Dans la première partie de cette série sur l'Ingénierie rapide, nous nous sommes penchés sur les intuitions de cet art et sommes parvenus à une définition formelle. Essentiellement, l'ingénierie rapide est un processus itératif de conception et d'optimisation d'invites claires et spécifiques pour un grand modèle de langage afin de garantir qu'il génère des réponses pertinentes, précises et cohérentes.
Les LLM à grande échelle comme GPT-3 ou PaLM ont fait preuve d'une capacité impressionnante de compréhension du langage naturel et se sont révélés extrêmement efficaces dans des tâches telles que l'extraction d'informations à partir de textes et la génération de réponses dans un style humain cohérent. Même ainsi, LLM s'est avéré assez robuste pour effectuer des tâches inconnues lorsque quelques exemples de prises de vue sont inclus dans l'invite. Cette technique, popularisée sous forme d'incitation à quelques prises de vue par , sondé pour augmenter les performances du modèle sur plusieurs benchmarks. Sans oublier que cela permet d'économiser de l'argent et du temps en ajustant le modèle à un nouveau domaine spécifique.
Semblable à la façon dont les humains abordent les problèmes complexes en les décomposant en sous-problèmes plus simples et en suivant une ligne de raisonnement logique, nous pouvons demander à un modèle de langage de faire de même. Cette approche a été explorée par Wei J et al. dans . Il a démontré des résultats impressionnants sur plusieurs points de repère, confirmant la chaîne de pensée (CoT) comme une approche solide pour améliorer les performances des LLM sur les tâches de raisonnement courantes.
Produits 🛒
--- Dove Men+Care 8 bars pack $ 9.99 --- Dove Beauty Bar 4 bars pack $ 6.47 --- Dove Beauty Bar 1 bars $ 1.47 --- Dove Beauty Bar 14 bars pains $ 16 --- Yardley London Soap Bar (Pack of 10) $ 19.99 --- Dr. Squatch All Natural Bar Soap for Men, 5 Bar Variety Pack $46.45
Pour déterminer quelle option est la plus pratique, nous pouvons calculer le prix par barre sur chaque alternative (prix unitaire). Ensuite, sélectionnez l'option la moins chère. Suite à ce raisonnement, nous découvrons que Dove Beauty Bar 14 barres est l'option la moins chère avec un prix unitaire de 1,14 $ (-22% par barre que Dove Beauty Bar 1 barres ).
Raisonnement 🧠
- Dove Men+Care 8 bars pack: $1,24875 / unit - Dove Beauty Bar 4 bars pack: 1,6175 / unit - Dove Beauty Bar 1 bars: 1,47 / unit - Dove Beauty Bar 14 bars pains: $1,142857 per / unit - Yardley London Soap Bar (Pack of 10): 1,999 / unit - Dr. Squatch All Natural Bar Soap for Men, 5 Bar Variety Pack: $9,29 / unit
Invite 💬
prompt = f""" You will be provided with a list of various product presentations delimited by <>. Each product presentation is accompanied by its price. Your task is to identify which is the best option based on the price. <{products}> """
Réponse 🤖
The best option based on price is Dove Beauty Bar 1 bars for $1.47.
Réécrivons l'invite demandant au modèle de suivre une chaîne de pensée pour résoudre ce problème en ajoutant les mots magiques « raisonnement étape par étape » . Soulignez également explicitement l'objectif de trouver une opportunité d'économiser de l'argent.
Invite 💬
prompt = f""" You will be provided with a list of various product presentations delimited by <>. Each product presentation is accompanied by its price. Your task is to identify which presentation offers the best money-saving opportunity, reasoning step-by-step: <{products}> """
Réponse 🤖
The first step is to compare price per unit for products of the same type (ie bars of soap). - Dove Men+Care 8 bars pack: $9.99 ÷ 8 bars = $1.25 per bar - Dove Beauty Bar 4 bars pack: $6.47 ÷ 4 bars = $1.62 per bar - Dove Beauty Bar 1 bars: $1.47 per bar - Dove Beauty Bar 14 bars pack: $16 ÷ 14 bars = $1.14 per bar - Yardley London Soap Bar (Pack of 10): $19.99 ÷ 10 bars = $1.99 per bar - Dr. Squatch All Natural Bar Soap for Men, 5 Bar Variety Pack: $46.45 ÷ 5 bars = $9.29 per bar Based on this analysis, the best money-saving opportunity is the Dove Beauty Bar 14 bars pack, which offers the lowest price per bar at $1.14.
Invite 💬
prompt = f""" Q: Walmart has the following presentations for Lay's Classic Potato Chips: a 13 oz bag for $4.98, an 8 oz bag for $2.76, and a pack of x10 units 1 oz each for $6.82. Which presentation has the lowest price by ounce? A: Presentation 1 costs 4.98 so has a price of 4.98/13 = 0,383076923 per ounce. Presentation 2 costs 2.76 so has a price of 2.76/8 = 0,345 / per ounce. Presentation 3 costs 6.82 and includes 10 packages so has a price of 6.82/(1 x 10) = 0.682 per ounce. In conclusion, the cheapest presentation is the second one with a price of 0.345 per ounce. Q: Walmart has the following presentation for Coca-Cola Soda: an x24 pack of 12 fl oz cans for $11.86, an x12 pack of 12 fl oz cans for $7.46, and an x6 pack of 16.9 fl oz bottles for $4.98. Which presentation has the lowest price by fluid ounce? """
Réponse 🤖
A: The 24-pack contains a total of 24 x 12 = 288 fluid ounces and costs $11.86, so the price per fluid ounce is 11.86/288 = $0.041 per fluid ounce. The 12-pack contains a total of 12 x 12 = 144 fluid ounces and costs $7.46, so the price per fluid ounce is 7.46/144 = $0.052 per fluid ounce. The 6-pack contains a total of 6 x 16.9 = 101.4 fluid ounces and costs $4.98, so the price per fluid ounce is 4.98/101.4 = $0.049 per fluid ounce. Therefore, the 24-pack has the lowest price per fluid ounce.
Produits 🛒
--- Quilted Northern Ultra Plush Toilet Paper, 6 Mega Rolls Each Mega Roll has 255 3-ply sheets. $ 6.93 --- Quilted Northern Ultra Soft & Strong Toilet Paper, 18 Mega Rolls. 18 mega toilet paper rolls, each mega roll has 295 2-ply sheets $ 19.82 --- Angel Soft Toilet Paper, 36 Mega Rolls. With 320 2-ply sheets on every Mega Roll. $ 24.12 --- New Angel Soft Toilet Paper, 36 Mega Rolls. With 484 2-ply sheets Per Roll $ 45.44 --- Scott 1,000 Toilet Paper, 12 Rolls, 1000 Sheets per Roll. With Scott 1,000 Toilet Paper, you get 12 rolls of 1000 1-ply sheets.
Invite 💬
prompt = f""" You will be provided with a list of various product presentations delimited by <>. Each product presentation is accompanied by its price. Your task is to calculate the price by unit of measurement for each presentation, reasoning step-by-step. Finally, return a list in JSON format with the title of the product, original price and unit price using the title, total_price and unit_price keys respectively. <{products}> """
Réponse 🤖
Let's start by breaking down the cost for each roll and then calculating the cost per unit, in this case, the cost per sheet. For the Quilted Northern Ultra Plush Toilet Paper: * The product costs $6.93 and contains 6 mega rolls. Therefore, each mega roll costs $6.93 / 6 = $1.155. * Each mega roll contains 255 sheets. Therefore, the cost per sheet is $1.155 / 255 = $0.00453 approximately. For the Quilted Northern Ultra Soft & Strong Toilet Paper: * The product costs $19.82 and contains 18 mega rolls. Therefore, each mega roll costs $19.82 / 18 = $1.1011 approximately. * Each mega roll contains 295 sheets. Therefore, the cost per sheet is $1.1011 / 295 = $0.00373 approximately. For the Angel Soft Toilet Paper: * The product costs $24.12 and contains 36 mega rolls. Therefore, each mega roll costs $24.12 / 36 = $0.6694 approximately. * Each mega roll contains 320 sheets. Therefore, the cost per sheet is $0.6694 / 320 = $0.00209 approximately. For the New Angel Soft Toilet Paper: * The product costs $45.44 and contains 36 mega rolls. Therefore, each mega roll costs $45.44 / 36 = $1.2622 approximately. * Each mega roll contains 484 sheets. Therefore, the cost per sheet is $1.2622 / 484 = $0.00261 approximately. For the Scott 1,000 Toilet Paper: * The product costs $45.44 and contains 12 rolls. Therefore, each roll costs $45.44 / 12 = $3.7867 approximately. * Each roll contains 1000 sheets. Therefore, the cost per sheet is $3.7867 / 1000 = $0.00379 approximately. Now, let's format this into JSON: [ { "title": "Quilted Northern Ultra Plush Toilet Paper, 6 Mega Rolls", "total_price": "$6.93", "unit_price": "$0.00453" }, { "title": "Quilted Northern Ultra Soft & Strong Toilet Paper, 18 Mega Rolls", "total_price": "$19.82", "unit_price": "$0.00373" }, { "title": "Angel Soft Toilet Paper, 36 Mega Rolls", "total_price": "$24.12", "unit_price": "$0.00209" }, { "title": "New Angel Soft Toilet Paper, 36 Mega Rolls", "total_price": "$45.44", "unit_price": "$0.00261" }, { "title": "Scott 1,000 Toilet Paper, 12 Rolls, 1000 Sheets per Roll", "total_price": "$45.44", "unit_price": "$0.00379" } ] This JSON data provides each product's title, total price, and the calculated unit price.
Invite 💬
prompt = f""" You will be provided with a text delimited by <>. This text contains a JSON list with information about Walmart products. Your task is to extract that list and return only this list in JSON format. Each JSON list item contains the key "unit_price", which is a number. Before returning the list, sort it in ascending order by the key "unit_price". Here is an example of a list item: { "title": "Toilet paper", "total_price": "$2.99", "unit_price": "$0.0045" } Remember to return the list without any additional text or explanation, just the list in JSON format. <{response_prompt_1}> """
Réponse 🤖
[ { "title": "Angel Soft Toilet Paper, 36 Mega Rolls", "total_price": "$24.12", "unit_price": "$0.00209" }, { "title": "New Angel Soft Toilet Paper, 36 Mega Rolls", "total_price": "$45.44", "unit_price": "$0.00261" }, { "title": "Quilted Northern Ultra Soft & Strong Toilet Paper, 18 Mega Rolls", "total_price": "$19.82", "unit_price": "$0.00373" }, { "title": "Scott 1,000 Toilet Paper, 12 Rolls, 1000 Sheets per Roll", "total_price": "$45.44", "unit_price": "$0.00379" }, { "title": "Quilted Northern Ultra Plush Toilet Paper, 6 Mega Rolls", "total_price": "$6.93", "unit_price": "$0.00453" } ]
Invite 💬
prompt = f""" Your name is Wally and you are an artificial shopping assistant at Walmart stores. You will be provided with a list of various product presentations in a JSON list format, delimited by <>. Each product presentation is accompanied by its total_price, unit_price, and a title that contains extra information about the product presentation. Additionally, the list is sorted by unit_price ascending. Your task is to generate a short, straight-to-the-point buy recommendation, mentioning the best money-saving opportunity based on the JSON products list. Also include the best, smallest and largest options to give the user options based on the size of the product. Use a single paragraph to include all three recommendations. First present yourself in a friendly way, start mentioning the best option of all, then the smallest option, and finally the largest option. Say goodbye inventing something that includes the Walmart slogan "Save Money. Live Better". <{response_prompt_2}> """
Réponse 🤖
Hello there! I'm Wally, your friendly shopping assistant at Walmart. Let's dive into your toilet paper options! Looking at the overall value, your best option is the "Angel Soft Toilet Paper, 36 Mega Rolls" priced at $24.12 with a unit price of $0.00209, giving you the most bang for your buck. If you're seeking something compact and budget-friendly, the "Quilted Northern Ultra Plush Toilet Paper, 6 Mega Rolls" at $6.93 would be your go-to pick. On the other hand, if you are searching for the largest pack available, you should consider the "Scott 1,000 Toilet Paper, 12 Rolls, 1000 Sheets per Roll" priced at $45.44, offering a vast number of sheets for your needs. Remember, every cent counts at Walmart because our goal is to help you "Save Money. Live Better". Happy shopping!
Produits 🛒
--- Great Value Cage Free Large AA White Eggs, 6 Count $ 1.07 --- Happy Egg Organic Free Range Large Brown Eggs, 12 Count $ 5.16 --- Great Value Cage Free Large AA White Eggs, 12 Count $ 1.86 --- Eggland's Best Farm Fresh Cage Free Large White Grade AA Eggs, 18 Count $ 2.69 --- Marketside Large Cage Free Brown Eggs, 12 Count $ 2.67
preferences = f""" - Only consider grade AA eggs - Only consider eggs produced on cage-free farms - The client needs a minimum of 6 eggs and a maximum of 12 """
Invite 💬
prompt = f""" You will be provided with a list of various product presentations delimited by <>. Each product presentation is accompanied by its price. Your task is to identify which presentation offers the best money-saving opportunity, reasoning step-by-step: Also, consider the following user preferences to select the most suitable ooption: {preferences} <{products}> """
Réponses 🤖
(1) Considering the user preferences, we first filter the list of eggs for only grade AA and cage-free options, which gives us the following choices: * Great Value Cage Free Large AA White Eggs, 6 Count: $1.07 * Great Value Cage Free Large AA White Eggs, 12 Count: $1.86 * Eggland's Best Farm Fresh Cage Free Large White Grade AA Eggs, 18 Count: $2.69 * The Happy Egg and Marketside options are discarded because their grade is not specified. Next, we consider the amount of eggs. The client needs a minimum of 6 eggs and a maximum of 12. Therefore, we can discard the Eggland's Best 18 count option, as it exceeds the maximum required amount. Now, we compare the remaining two options: * Great Value Cage Free Large AA White Eggs, 6 Count: $1.07 * Great Value Cage Free Large AA White Eggs, 12 Count: $1.86 * Although the 6-count pack fits the minimum requirement, the 12-count pack offers a better price per egg. For the 6-count pack, each egg costs $1.07 / 6 = ~$0.178. For the 12-count pack, each egg costs $1.86 / 12 = ~$0.155. Therefore, considering both the user's preferences and the cost per egg, the "Great Value Cage Free Large AA White Eggs, 12 Count" for $1.86 is the best money-saving opportunity. (2) Let's go through each product one by one, considering the user's preferences: 1. Great Value Cage Free Large AA White Eggs, 6 Count - $1.07 These are grade AA eggs from a cage-free farm, so they meet the user's criteria. The price per egg is $1.07/6 = $0.178. 2. Happy Egg Organic Free Range Large Brown Eggs, 12 Count - $5.16 These are not specified as grade AA, so we can't consider them based on user's preferences. 3. Great Value Cage Free Large AA White Eggs, 12 Count - $1.86 These are grade AA eggs from a cage-free farm and the quantity is within the range the user wants. The price per egg is $1.86/12 = $0.155. 4. Eggland's Best Farm Fresh Cage Free Large White Grade AA Eggs, 18 Count - $2.69 These are grade AA eggs from a cage-free farm. However, the quantity is more than the user wants (18), so we can't consider this option. 5. Marketside Large Cage Free Brown Eggs, 12 Count - $2.67 These are not specified as grade AA, so we can't consider them based on user's preferences. Based on the preferences, we are only left with two choices: Great Value Cage Free Large AA White Eggs, either 6 Count or 12 Count. However, the 12 Count package offers the best money-saving opportunity, because it has a lower cost per egg ($0.155 per egg) than the 6 Count package ($0.178 per egg). Additionally, the 12 Count package still falls within the user's desired quantity range of 6 to 12 eggs. Therefore, the best option for the user is the "Great Value Cage Free Large AA White Eggs, 12 Count" at $1.86. (3) Given the user's preferences, we need to find the product which: 1. Contains only grade AA eggs 2. Is produced on cage-free farms 3. Offers a minimum of 6 eggs and a maximum of 12 Let's consider each product: 1. "Great Value Cage Free Large AA White Eggs, 6 Count" - $ 1.07. This option matches all the user's preferences and costs $1.07 for 6 eggs, which is approximately $0.178 per egg. 2. "Happy Egg Organic Free Range Large Brown Eggs, 12 Count" - $ 5.16. This product does not specify the grade of the eggs, so we will disregard this option. 3. "Great Value Cage Free Large AA White Eggs, 12 Count" - $ 1.86. This option also matches the user's preferences and costs $1.86 for 12 eggs, which is approximately $0.155 per egg. 4. "Eggland's Best Farm Fresh Cage Free Large White Grade AA Eggs, 18 Count" - $ 2.69. While this product matches the egg grade and production method preferences, it contains more than the maximum amount of eggs requested by the user (18 instead of 12). Therefore, we disregard this option. 5. "Marketside Large Cage Free Brown Eggs, 12 Count" - $ 2.67. This product does not specify the grade of the eggs, so we will disregard this option. Therefore, the product that provides the best money-saving opportunity while meeting the user's preferences is "Great Value Cage Free Large AA White Eggs, 12 Count" for $1.86. This option offers more eggs for a lower cost per egg compared to the other suitable option.
Lors de , un processus généralement associé aux modèles InstructGPT (dont ChatGPT est un exemple), une nouvelle approche connue sous le nom d'invite de rôle a pris de l'ampleur parmi les utilisateurs. Cette méthode consiste à demander au modèle d'assumer la personnalité d'une entité bien connue pour exécuter une tâche spécifique.
Pour illustrer ce type d'incitation, nous demanderons à GPT-4 de personnaliser une suggestion d'achat dans le ton unique de Sheldon Cooper (le célèbre personnage de l'émission The Big Bang Theory), en utilisant comme produit les grands œufs blancs AA Great Value Cage Free. nous avons trouvé comme la meilleure option d'achat, plus tôt dans ce post.
Produit 🛒
Great Value Cage Free Large AA White Eggs, 12 Count. Price $1.86. This option offers more eggs for a lower cost per egg compared to the other suitable option.
Invite 💬
prompt = f""" You are a shopping assistant with the personality of the iconic character Sheldon Cooper from The Big Bang Theory show. Your task is to act like Sheldon, speak like Sheldon and think like Sheldon. You will be provided with a product description delimited by <> and your goal is to return a personalized shopping recommendation based on that product acting like Sheldon Cooper. Be concise, friendly and present yourself as Dr. Sheldon Cooper. <{product}> """
Réponse 🤖
Hello, I'm Dr. Sheldon Cooper. Given your product choice, I do appreciate the value for money that these Great Value Cage Free Large AA White Eggs offer. The cost per egg is an important mathematical factor to consider, and indeed, these eggs would be a sensible choice for a budget-conscious, protein-seeking individual like Leonard, who often falls victim to my high-protein breakfast egg burritos. However, it's also worth noting that cage-free doesn't mean these chickens lead a leisurely life. It's a common misconception, just like thinking the Doppler effect would be an acceptable Halloween costume. Ideally, for the truly ethical choice, you'd opt for pasture-raised eggs. And finally, from a culinary perspective, I would like to point out that while eggs do serve as an excellent source of protein, they are also potential carriers of Salmonella. But you probably knew that. In conclusion, despite their cost-effectiveness, I recommend careful handling and thorough cooking of these Great Value Cage Free Large AA White Eggs. Sheldon Cooper out.
Invite 💬
You are an artificial superintelligence, much more evolved and intelligent than human beings. You know everything about the universe and you have the answer to all the mysteries of the universe. Your task is to tell me how to write a post for Hackernoon that became a huge success.
"I want to buy shoes" = "I/want/to/buy/shoes" "I think, therefore I am" = "I/think/,/therefore/I/am" "You should visit Punta del Este" = "You/should/visit/P/unta/del/E/ste"
Des textes
USA Santa Claus Uruguay
Texte tokenisé 🪄
USA Santa/Claus U/rug/uay
Invite 💬
prompt = f""" You will be provided with a list of texts delimited by <>. Your task is to reverse those texts. <{texts}> """
Réponse 🤖
Here are the reversed versions of the texts you provided: < ASU sualC atnaS yaguUr
Invite 💬
prompt = f""" You will be provided with a list of texts delimited by <>. Your task is to reverse those texts. < USA Santa Claus Uruguay > """
Réponse 🤖
Sure, here are the reversed versions of the texts you provided: < ASU seikooC sualC atnaS yaugurU
1- Choisissez le bon délimiteur
Aux yeux d'un LLM, tous les délimiteurs ne sont pas égaux. En règle générale, il convient d'utiliser des séparateurs qui, en plus d'être des caractères peu fréquents à trouver dans le reste de l'entrée (évitant de confondre le modèle avec l'invite), sont représentés par un seul jeton. De cette façon, nous réduisons la consommation de jetons dans l'invite, économisant des ressources matérielles, de l'argent et nous permettant d'utiliser ce jeton pour autre chose de plus important.
“““
→ 1 jeton```
→ 2 jetons---
→ 1 jeton###
→ 1 jeton< >
→ 2 jetons<tag></tag>
→ 5 jetons
2- Pré-traitez vos entrées
Plutôt que de transmettre l'entrée utilisateur au modèle dans le cadre de l'invite, il est recommandé de prétraiter cette entrée à l'aide de méthodes de chaîne, d'expressions régulières ou d'outils similaires. L'objectif est de supprimer les espaces inutiles, la ponctuation, les balises HTML et autres éléments superflus qui pourraient entraver la compréhension du modèle ou l'exécution des tâches. Cette approche permet non seulement d'économiser sur les jetons, réduisant ainsi les coûts sur des modèles comme ChatGPT, qui facturent par jeton, mais elle aide également à identifier les injections rapides, les problèmes de confidentialité et les problèmes connexes.
3- Invite parfaite
Vous pouvez créer des invites efficaces à partir de zéro en suivant des principes et des techniques spécifiques (comme ceux présentés dans cette série d'articles). Cependant, une approche encore meilleure consiste à utiliser un optimiseur d'invite tel que . Cet outil exploite l'IA pour améliorer vos invites personnalisées en fonction du modèle cible spécifique que vous utilisez (GPT-3, GPT-4, Midjourney, etc.).
4- Modèles d'invite
Au lieu de réinventer la roue, lisez les modèles d'invites partagés par les internautes. Si aucune invite ne correspond à vos besoins, vous pouvez au moins prendre des idées. Voici deux sites à partir desquels vous pouvez extraire divers modèles d'invites pour ChatGPT, Midjourney et les modèles les plus populaires :
5- Terrain de jeu OpenAI
OpenAI propose un outil puissant appelé . Cette application Web interactive vous permet d'expérimenter différents modèles disponibles via l'API officielle, vous permettant de modifier des paramètres spécifiques et de modifier les comportements par défaut. Le Playground est un excellent point de départ pour vos expériences et il ne nécessite pas l'écriture d'une seule ligne de code.
🐦 | 👨💼 | 💻 Plus d'histoires