Mit über 70.000 verkauften Einheiten spielte der Macintosh eine entscheidende Rolle für den Erfolg von Apple . Kurioserweise war die Einführungsveranstaltung sogar noch erfolgreicher als der Mac selbst. Mit einem Budget von 1,5 Millionen US-Dollar drehte der renommierte Ridley Scott einen in klarer Anspielung auf Orwells legendären Roman „Neunzehnhundertvierundachtzig“, der zu einem Meisterwerk und Wendepunkt wurde.
„Prompt Engineering 101“ ist eine Beitragsreihe, die entwickelt und geschrieben wurde, um die Prinzipien und Techniken des Prompt Engineering zu enthüllen, die Kunst, klare und effektive Texte zu verfassen, um Sprachmodelle zu veranlassen und genau das zu bekommen, was Sie suchen. Diese Serie behandelt das Prompt Engineering für eine breite Palette generativer Modelle, einschließlich ChatGPT und anderer Text-zu-Text-Modelle. Erforscht außerdem Text-zu-Bild-Modelle wie Stable Diffusion oder Midjourney und befasst sich mit zusätzlichen Aspekten von LLMs wie Halluzinationen, Datenschutz- und Sicherheitsproblemen und mehr ...
Dies ist Beitrag Nr. 2 der Serie , in dem wir fortgeschrittene Techniken wie Gedankenkette und Selbstkonsistenz behandeln, um Prompt Crafting zu meistern. Ich hoffe du genießt es!
Im ersten Teil dieser Serie zum Thema Prompt Engineering haben wir uns mit den Intuitionen dieser Kunst befasst und eine formale Definition erreicht. Grundsätzlich ist Prompt Engineering ein iterativer Prozess zum Entwerfen und Optimieren klarer und spezifischer Eingabeaufforderungen für ein großes Sprachmodell, um sicherzustellen, dass relevante, genaue und kohärente Antworten generiert werden.
Groß angelegte LLMs wie GPT-3 oder PaLM haben eine beeindruckende Fähigkeit zum Verstehen natürlicher Sprache gezeigt und sich bei Aufgaben wie dem Extrahieren von Informationen aus Texten und dem Generieren von Antworten in einem konsistenten menschlichen Stil als außerordentlich effektiv erwiesen. Dennoch erwies sich LLM als recht robust bei der Bewältigung unbekannter Aufgaben, wenn einige Schussbeispiele in die Eingabeaufforderung aufgenommen wurden. Diese Technik, die von wurde untersucht, um die Modellleistung bei mehreren Benchmarks zu steigern. Ganz zu schweigen davon, dass dadurch Geld und Zeit bei der Feinabstimmung des Modells auf eine neue spezifische Domäne gespart werden.
Ähnlich wie Menschen komplexe Probleme angehen, indem sie sie in einfachere Teilprobleme zerlegen und einer logischen Argumentationslinie folgen, können wir ein Sprachmodell anweisen, dasselbe zu tun. Dieser Ansatz wurde von Wei J et al. untersucht. in . Es zeigte beeindruckende Ergebnisse bei mehreren Benchmarks und bestätigte, dass Chain-of-Thought (CoT) ein solider Ansatz zur Verbesserung der Leistung von LLMs bei häufigen Argumentationsaufgaben ist.
Produkte 🛒
--- 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
Um festzustellen, welche Option bequemer ist, können wir den Preis pro Barren für jede Alternative berechnen (Stückpreis). Wählen Sie als Nächstes die günstigste Option aus. Aus dieser Überlegung heraus stellen wir fest, dass Dove Beauty Bar 14 Riegel die günstigste Option mit einem Einheitspreis von 1,14 $ ist (-22 % pro Riegel als Dove Beauty Bar 1 Riegel ).
Begründung 🧠
- 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
Prompt 💬
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}> """
Antwort 🤖
The best option based on price is Dove Beauty Bar 1 bars for $1.47.
Schreiben wir die Eingabeaufforderung um und weisen das Modell an, einer Gedankenkette zu folgen, um dieses Problem zu lösen, indem wir die magischen Worte „Schritt für Schritt argumentieren“ hinzufügen. Betonen Sie außerdem ausdrücklich das Ziel, eine Möglichkeit zur Kosteneinsparung zu finden.
Prompt 💬
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}> """
Antwort 🤖
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.
Prompt 💬
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? """
Antwort 🤖
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.
Produkte 🛒
--- 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.
Prompt 💬
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}> """
Antwort 🤖
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.
Prompt 💬
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}> """
Antwort 🤖
[ { "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" } ]
Prompt 💬
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}> """
Antwort 🤖
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!
Produkte 🛒
--- 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 """
Prompt 💬
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}> """
Antworten 🤖
(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.
Beim , einem Prozess, der typischerweise mit InstructGPT-Modellen verbunden ist (wofür ChatGPT ein Beispiel ist), hat ein neuartiger Ansatz namens Role Prompting bei den Benutzern an Popularität gewonnen. Bei dieser Methode wird das Modell angewiesen, die Persönlichkeit einer bekannten Entität anzunehmen, um eine bestimmte Aufgabe auszuführen.
Um diese Art der Aufforderung zu veranschaulichen, werden wir GPT-4 bitten, einen Einkaufsvorschlag im einzigartigen Ton von Sheldon Cooper (der berühmten Figur aus der Serie „The Big Bang Theory“) anzupassen und dabei die preiswerten, käfigfreien, großen weißen AA-Eier als Produkt zu verwenden Wir haben weiter oben in diesem Beitrag festgestellt, dass es sich um die beste Kaufoption handelt.
Produkt 🛒
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.
Prompt 💬
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}> """
Antwort 🤖
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.
Prompt 💬
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"
Texte
USA Santa Claus Uruguay
Tokenisierter Text 🪄
USA Santa/Claus U/rug/uay
Prompt 💬
prompt = f""" You will be provided with a list of texts delimited by <>. Your task is to reverse those texts. <{texts}> """
Antwort 🤖
Here are the reversed versions of the texts you provided: < ASU sualC atnaS yaguUr
Prompt 💬
prompt = f""" You will be provided with a list of texts delimited by <>. Your task is to reverse those texts. < USA Santa Claus Uruguay > """
Antwort 🤖
Sure, here are the reversed versions of the texts you provided: < ASU seikooC sualC atnaS yaugurU
1- Wählen Sie das richtige Trennzeichen
Aus Sicht eines LLM sind nicht alle Trennzeichen gleich. Im Allgemeinen ist es praktisch, Trennzeichen zu verwenden, die nicht nur selten in der restlichen Eingabe zu finden sind (um eine Verwechslung des Modells mit der Eingabeaufforderung zu vermeiden), sondern auch nur durch ein Token dargestellt werden. Auf diese Weise reduzieren wir den Verbrauch von Tokens in der Eingabeaufforderung, sparen Hardware-Ressourcen und Geld und ermöglichen es uns, den Token für etwas Wichtigeres zu verwenden.
“““
→ 1 Token```
→ 2 Token---
→ 1 Token###
→ 1 Token< >
→ 2 Token<tag></tag>
→ 5 Token
2- Verarbeiten Sie Ihre Eingaben vor
Anstatt Benutzereingaben als Teil der Eingabeaufforderung an das Modell zu übergeben, wird empfohlen, diese Eingaben mithilfe von Zeichenfolgenmethoden, regulären Ausdrücken oder ähnlichen Tools vorzuverarbeiten. Ziel ist es, unnötige Leerzeichen, Satzzeichen, HTML-Tags und andere überflüssige Elemente zu entfernen, die das Verständnis des Modells oder die Erledigung der Aufgabe behindern könnten. Dieser Ansatz spart nicht nur Token und senkt so die Kosten bei Modellen wie ChatGPT, die pro Token abrechnen, sondern hilft auch bei der Erkennung von zeitnahen Injektionen, Datenschutzbedenken und damit verbundenen Problemen.
3- Prompt Perfekt
Sie können effektive Aufforderungen von Grund auf erstellen, indem Sie bestimmte Prinzipien und Techniken befolgen (wie die in dieser Beitragsreihe vorgestellten). Ein noch besserer Ansatz ist jedoch die Verwendung eines Prompt-Optimierers wie . Dieses Tool nutzt KI, um Ihre benutzerdefinierten Eingabeaufforderungen basierend auf dem spezifischen Zielmodell, das Sie verwenden (GPT-3, GPT-4, Midjourney usw.), zu verbessern.
4- Eingabeaufforderungsvorlagen
Anstatt das Rad neu zu erfinden, lesen Sie Aufforderungsvorlagen, die von Menschen im Internet geteilt werden. Wenn keine Aufforderung Ihren Anforderungen entspricht, können Sie zumindest Ideen übernehmen. Hier sind zwei Websites, von denen Sie verschiedene Eingabeaufforderungsvorlagen für ChatGPT, Midjourney und die beliebtesten Modelle abrufen können:
5- OpenAI-Spielplatz
OpenAI bietet ein leistungsstarkes Tool namens . Mit dieser interaktiven Web-App können Sie mit verschiedenen Modellen experimentieren, die über die offizielle API verfügbar sind, und so bestimmte Parameter optimieren und Standardverhalten ändern. Der Playground ist ein hervorragender Ausgangspunkt für Ihre Experimente und erfordert nicht das Schreiben einer einzigen Codezeile.
🐦 | 👨💼 | 💻 Weitere Geschichten