Prompt - Historique des versions

Jboscher le 2 mai 2023 à 12:43

2023-05-02T12:43:18Z

← Version précédente		Version du 2 mai 2023 à 12:43
Ligne 1 :		Ligne 1 :
	Un prompt est une commande textuelle transmise afin d'exécuter une action. Cette commande s'adresse principalement aux LLM (Large Language Model) ou aux logiciels de génération d'images entraînées pour comprendre ces commandes.		Un prompt est une commande textuelle transmise afin d'exécuter une action. Cette commande s'adresse principalement aux LLM (Large Language Model) ou aux logiciels de génération d'images entraînées pour comprendre ces commandes.

			Exemples:

			Un prompt basique, le LLM (Large Language Model) poursuit le texte commencé.

			Prompt:
			Four score and seven years ago our

			Réponse:
			fathers brought forth on this continent, a new nation, conceived in Liberty, and dedicated to the proposition that all men are created

			Les prompts peuvent être aussi des instructions simples ou complexes.

			Prompt:
			Write an introduction for a weekly newsletter.

			Réponse:
			Welcome to our weekly newsletter. This week we have a special focus on productivity. We'll be sharing tips and tricks on how to be productive in all areas of your life. We hope you enjoy and please share with your friends!

			ou dans un cas plus complexe :

			Prompt:
			Write an introduction for a weekly newsletter to my company named Contoso. It should mention the great all hands meeting we had last week and thank the team for all their hard work over the tough past few months.

			Réponse:
			Welcome to Contoso's weekly newsletter! We had a great all hands meeting last week and I want to thank the team for all their hard work over the tough past few months. We're looking forward to a bright future and I'm confident that with our team's dedication and commitment, we will achieve great things. Thank you for being a part of our team and I look forward to working with you all in the coming weeks and months.

			On peut aussi écrire des prompts du type "Primary Content" où un texte est modifié.

			Prompt:
			Can you please tell me how to get to the museum?
			Translate to French:

			Réponse:
			Pouvez-vous s'il vous plaît me dire comment aller au musée?


	Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.[4]		Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.[4]

Jboscher le 2 mai 2023 à 09:52

2023-05-02T09:52:44Z

← Version précédente		Version du 2 mai 2023 à 09:52
Ligne 17 :		Ligne 17 :
	* [https://www.promptingguide.ai/fr] Prompt Engineering Guide (fr)		* [https://www.promptingguide.ai/fr] Prompt Engineering Guide (fr)
	* [https://www.youtube.com/watch?v=dOxUroR57xs] Prompt Engineering Overview		* [https://www.youtube.com/watch?v=dOxUroR57xs] Prompt Engineering Overview
			* [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions] Learn how to work with the ChatGPT and GPT-4 models

Jboscher le 2 mai 2023 à 09:37

2023-05-02T09:37:18Z

← Version précédente		Version du 2 mai 2023 à 09:37
Ligne 2 :		Ligne 2 :

	Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.[4]		Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.[4]

			Ecrire un prompt, contrairement à ce qu'on peut imaginer, n'est pas chose facile. Il faut faire l'analogie avec le piano. Obtenir des notes est facile, bien jouer est très compliqué.

			While these models are extremely powerful, their behavior is also very sensitive to the prompt. This makes prompt construction an important skill to develop.
			Prompt construction can be difficult. In practice, the prompt acts to configure the model weights to complete the desired task, but it's more of an art than a science, often requiring experience and intuition to craft a successful prompt. [1]


Ligne 11 :		Ligne 16 :
	* [https://github.com/dair-ai/Prompt-Engineering-Guide] Prompt Engineering Guide		* [https://github.com/dair-ai/Prompt-Engineering-Guide] Prompt Engineering Guide
	* [https://www.promptingguide.ai/fr] Prompt Engineering Guide (fr)		* [https://www.promptingguide.ai/fr] Prompt Engineering Guide (fr)
			* [https://www.youtube.com/watch?v=dOxUroR57xs] Prompt Engineering Overview

Jboscher le 2 mai 2023 à 08:56

2023-05-02T08:56:45Z

← Version précédente		Version du 2 mai 2023 à 08:56
Ligne 10 :		Ligne 10 :
	* [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions] Prompt engineering techniques		* [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions] Prompt engineering techniques
	* [https://github.com/dair-ai/Prompt-Engineering-Guide] Prompt Engineering Guide		* [https://github.com/dair-ai/Prompt-Engineering-Guide] Prompt Engineering Guide
			* [https://www.promptingguide.ai/fr] Prompt Engineering Guide (fr)

Jboscher le 1 mai 2023 à 07:36

2023-05-01T07:36:49Z

← Version précédente		Version du 1 mai 2023 à 07:36
Ligne 1 :		Ligne 1 :
	Un prompt est une commande textuelle transmise afin d'exécuter une action. Cette commande s'adresse principalement aux LLM (Large Language Model) ou aux logiciels de génération d'images entraînées pour comprendre ces commandes.		Un prompt est une commande textuelle transmise afin d'exécuter une action. Cette commande s'adresse principalement aux LLM (Large Language Model) ou aux logiciels de génération d'images entraînées pour comprendre ces commandes.


	Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.[4]		Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.[4]

Jboscher le 1 mai 2023 à 07:33

2023-05-01T07:33:15Z

← Version précédente	Version du 1 mai 2023 à 07:33
Ligne 1 :	Ligne 1 :
		Un prompt est une commande textuelle transmise afin d'exécuter une action. Cette commande s'adresse principalement aux LLM (Large Language Model) ou aux logiciels de génération d'images entraînées pour comprendre ces commandes.


		Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.[4]

Jboscher : Page créée avec «  == Références == * [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/prompt-engineering] Introduction to prompt engineering * [https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/] ChatGPT Prompt Engineering for Developers * [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions] Prompt engineering techniques... »

2023-05-01T07:29:28Z

Page créée avec «  == Références == * [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/prompt-engineering] Introduction to prompt engineering * [https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/] ChatGPT Prompt Engineering for Developers * [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions] Prompt engineering techniques... »

Nouvelle page

== Références ==

* [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/prompt-engineering] Introduction to prompt engineering
* [https://www.deeplearning.ai/short-courses/chatgpt-prompt-engineering-for-developers/] ChatGPT Prompt Engineering for Developers
* [https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/advanced-prompt-engineering?pivots=programming-language-chat-completions] Prompt engineering techniques
* [https://github.com/dair-ai/Prompt-Engineering-Guide] Prompt Engineering Guide