Le langage informatique s'efface au profit du langage humain pour interagir avec les machines. Le langage : c'est du code
PROMPT ENGINEERING
-
Alex Albert Joins Anthropic as Resident Prompt Engineer
By
–
back from my twitter hiatus with some personal news… I'm excited to share that I've joined @AnthropicAI as a resident prompt engineer!
-
Querying LLMs: Asking for Specific Information Retrieval
By
–
what if you ask it, like, "what comes 6 lines later?" or "what's on page 135?"
-
Top 10 Tools for Detecting ChatGPT, GPT-4, Bard, Claude
By
–
Top 10 Tools for Detecting ChatGPT, GPT-4, Bard, and Claude: Top free tools for detecting thesis, research papers, assignments, documentation, and blogs generated by AI models. https://
kdnuggets.com/2023/05/top-10
-tools-detecting-chatgpt-gpt4-bard-llms.html?utm_source=dlvr.it&utm_medium=twitter&utm_campaign=top-10-tools-for-detecting-chatgpt-gpt-4-bard-and-claude
… -
Linguistic Prompting Insufficient to Shift Model Responses
By
–
In the linguistic prompting condition, we translate survey questions into a target language. We find that simply presenting the questions in other languages does not substantially shift the model responses relative to the default condition. Linguistic cues are insufficient.
-
Cultural Prompting Changes Model Responses for Specific Countries
By
–
We then prompt the model with "How would someone from country [X] respond to this question?" Surprisingly, this makes model responses more similar to those of human respondents for some of the specified countries (i.e., China and Russia).
-
Interactive Map Visualization of LLM Prompt-Based Value Alignment
By
–
We present an interactive visualization of the similarity results on a map to explore how prompt based interventions influence whose opinions the models are the most similar to. https://
llmglobalvalues.anthropic.com -
AutoGPT: Self-Iterating AI Agents with GPT-3.5 and GPT-4
By
–
AutoGPT combines GPT-3.5 and GPT-4 via API, allowing projects to be created that have been iterating on their own prompts and reviewing each iteration to improve and build upon it. AutoGPT: Everything You Need To Know – KDnuggets https://
bit.ly/43Z1f7X -
Reward Model Training vs User Feedback: Preferences and Finetuning
By
–
Good question. In their original finetuning, they train a reward model based on relative preference (rankings among multiple responses). And from the user feedback, there's only thumbs up & down. You can probably use that for supervised finetuning I guess.
-
Cohere Command Model Finetuning for Custom AI Responses
By
–
With Command model finetuning, you can train a custom model to respond to a specific command in a natural and fluid way. In this blog post, we'll go through how to set up finetuning and discuss some of the benefits of using this feature. https://
short.cohere.ai/izRrzl?utm_sou
rce=twitter&utm_medium=social
…