Generative AI for News Media.ipynb

100%

Generative AI for News Media.ipynb

✓ Published0🌍 Public

Last edited Feb 26, 2023

Created on Feb 26, 2023

This notebook demonstrates how GPT-3 can be prompted for journalistic tasks like brainstorming article ideas and summarizing abstracts, while also outlining model limitations such as hallucination and bias. It uses the OpenAI API through Python code with predefined prompts, and includes a Colab badge link for interactive access. The content focuses on text generation examples rather than data visualization, relying on markdown explanations and code cells to illustrate prompting techniques.

AI-generated description

Similar vizzes

Loading thumbnail…

Gist e71cb443307994e24e63465bac636d3e

This example demonstrates how to extract and summarize the content of a New York Times opinion article about regulating artificial intelligence. The notebook uses the `newspaper` library to download and parse the article, returning its title, publication date, and initial text. It then calls the `nlp()` method to generate a list of keywords and a multi-sentence summary, showing a straightforward pipeline from a URL to condensed article insights. The code relies on `Article` from `newspaper` and standard pandas imports.

GGeorgeMcIntire

65% match

Loading thumbnail…

Gist 01500f8ab6e9b7d98dd0aeea50347b9f

This example shows how a classroom activity integrates generative AI tools to design community micro-campaigns. It demonstrates a structured session where learners use ChatGPT, Adobe Firefly, and Adobe Express for ideation, visual production, and operational strategy. The visualization relies on text-based prompts and workflow steps rather than code libraries. It displays the pedagogical flow, including phases for guided activity, critical reflection, and optional mini-challenges, without using data-driven rendering or computational graphics.

IIoTeacher

61% match

Loading thumbnail…

synthetic-data-generation-of-wikipedia-infoboxes.ipynb

This example demonstrates how to generate synthetic Wikipedia infoboxes from stub articles and fine-tune a T5 model to reproduce that transformation. It shows a complete pipeline that starts with a Hugging Face dataset of women-in-religion stubs, uses GPT-4o-mini via the OpenAI API to produce infoboxes, and then trains a T5 model using the DataDreamer framework. The notebook also publishes the resulting dataset and model to the Hugging Face Hub, with experiment tracking through Weights & Biases. The visible code focuses on data loading, API key configuration, and session initialization rather than interactive chart rendering.

CCliffordAnderson

61% match

Loading thumbnail…

GPT3 prompt

This example demonstrates how a generative prompt can transform raw running statistics into personalized, motivational narratives. It shows a template where runner data—name, distance, total runs, hours, streak, climb, and classification—are inserted into a structured story, with comparisons like "run around the world in 14 years" making the numbers relatable. The code relies on string templating (likely via a language like JavaScript or Python) to populate the narrative field, while the data source is a simple text file with key-value pairs. The rendering is plain text output, with no visual charts or libraries involved.

CColinEberhardt

61% match

Loading thumbnail…

Gist 18319c4f30bf20182aad

This example uses an iPython Notebook to teach basic Python and Markdown skills. It shows a sequence of tasks for editing text cells, writing code, and manipulating strings, using the NLTK library to process a sentence. The notebook’s cells contain instructional headings, markdown explanations, and Python code inputs with output. The visualization is the notebook itself, rendered as a static document with WebGL, demonstrating its interactive, code-driven structure.

MMartiHearst

59% match

Loading thumbnail…

running report GPT3 prompt

This example visualizes the running habits of several athletes, generating a playful, personalized narrative for each based on their weekly patterns. It shows when each runner tends to go out, the typical time of day, and their preferred days for long runs and workouts. The code uses a simple data structure and template-based text generation, likely via a GPT-3 prompt, to produce the fun, inspiring summaries displayed alongside each runner’s profile.

CColinEberhardt

58% match

Loading thumbnail…

Gist fdb22d9ec25b96538814323e0609c895

The example is a curated markdown document that catalogs online resources for synthetic media, organized by categories such as synthetic text, voice, music, art, and gaming. It lists specific websites and tools, including thispersondoesnotexist.com, Hugging Face’s BERT, OpenAI’s GPT-3 and Jukebox, Descript, and AI Dungeon, with hyperlinks for each entry. The page is a static text file, not an interactive visualization, using no JavaScript libraries or rendering APIs. It functions as a reference list, showing the breadth of generative media platforms rather than demonstrating any particular code or chart.

CCliffordAnderson

58% match

Loading thumbnail…

using-pretrained-abstract-to-tweet-model.ipynb

This example shows how a pre-trained transformer model converts academic abstracts into concise, tweet-sized summaries, demonstrating a text-to-text generation workflow. It loads a Hugging Face `AutoModelForSeq2SeqLM` and `AutoTokenizer` from the `andersoncliffb/abstracts_to_tweet_model` repository, then creates a `text2text-generation` pipeline to produce the output. The notebook’s code uses the Transformers library’s pipeline API, with the model and tokenizer specified directly. It does not include a data visualization, instead focusing on the model’s generative output from input text.

CCliffordAnderson

58% match