PROMPT ENGINEERING - AI Dynamics

GPTwitter: Novel User-Level Personalization on LangChain

By

–

01 February 2023 18h24

Introducing the first of hopefully many guest posts highlighting novel applications building on top of LangChain GPTwitter: an application that we believe achieves user-level personalization in a novel, reproducible, and under-explored way

→ View original post on X — @langchain

1 February 2023

Bypassing AI Text Classifiers: From Detection to Human-Like Output

By

@saboo_shubham_

–

31 January 2023 19h43

Step-3: Check the newly generated text again by running it through OpenAI classifier. And Voila The text is now categorized as human-generated!

→ View original post on X — @saboo_shubham_

31 January 2023

Bypassing AI Classifiers with Synonym Replacement Techniques

By

@saboo_shubham_

–

31 January 2023 19h40

Step – 2: Copy the text and run it through GPT-Minus1 that will help you fool the classifier by randomly replacing words with synonyms in your text. Copied the previous text and got the newly generated text from GPT-Minus1 application.

→ View original post on X — @saboo_shubham_

31 January 2023

Magic Blog: Bypassing AI Classifiers as Competitive Advantage

By

@saboo_shubham_

–

31 January 2023 19h28

Try bypassing this classifier with Magic Blog. Seems like now it's going to become their biggest USP

→ View original post on X — @saboo_shubham_

31 January 2023

ChatGPT’s Wikipedia Article Generation: Capabilities and Detection Flaws

By

@dotcsv

–

31 January 2023 19h23

A la tercera bien. Le he pedido a ChatGPT que me escriba un artículo de Wikipedia sobre Súperlopez y lo ha pillado. Pero claro, podría ser un detecto defectuoso, o directamente uno que grita siempre "ES UNA IA"

→ View original post on X — @dotcsv

31 January 2023

AI Detection Challenge: Distinguishing Human from Machine-Generated Content

By

@dotcsv

–

31 January 2023 19h18

La primera en la frente: Pruebo a ponerle un trozo de un guion de Youtube, y me dice que lo ha generado una IA. Prometido que (aún) no

→ View original post on X — @dotcsv

31 January 2023

AI Detection Tools Arms Race Begins in Education

By

@dotcsv

–

31 January 2023 19h15

La herramienta está disponible, y con esto comienza una batalla de días (¿horas?) hasta que alguien desarrolle una herramienta a la contra para ofuscar los resultados. Una batalla super interesante que da solución en el corto plazo a muchos profes

→ View original post on X — @dotcsv

31 January 2023

Human-in-the-loop pause mechanism for AI automation systems

By

@langchain

–

31 January 2023 18h06

not currently, could be a future consideration! would desired ux be like "pause and wait for human to ok it"?

→ View original post on X — @langchain

31 January 2023

Curriculum Learning with Positive Examples: Don’t Shoot the Dog

By

@petitegeek

–

30 January 2023 4h24

Have you read Don't Shoot the Dog? I found it super interesting, there's the idea of curriculum learning with only positive examples first then negative examples for refinement https://
amazon.ca/Dont-Shoot-Dog
-Teaching-Training/dp/0553380397
…

→ View original post on X — @petitegeek

30 January 2023