Code Interpreter by OpenAI is truly a game changer. It's an analyst/assistant on your fingertip, who have general knowledge about the world(such as mathematics, stats, economics, etc…), who can answer your questions with beautiful visualizations, who can code, etc… Like many
PROMPT ENGINEERING
-
Transformer Architecture and Middle Document Retrieval Performance Bias
By
–
2) To my knowledge, there is no specific inductive bias in transformer-based LLM architectures that explains why the retrieval performance should be worse for text in the middle of the document. 4/5
-
LLMs Struggle Retrieving Information from Document Middle
By
–
According to "Lost in the Middle: How Language Models Use Long Contexts" (
https://
arxiv.org/abs/2307.03172) LLMs are good at retrieving information at the beginning of documents. They do less well in terms of retrieving information if its contained in the middle of a document. 2/5 -
ChatGPT Code Interpreter Now Available to All Plus Users
By
–
This week, the company said that it is taking one of its own in-house plug-ins, Code Interpreter, and making it available to all of its ChatGPT Plus subscribers. Code Interpreter comes to all ChatGPT Plus users — ‘anyone can be a data analyst now’ https://
bit.ly/43vPh4l -
New Stable Diffusion Course Development with Interesting Prompt Results
By
–
Working on our new course Stable Diffusion course is fun! The prompt I used here had the word “fit” in it. Ahem!
-
ChatGPT Limitations in Research Summary Writing
By
–
I must say I would use ChatGPT with a grain of salt. I tried that for doing the research highlights in my newsletter (like https://
magazine.sebastianraschka.com/p/ai-research-
highlights-in-3-sentences-2a1
…) but yeah, next to the occasional mistake it didn't always pick the most relevant parts so I am sticking to manual summaries. -
Can You Trust ChatGPT’s Package Recommendations?
By
–
Can you trust ChatGPT’s package recommendations? https://
bit.ly/3CAELxE #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Training AI: Tell Your Model What You Dislike
By
–
Mine is amazing but you gotta tell the AI what tweets you don’t like.
-
Text to Video AI with Pika Labs: Three Creative Prompts
By
–
Text to video AI using @pika_labs
— AK (@_akhaliq) 6 juillet 2023
prompts in order
1. A marathon runner is running in a marathon competition
2. A Wasteland Punk style digital computer game character is fully armed and walking in a ruined city
3. Ice-skating in Bryant Park at 9 pm, warm ambient light in… pic.twitter.com/8oibe4hfxrText to video AI using @pika_labs prompts in order 1. A marathon runner is running in a marathon competition 2. A Wasteland Punk style digital computer game character is fully armed and walking in a ruined city 3. Ice-skating in Bryant Park at 9 pm, warm ambient light in
-
OpenAI Function Calling Tutorial Guide
By
–
OpenAI's function calling is really powerful…
— Dave Ebbelaar (@daveebbelaar) 6 juillet 2023
But how do you actually use it?
Check out my full tutorial here: https://t.co/tDkJzK5qqh pic.twitter.com/GssoOoP0GPOpenAI's function calling is really powerful… But how do you actually use it? Check out my full tutorial here: https://
youtu.be/aqdWSYWC_LI