5 Bad ChatGPT Mistakes You Must Avoid
#AI #AIio #BigData #ML #NLU #Futureofwork @Kevin_Jackson @sallyeaves @schmarzo @kdnuggets @akwyz @BrettKing @TechNative @MiaD http://
ow.ly/mnol30svSuc
PROMPT ENGINEERING
-
5 Bad ChatGPT Mistakes You Must Avoid
By
–
-
Start Your Own Software Project with AI Tools Today
By
–
You can start your own personal software project today. In many cases, hiring a developer isn’t necessary. Even if you’re non-technical. AI like GPT and Ghostwriter can get you most of the way there.
-
Command LLM Applications: Recognizing Patterns for Practical Use
By
–
Large language models (LLMs) like the Command model can be applied in infinite ways, but if one can’t recognize the patterns where they can be useful, it can feel overwhelming. In this blog post, we’ll go through the different ways how you can use the Command model.
-
AI Transcription Accuracy and Generation Strategy Optimization
By
–
Yess! Quite possible – although the accuracy of the transcriptions still needs to be checked. I’ve found it to loose context if not used with the right generation strategy!
-
The Art of Prompt Engineering for Generative AI
By
–
The art of the prompt: How to get the best out of generative AI – Source https://
bit.ly/46bZl54 #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Contrastive Search vs Greedy Search for LLM Generation
By
–
Yeh! Would deffo recommend contrastive search. It works quite well (however, over generates sometime ) Greedy search simply results in lost context.
-
Fine-tuned Models Performance on Multilingual Translation Tasks
By
–
Agreed! From my experience, it works well on languages that were abundant in the train set and also had lang -> en translate pairs. I’ll run some experiments to see how well do fine-tuned models perform. Quite lovely to see ya already using this
-
Guide pratique sur l’utilisation des LLMs : modèles, données et applications
By
–
Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond This survey paper provides a comprehensive and practical guide on working with LLMs for various settings(in-context learning & fine-tuning). I like how it approach LLMs usage in lens of models, data, and
-
Few-Shot Prompting Improves Model Performance on MMLU
By
–
15/ To make sure that the model does as few as possible of these sort of errors, we can use “few shots”: we provide the model with a few examples in the prompt with the expected answers. Since this improves performance, MMLU is evaluated in 5 shots in all our experiments
-
Model Evaluation: Uncounted Prediction Errors in Multiple Choice
By
–
14/ As you can see, we compare the probabilities predicted by the model, on the four answers *only*. But sometimes that model would have made a mistake (generating "Zygote" here) which is not counted as a mistake…