"Technology like what Groq has built is the key to building natural human-to-AI interactions." — @BrownridgeJB
LLMS
-
Rating LLM outputs: hand-labeling versus prompt-based evaluation
By
–
Determine what you care about (ex: conciseness, factuality, style, etc.). The either:
– hand rate a bunch of examples on each dimension, train a model to understand what to look for
– build a LLM prompt with Mistral or similar to do this without fine-tuning Run over all the -
Manual Model Evaluation Through Held-Out Test Sets
By
–
I have a held-out test set that I manually prompt the model with and evaluate myself, and then beyond that, I just keep asking the model questions till I feel the vibes
-
Digital CXM: AI and LLMs Transform Customer Experience
By
–
Digital CXM combines AI, LLMs, and diverse technologies within a layered ecosystem, improving customer experience by unlocking new applications, optimizing operations, and identifying business investment opportunities. #infographic by @EverestGroup via @antgrasso #AI
-
Looping LLMs in Self-Conversation to Emerge Artificial Consciousness
By
–
Faire boucler des IA en conversations avec elles-mêmes pour faire émerger la conscience artificielle. Westworld avec des LLM.
-
How LLMs Correct Training Data Bias Detection Methods
By
–
If you want to know how your LLM corrects for biases in its training data, you can ask it whether Covid had a zoonotic origin
-
Model Unification and A/B Testing Platform Improvements
By
–
Interesting. Definitely try using the platform with this (provide examples). If you’re on a good model a/b test, it should work near-perfectly. Sorry for the a/b test confusion — we’re hopefully going to unify on one model in the coming weeks so there’s no guessing.
-
Prompt Optimization: Context Size Impact on Model Performance
By
–
Depends how many examples you have. If say, 500 or less, include the task description in the prompt so the model picks it up quicker. If you’re in the thousands, no context often leads to similar or better performance and slightly lower inference costs.