Nice, send like the knowledge files potentially make a big difference by better grounding the model / introducing more recent data.
GENERATIVE AI
-
GPT Customization: Prompts or Actions?
By
–
Are the GPTs primarily customized by prompts, or do they include actions too?
-
Subscription pricing comparison: $20 monthly for Claude-2 and GPT-4
By
–
Yeah it’s $20/month just like Claude-2 and GPT-4
-
Claude Ultra vs 3.5: Performance Differences on Complex Prompts
By
–
Similar to ChatGPT 3.5 vs 4. Ultra can handle my mega prompts and tends to have more nuance. Both do well with prompts that are only a few sentences though. It’s naturally got some chain-of-thought reasoning built in.
-
Gemini Ultra Superiority Over GPT-4 Despite API Limitations
By
–
Gemini Ultra > GPT-4 (Except that it doesn’t have an API.)
-
Crypto AI Art NFT Collection Montreal AI Floor Price Analysis
By
–
[ C R Y P T O A I A R T ] The "Crypto AI Art" Collection could be the "CryptoPunks" of the #AIArt era "Only 14 pieces listed (3%) !" Verified Collection : https://
opensea.io/collection/mon
trealai
… MINTED in 2021 Floor : 0,42 ETH #MontrealAI #NFT #NFTs #NFTCommunity #QuebecAI -
RAG Systems Evolution with LangChain and Redis Webinar
By
–
Join us this Thursday 2/29 at 9 AM PT for a webinar we're hosting with @Redisinc to learn more about the future of RAG! We'll talk about the evolution of RAG systems and go over practical examples illustrating the power of LangChain and Redis in RAG architectures. Sign up
-
HONOR Magic 6Pro launches with Magic OS 8.0 and Llama integration
By
–
#HONORMWC2024 #DiscoverTheMagic #HONORMagic6 #Ad #Sponsored Check out the brilliant news released by @HonorGlobal at #MWC2024… Creating new collaborations among industry partners, such as HONOR x Llama Honor Magic 6Pro features the Magic OS 8.0, enabling the "Magic
-
Generative AI Needs Personalization Through User Embeddings
By
–
Generative AI Products need to go through their "personalization" revolution.
A single "prompt" for the entire world is a single human preference for the entire world. That obviously doesn't work.
You'd want to adjust the prompt embeddings with user embeddings, to give