Brilliant! File this under “things definitely not written by ChatGPT.” Maybe Grok.
LLMS
-
Lessons from the TinyStories AI Research Paper
By
–
The world is still digesting the lessons of TinyStories https://
arxiv.org/abs/2305.07759 -
Data Scrutiny and Open Source AI Model Transparency Challenges
By
–
If we could train all our models from scratch on publicly scrutinized data that’d be great an I hope it happens! But that’s not the world right now. Even “open source” models don’t distribute their pre-train data — weights are closer to binaries than source code.
-
Adding Conversational Memory to RAG Applications
By
–
Adding conversational memory to your RAG app The main UX for LLM applications is chat. That makes it important to know how to add conversational memory to your apps – including you RAG apps! @curious_kaylynn walks through how to do exactly that!
-
Reflections on AI Task Performance and Ecosystem Integration
By
–
If AI’s power is insufficient, it would be failing to resolve a task in more cases than the one who does things well. Integration with the ecosystem is not the hardest problem to solve
-
GPT 4.5 Expected to Lead AI Models in 2024
By
–
GPT 4.5. By far. I assume LLama 3 will be on par with GPT 4 and Gemini Ultra will be a disappointment, a bit below GPT4.
-
Criticism of poor English quality in modern context with AI
By
–
I can't believe they used broken English to make it look immediately sketchy, in this age of ChatGPT.
-
Local LLM RAG Demo with Creative User Experience Design
By
–
The demo below is really interesting for a few reasons:
— LangChain (@LangChain) 14 janvier 2024
🦜Uses local LLMs (seems like @MistralAI via @ollama)
🌲RAG integration for PDFs and web pages
Even more exciting to us though… it changes up the UX! It's not just simply a chat text box
Super creative and practical https://t.co/PLGOO01NO8The demo below is really interesting for a few reasons: Uses local LLMs (seems like @MistralAI via @ollama
)
RAG integration for PDFs and web pages Even more exciting to us though… it changes up the UX! It's not just simply a chat text box Super creative and practical -
Patrick Lewis RAG Research Augments Language Models Retrieval
By
–
Research on RAG over corpora of documents by Patrick Lewis has profoundly impacted the NLP field. At Cohere, Patrick leads the modeling team effort to augment language models with access to retrieval systems and tools.
— Cohere (@cohere) 14 janvier 2024
Learn more on Chat with RAG: https://t.co/OR1VCAcnX8 pic.twitter.com/SCyxbccI9oResearch on RAG over corpora of documents by Patrick Lewis has profoundly impacted the NLP field. At Cohere, Patrick leads the modeling team effort to augment language models with access to retrieval systems and tools. Learn more on Chat with RAG: https://
txt.cohere.com/chat-with-rag/ -
Leveraging Conversational AI for Enhanced Critical Thinking
By
–
4. The Power of Conversation Interaction with language models like ChatGPT facilitates exploration. The back-and-forth dialogue enhances output by encouraging critical thinking. Ken views the "hallucinations" as beneficial since they force deeper questioning.