i think even <base models have in-context learning ability if instruction tuned.
LLMS
-
Microsoft executive confirms development of GPT-5 and GPT-6
By
–
Executive Director of Microsoft Korea mentions GPT-5 and GPT-6 in comments: "Issues related to AI and copyright are important, but I think we are already in an environment that has surpassed this… We are preparing GPT-5, and GPT-6 will also come out."
-
GPT-4 Theory of Mind Investigation Through Empirical Testing
By
–
3/ @labenz had a hypothesis that a paper on GPT-4 lacking “theory of mind” was incorrect and wanted to investigate further. He posted a Bounty for a script that used GPT-4 to run on 400 random sample problems and document the results to prove or disprove the paper findings
-
Conversational Interfaces for Model Understanding and Explainability
By
–
Check out this video with Prof. Hima Lakkaraju on the role of conversational interfaces in model understanding. With this tool, users can understand model predictions & explanations. An essential viewing for those interested in NLP.
-
Cohere Releases Comprehensive LLM University Curriculum
By
–
LLM University – Cohere Cohere just released a comprehensive LLM curriculum. The curriculum covers basic NLP foundations and advanced topics like large language models(LLMs). Coming from a company building NLP & LLMs tools for developers and users, this LLM curriculum is as
-
Create Custom ChatGPT with Abacus AI Data Integration
By
–
Create your own Custom ChatGPT Use @abacusai to: – Ingest data from different sources
– create embeddings using open AI or BERT
– use our vector-matching engine
– feed results to GPT-4 to create a custom chat experience -
ODSC Europe 2023 Schedule Live with Speaker Topics
By
–
#ODSCEurope’s schedule is now live! See the speakers who will be attending and the topics they’ll be presenting: https://
bit.ly/3MxGk54 by @_odsc ————
#BigData #DataScience #AI #ML #MachineLearning #DeepLearning #Python #NeuralNetworks #LLMs #NLProc #ComputerVision #GenerativeAI -
Testing ChatGPT’s Voice Recognition Accuracy with Simple Prompts
By
–
I’m most curious about the voice recognition accuracy (we already know many of chatgpt’s strengths and weaknesses), so I gave it simple prompt tests (it helps that my voice is a mess as I recover from a cold). It did a good job transcribing, and produced relevant answers.
-
Eleven Multilingual v1: New Speech Synthesis Model Introduced
By
–
Introducing Eleven Multilingual v1: Our New Speech Synthesis Model https://
bit.ly/3Nou3Rr #AI #MachineLearning #LLMs #deeplearning -
Compressed NLP Models: Cost-Effective LLM Deployment Alternative
By
–
"Why smaller specialized NLP models might be the secret to easier LLM deployment" proposes the use of compressed NLP models as a cost-effective & efficient alternative to #LLMs, with similar performance but significantly reduced deployment challenges. By: Meryem Arik @titanML