Few-Shot Domain Adaptation with Polymorphic Transformers Li et al.: https://
arxiv.org/abs/2107.04805 #Transformers #GPT #ChatGPT
LLMS
-
Few-Shot Domain Adaptation with Polymorphic Transformers
By
–
-
Anthropic Claude 2.1 API pricing cut below GPT-4 Turbo
By
–
Claude 2.1 API pricing from @AnthropicAI has been reduced to make it cheaper per-token than #GPT4 Turbo! (spotted by @jeremyphoward
) -
GPT as Turing Machine: Programming Capabilities Explained
By
–
GPT is becoming a Turing machine: Here are some ways to program it Ana Jojic, Zhen Wang, Nebojsa Jojic: https://
arxiv.org/abs/2303.14310 #GPT #ChatGPT #TuringMachine -
LLMs Will Significantly Replace Lawyers in Legal Profession
By
–
I honestly believe that while lawyers will not cease to exist as a profession altogether, they will be significantly replaced by LLMs. LLMs have access to all legal cases, can abstract and individually apply each case to the current legislation.
-
Build and Scale LLM Applications 20x Cheaper Than GPT-4
By
–
You can build and scale LLM applications within minutes using our platform. It's 20x cheaper than GPT-4! • Set up and scale RAG applications
• Pick any open-source LLM to power your RAG apps
• Customize chunking, embedding, and retrieval strategies https://
abacus.ai/ragapi -
Math Updates Required for Next Generation AI
By
–
Seems the math needs to be updated for nextgen https://
x.com/choldgraf/stat
us/1727819994640289935
… -
Self-Attention Mechanism in Large Language Models Explained
By
–
Understanding and Coding the Self-Attention Mechanism of Large Language Models From Scratch https://
bit.ly/3YL821l #AI #DeepLearning #MachineLearning #DataScience -
Proposal for Language Modeling Competition Between Humans and AI
By
–
Like the International Math Olympiad or Spelling Bee, there should be a “language modeling competition” where humans compete to predict the next word in a sequence. The best humans would probably still lose to GPT-2, and we’d have more empathy for how hard it is to be an LLM 🙂
-
Vectara QA Chain avec résumé et citations multilingues
By
–
📄 Vectara QA Chain
— FlowiseAI (@FlowiseAI) 24 novembre 2023
Inspired by Vectara-Answer github repo, we worked with @ofermend to create a custom Vectara QA Chain with
✅Built-in summarization
✅Citations
✅Ability to switch between languages pic.twitter.com/nc48flblUNVectara QA Chain Inspired by Vectara-Answer github repo, we worked with @ofermend to create a custom Vectara QA Chain with Built-in summarization
Citations
Ability to switch between languages -
Moderation Nodes Prevent Harmful Content in LLM Systems
By
–
Moderation To prevent harmful content being passed to LLM, we have added Moderation nodes. Input will be checked against violation rules, and an error message will be shown accordingly.