Depends on the prompt! More examples is especially helpful when the examples relate to one another and contain explicit information to inform future generations. But too many examples can lead to decreased performance and variation in responses.
LLMS
-
Writing Effective AI Prompts: Language Skills and Formatting
By
–
For example, my go-to is to provide instructions in plain English, then examples in JSON for easy parsing. I’ve seen others use English for everything. Or markdown. One thing is clear though — great language + reasoning skills are necessary to write good prompts.
-
Emergent Capabilities in Large-Scale Language Models Explained
By
–
As language models increase in scale they sometimes exhibit various useful emergent capabilities. In today’s post, we explore this phenomenon to better understand its dependence on model properties and its potential impact in applications. Read more at https://
goo.gle/3hvJMAb -
Larger AI Models Show Increased Bias Demonstration
By
–
It looks like the bigger the model, the harder it gets for it not to demonstrate biases. Very cool stuff from @mathemakitten
! https://
huggingface.co/blog/zero-shot
-eval-on-the-hub
… -
LangChain 0.0.11 Release: New Embeddings and Text Splitting Features
By
–
LangChain version 0.0.11: – @CohereAI embedding support from @abdrahman_issam – @NLTK_org and @spacy_io support for text splitting from @deliprao "Optimized Prompts" from @sjwhitmore misc cleanup from @deliprao and @nlarusstone https://
github.com/hwchase17/lang
chain
… -
Cohere’s LLM Applications Talk at PyData NYC
By
–
Attending @PyData NYC? Join @CohereAI's @hemanham on Nov 10th, 11:45am EDT, where he'll give a "gentle intro" to real-world applications of large language models. No prior knowledge needed! Read more about the talk: https://
nyc2022.pydata.org/cfp/talk/AEFDA
8/
… -
Making Large Language Models Accessible for Developers
By
–
Learn how Cohere is making large language models accessible and easy to use for all kinds of developers in this talk with @scale_AI
's Head of Engineering, @vjkaruna
, and Cohere's VP of Engineering, @BillMacCartney ↓ -
Dataset Curation Strategy for AI Use Cases
By
–
My rule of thumb: If the use-case doesn’t have a ‘right answer’, or is creative, curate small datasets. If the use-case has a ‘right answer’, lots of data is helpful and a moat will persist for a couple of years until models are ridiculously smart. Applies often but not always
-
LangChain 0.0.10: Cloud NLP, Elastic, and Model Laboratory Features
By
–
LangChain version 0.0.10: @cloud_nlp support (
@sjwhitmore
) @elastic support (
@sjwhitmore
) support for text2text generation models on @huggingface (h/t @deliprao 4 idea) model laboratory: easily compare the same input to different models https://
github.com/hwchase17/lang
chain/
… -
Using LLMs to Generate Product Descriptions at Scale
By
–
Learn how to use large language models (LLMs) to generate product descriptions for ads quickly and at scale. Get started ↓ https://
hubs.li/Q01rSBpt0 PS: This social post was generated using text summarization by Cohere.