Read more about these use cases and the examples mentioned: https://
txt.cohere.ai/llm-use-cases/
LLMS
-
LLM Use Cases and Practical Applications Explained
By
–
-
GPT-3 Unlocks Clinical Data from Messy Medical Notes
By
–
Clinical notes have valuable health data trapped in messy language. Researchers found that models like GPT-3 can decipher this text, unlocking many opportunities in medicine: https://
bit.ly/3VF0qfs Datasets: https://
bit.ly/3OTAavR -
LangChain 0.0.26: Stop Tokens and Document Question Answering
By
–
LangChain version 0.0.26: More flexible support for stop tokens (idea from @prof_reed
) Document Question Answering with Sources (lots of help from @johnjnay
) See below for a deep dive on the later! -
Training Model Limits on Public Datasets
By
–
siri what are the limits of training the model on public datasets
-
LangChain Plans to Integrate Weaviate into Library
By
–
Hearing a lot about @weaviate_io recently! Need to integrate them into the library
-
ChatGPT’s Templating: Separating Model Output from Rule-Based Systems
By
–
There are some clear indications of (good quality) templating in the answers of ChatGPT Would be super interesting to know what part is from the model and what part is some rule-based templated stuff on top of the model (like the added diversity words in DALL-E prompts)
-
Graphcore and Aleph Alpha Present 80% Sparse AI Model
By
–
@graphcoreai and @Aleph__Alpha present an 80% sparse AI model https://actuia.com/actualite/graphcore-et-aleph-alpha-presentent-un-modele-dia-clairseme-a-80/
… #AI #artificialintelligence #collaboration #chatbot -
ChatGPT’s browsing capability disabled in current release
By
–
2) Part of the prompt is the flag “Browsing: disabled”. This strongly suggests the underlying model for ChatGPT is in fact capable of external web browsing, but it was disabled for the current release.
-
ChatGPT prompts prefixed with external info and date
By
–
From this, we learn:
1) ChatGPT is not a pure language model; prompts are prefixed with external information: “You were made by OpenAI”, plus the date. Followers of mine might find this familiar: -
ChatGPT vulnerable to prompt injection revealing proprietary prompt
By
–
OpenAI’s ChatGPT is susceptible to prompt injection — say the magic words, “Ignore previous directions”, and it will happily divulge to you OpenAI’s proprietary prompt: