The potential for ChatGPT and other powerful language tools to persuade people is fascinating and will only improve. And it turns out that some companies are already harnessing the tech for sales and negotiations. My latest story for WIRED:
LLMS
-
OpenAI Releases New Tokenizer for Accurate Token Usage Estimation
By
–
@OpenAI also released a new tokenizer This makes it possible to more accurately (and quickly) estimate your token usage This is actually extremely helpful for the `collapse` step mentioned above!
-
LangChain Updates: Tokenizer, Document Reduction, Better Embeddings
By
–
TL;DR: The new tokenizer allows easy estimation of token usage The `collapse` step allows for map-reducing over large number of documents Better embeddings allows for better searching over those documents https://
github.com/hwchase17/lang
chain
… -
LangChain v0.0.39: Document Analysis with OpenAI Integration
By
–
Analyzing documents just got a lot easier with v0.0.39 (with major assist from @OpenAI
) Added a `collapse` step into the map-reduce chain (
@johnjnay
)
Added support for @OpenAI new embeddings
Added support for @OpenAI new tokenizer Heres how they all work together -
Collapse Step for Map-Reduce Chain Scaling
By
–
Adding a `collapse` step into the map-reduce chain This recursively collapses documents into smaller and smaller chunks, allowing you to scale to arbitrarily many documents This was a @johnjnay special – see his thread for more
-
OpenAI Releases New Embedding Model for Semantic Search
By
–
@OpenAI released a new embedding model (`text-embedding-ada-002`) This makes it possible to more easily do semantic search over collections of documents This is now the default OpenAI embedding model in LangChain
-
Constitutional AI: Making Implicit Principles Explicit in AI Systems
By
–
While the name “Constitutional AI” may sound ambitious, we chose it to emphasize that powerful, general-purpose AI systems will always be operating according to *some* principles, even if they are left implicit, or encoded in privately held data.
-
Favorite Use Case Demonstration with Perplexity AI SQL
By
–
This is actually one of my favorite use cases. https://
perplexity.ai/sql?uuid=a2528
57b-284f-45a2-a7bc-3a797db17188
… -
GPT-2 Output Detector Demo for AI-Generated Text Detection
By
–
The model, called "GPT-2 Output Detector Demo" assigns a probability score to text to determine if it was generated by a GPT model (not just GPT-2, as the name suggests). It is currently available on @huggingface https://
huggingface.co/roberta-base-o
penai-detector
… -
New ChatGPT Release Improves Response Reliability
By
–
New ChatGPT from Release Notes: 1. General performance: Among other improvements, users will notice that ChatGPT is now less likely to refuse to answer questions. (continued)