Yeah it’s really not limited to prompts talking to eachother, but rather any interactions between an LLM and other things (whether that be another prompt, or a python REPL, or anything)
LLMS
-
Latest LLM Reads Text on Wall Warning of Impact
By
–
The latest LLM can read writing on a wall. It says "You're about to hit me."
-
LangChain 0.0.21: Memory, Conversational Chain, and Improvements
By
–
LangChain version 0.0.21 Added in Memory abstraction (
@sjwhitmore
) Conversational chain (
@sjwhitmore
) Method for adding examples to ExampleSelector class (
@sjwhitmore
) Bug fix for search class Support for all params in the OpenAI wrapper -
Generative AI framing undersells actual capabilities
By
–
Similar issue with "Generative AI" – so hot right now, but this framing is, believe it or not, *underselling* capabilities we are already seeing, and perhaps causing people to work on the wrong things.
-
LangChain Overview by Shubham Saboo Appreciated
By
–
A good overview of LangChain by @Saboo_Shubham_ ! Thanks for the write up 🙂
-
InstructGPT/RLHF tuning makes model assume all questions answerable
By
–
My guess is this is InstructGPT/RLHF rather than anything in the pre-training corpus. Tuning implicitly makes it assume all questions are answerable — it sees all text as “ ” and Q/A is a subset of that.
-
Running Out of Data to Train AI Language Models
By
–
We could run out of data to train #AI language programs https://
technologyreview.com/2022/11/24/106
3684/we-could-run-out-of-data-to-train-ai-language-programs/
… @techreview #MachineLearning #DataScience #IoT #serverless #womenwhocode #Robots #100DaysofCode @JAdP @CatherineAdenle @FmFrancoise @Shi4Tech #BigData #Analytics #DigitalTransformation #DeepLearning -
Dialect-robust Evaluation of Generated Text
By
–
Dialect-robust Evaluation of Generated Text Sun et al.: https://
arxiv.org/abs/2211.00922 #ArtificialIntelligence #DeepLearning #MachineLearning -
Capabilities and use cases for GPT-3
By
–
So what can you use it for? GPT-3 will attempt to answer virtually any text prompt you give it. It can answer questions, write stories, poems, create lists, write research papers, and it can write code. A lot of code. The best way to describe what it can do is to just try it.
-
How AI Models Transform Input into Predictions
By
–
This means that it can take user's input text and transform it into what it predicts the most useful result will be based on the patterns recognized from the parameter library.