AI - AI Dynamics

Customizable AI Response Prefix in Conversational Memory

By

–

27 December 2022 20h00

More customizability for conversational memory A small change, but allows for specification of the prefix to use for for the AI response Was previously hardcoded to "AI", but can now be set to whatever Idea came from the discord! https://
langchain.readthedocs.io/en/latest/exam
ples/memory/conversational_customization.html
…

LangChain Improves Memory Documentation Organization

By

AI Dynamics

–

27 December 2022 20h00

Improved memory docs In order to keep up with all these changes to memory, we also revamped the memory docs slightly to be more organized https://
langchain.readthedocs.io/en/latest/exam
ples/memory.html
… As always, let us know if you have feedback!

New Memory Type Combining Summary and Context Window

By

–

27 December 2022 20h00

New memory type Previously, we had one memory type that created a summary, another that kept a window of recent lines of conversation. jaloo555 added a new type of memory which does both! It decides the window based on token length. https://langchain.readthedocs.io/en/latest/examples/memory/conversational_memory.html#ConversationSummaryBufferMemory

Weaviate Vectorstore: New add_texts Method Implementation

By

–

27 December 2022 20h00

add_texts for @weaviate_io The @weaviate_io vectorstore implementation was previously missing an `add_texts` method @CShorten30 added one! This allows you to easily insert embeddings (eg, of examples for the example selector)

Map-Reduce and Refine Chains Now Return Intermediate Steps

By

–

27 December 2022 20h00

Return intermediate steps for map-reduce & refine chains @johnjnay had the great idea to allow for returning of intermediate steps of these chains to the user This makes it easy to inspect things like Q&A over each document, before combining https://
langchain.readthedocs.io/en/latest/exam
ples/data_augmented_generation/question_answering.html#The-map_reduce-Chain
…

→ View original post on X — @datarobot

DataRobot AI Ensures Diversity in COVID-19 Vaccine Trials

By

@datarobot

–

27 December 2022 19h04

@TrialsArena recognized DataRobot for our work to help ensure diversity of participants in COVID-19 vaccine trials by leveraging #AI. We're honored to play a role in this critical work alongside our customers & partners. Learn more https://
bit.ly/3vmtuNQ

→ View original post on X — @karpathy

Mixed Precision Training: Complexity Beyond High Level Concepts

By

@karpathy

–

27 December 2022 19h03

the high level picture is easy enough but keeping track of the mixed precision around the whole network, the dynamical behavior of the values and ranges, the support for them and their conversions across all the various kernels and library versions everywhere, is the nightmare

→ View original post on X — @karpathy

FP16 Efficiency and Gradient Scaling Considerations

By

@karpathy

–

27 December 2022 18h57

yeah fp16 is a little more efficient atm for the code as I have it right now but then need gradient scaler ;s

→ View original post on X — @sama

Experience and credentials arguments lack critical substance

By

@sama

–

27 December 2022 18h53

also, people who try to win arguments with “i have xx years of experience” are second only to the “i have xyz credentials” crowd in terms of lack of likelihood of actually responding to the critical point.