anyway its gonna be awhile, seems broken, just says "42" to every prompt?!
LLMS
-
LangChain 0.0.19: Sequential Chains and Vector DB Updates
By
–
LangChain version 0.0.19 Sequential chains: define a list of sub-chains and run them in order
Expose prompt for changing in vector db/qa
Clean up some documentation -
LangChain 0.0.18 Release with Documentation and Interface Updates
By
–
LangChain version 0.0.18 Docstring cleanup from @Jim_Salmons (first time contributor!)
Insert ability to the docstore/vectorstore interfaces from @sjwhitmore -
LangChain 0.0.17: Improved Prompt Documentation
By
–
ICYMI: LangChain version 0.0.17 Refactored and improved documentation around prompts
-
Large Language Models Should Master Multi-Digit Addition
By
–
Multi-digit addition should definitely be within reach for large language models at this point! https://t.co/snqwqxnVQ7
— Jason Wei (@_jasonwei) 18 novembre 2022Multi-digit addition should definitely be within reach for large language models at this point!
-
LangChain 0.0.16: Chain Input/Output Comparison and Model Evaluation
By
–
version 0.0.16: compare inputs/outputs on a whole chain Useful for evaluation when you're doing more than just a simple call to an LLM Github: https://
github.com/hwchase17/lang
chain
… How do different models do in @OfirPress
's self-ask w/ search example? https://
colab.research.google.com/drive/1atz4xfZ
LpIHJKD2kf38WnxHv61XU-dwb
… -
Unlocking Reasoning Capabilities in Smaller Language Models
By
–
Unlocking reasoning in smaller language models is a great direction
-
General-Purpose Neural Networks Through Simple Scalable Objectives
By
–
when the core unlock was achieving a kind of general-purpose computer neural net via simple scalable objectives that have strong training signal (many bits of contraints per training example). Like language modeling, and not like reinforcement learning.
So that was interesting 😀 -
Scaling Language Models: Neural Networks as General-Purpose Text Computers
By
–
TLDR: LMs have been around forever. Not obvious finding: turns out that if you scale up the training set and use a powerful enough neural net (Transformer), the network becomes a kind of general-purpose computer over text.
-
A Decade of AI Progress: Language Models and Neural Networks
By
–
I wrote this thread because I spent the last ~decade, obsessing over directions that would make fastest progress in AI, and was very interested in language models (e.g. my semi-famous 2015 post "The Unreasonable Effectiveness of Recurrent Neural Networks" https://
karpathy.github.io/2015/05/21/rnn
-effectiveness/
…)