Voyager: An Open-Ended Embodied Agent with Large Language Models Wang et al.: https://
arxiv.org/abs/2305.16291 ##ArtificialIntelligence #ChatGPT #LargeLanguageModels
LLMS
-
Voyager: Open-Ended Embodied Agent with Large Language Models
By
–
-
Visual Guide to Neural Network Basics for Data Scientists
By
–
A Visual Guide to the Basics of Neural Networks. #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #Python #RStats #TensorFlow #JavaScript #ReactJS #CloudComputing #Serverless #DataScientist #Linux #Programming #Coding #100DaysofCode https://
geni.us/Visual-Neural-
Nets
… -
CS224N NLP Deep Learning Course Updated 2023 Free
By
–
The CS224N Natural Language Processing with Deep Learning YouTube playlist has been updated for 2023, with new lectures on topics such as pretrained models, prompting, RLHF, natural language and code generation, linguistics, interpretability and more. Free Course v/
-
MLflow 2.7 Introduces New Prompt Engineering UI
By
–
Introducing new prompt engineering UI with MLflow 2.7 Users can now experiment with various base models, parameters, and prompts to see if outputs are promising enough. Give #MLflow a try for your #LLM development initiatives
-
What’s Your Favorite LLM Development Tool Stack?
By
–
What is your favorite LLM Dev Tool / what does your stack look like? Langchain? LlamaIndex? Haystack? Helicone?
-
Synthetic Text Generation: LLMs versus Traditional NLG
By
–
Czarniawska’s work looks interesting. But I think you and I aren't using "synthetic text" in the same way. I use it to refer to the kind of untethered generation that comes out of LLMs used as synthetic text extruding machines. Pre-"gen AI" hype, there was sensible work on NLG
-
Chess Widget in GPT Models: OpenAI Architecture Questions
By
–
Where
a) it doesn’t work with other notations (!)
b) it’s new, maybe after I started pointing to chess
c) doesn’t apparently work w ostensibly more powerful GPT4 d) OpenAI doesn’t disclose what it’s inside
I wonder whether they added a narrow chess specific widget? Or TONS of -
Templatic Generation vs LLM Untethered Synthetic Text
By
–
There's an enormous difference between templatic generation & other ways of going from structured data to natural language strings that reflect it to the kind of untethered synthetic text that comes out of LLMs.
-
LLMs gain senses and dexterity, heralding a new era.
By
–
There’s going to be a “Before Optimus” and “After Optimus” timeline in the history books.
— AI Breakfast (@AiBreakfast) 24 septembre 2023
LLMs just got eyeballs and opposable thumbs and you can probably run them for free from the solar charger on your roof. pic.twitter.com/lhp1J5CKcpThere’s going to be a “Before Optimus” and “After Optimus” timeline in the history books. LLMs just got eyeballs and opposable thumbs and you can probably run them for free from the solar charger on your roof.
-
OWL: Specialized LLM for IT Operations Management
By
–
9/ LLMs for IT Operations – proposes OWL, an LLM for IT operations tuned using a self-instruct strategy based on IT-related tasks; it discusses how to collect a quality instruction dataset and how to put together a benchmark.