.@Sprig doing very cool things with surveys and AI https://t.co/cjJE7OakEi pic.twitter.com/4AjvM8Bqzm
— Lenny Rachitsky (@lennysan) 30 août 2023
.
@Sprig doing very cool things with surveys and AI
TOOLS
-
Sprig Leverages AI for Advanced Survey Solutions
By
–
-
6 Best Practices to Fuel AI Project Innovation
By
–
Fuel innovation and level up your #AI projects with these 6 game-changing best practices by @ingliguori && @kenovy_it #GenerativeAI #Chatgpt #FutureOfWork #ArtificialIntelligence #GPT4 #innovation #DigitalTransformation #dataops #ethicalAI #mlops #AIOps
-
QLoRA-style Quantization Added with BNB NF4 Support
By
–
Yes! Just added QLoRA-style quantization the other week, too. You can use it via –quantize "bnb.nf4" for example. I have some benchmarks here:
-
LangSmith Monitoring: Tracking App Usage and User Experience
By
–
We launched monitoring in LangSmith today I've mainly been using for two use cases: Track usage – are people actually using my app? / Track feedback – are changes I introduced leading to a better user experience? Can you spot when we upgraded our app to use an agent?
-
Efficient object detection with YOLOv8 and KerasCV
By
–
Efficient object detection with YOLOv8 and KerasCV:
-
Fine-tune Models to Replace GPT-4 Using LangSmith Data
By
–
This is really useful for finetuning models to replace GPT-4 at particular points in your system Log all data flowing through your app to LangSmith Export with some filter (all runs, all runs with positive feedback, etc) to a dataset Finetune a model on this data!
-
Cerebras MBZUAI Develop Arabic-Optimized Language Model Techniques
By
–
(2/2) Researchers at Cerebras, Inception, and MBZUAI developed techniques to:
-Create a custom tokenization scheme optimized for Arabic -Identify the proper mix of English, Arabic, and code data -Augment Arabic tokens with machine-translations Models: https://
huggingface.co/inception-mbzu
ai
… -
Asking ChatGPT to evaluate its output and suggest missing input
By
–
What additional input do you need from me to help you write better output? This basically asks ChatGPT to evaluate its own output, as well as the initial prompt, and suggest additional information to improve the output.
-
Code Llama Now Available on Poe Platform
By
–
Code Llama is now available on Poe! Note that many of the Code Llama demos floating around during the last week on other services had bugs; we took some time to make sure our implementation works accurately to the underlying model.
-
SAS Viya Streamlines Workflow Management for Enterprise Solutions
By
–
Way too much to do and too little time? Meet SAS Viya. ⚪ https://t.co/buPU0MgYe2 pic.twitter.com/IJJycDK5Mw
— SAS Software (@SASsoftware) 30 août 2023Way too much to do and too little time? Meet SAS Viya. http://
2.sas.com/6019PtK0P