ive been trying to make semantic search work on 150k documents for a while. what ive found so far is that it doesnt work. it only works for toy examples, very small datasets and data which the LLM has more or less already seen and that's why it answers well from it.
LLMS
-
La méthode la plus rapide pour construire une interface de chat
By
–
The FASTEST way to build CHAT UI for LLMs pic.twitter.com/4KcDrk51oL
— abhishek (@abhi1thakur) 12 août 2023The FASTEST way to build CHAT UI for LLMs
-
OpenAI Faces Bankruptcy Risk: ChatGPT Daily Costs Soar
By
–
ChatGPT In Trouble: OpenAI may go bankrupt by 2024, AI bot costs company $700,000 every day! https://
firstpost.com/tech/news-anal
ysis/openai-may-go-bankrupt-by-2024-chatgpt-costs-company-700000-dollars-every-day-12986012.html
… #GPT #ChatGPT #LLMs #LLM #GenerativeAI #GenAI #technology #AI #tech #business #bankruptcy #SpendtoEarn #funding #OpenAI #AIethics -
List of Open Source Language Models for Commercial Use
By
–
GitHub – eugeneyan/open-llms: A list of open LLMs available for commercial use.
https://bit.ly/3MG7VRA #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Groq Achieves 100 Tokens Per Second Milestone
By
–
https://
forbes.com/sites/moorinsi
ghts/2023/08/11/groqs-record-breaking-language-processor-hits-100-tokens-per-second-on-a-massive-ai-model/?sh=291e431358f0
…
More excitement around our announcement. The first company to deliver 100 Tokens Per Second Per User! This means companies will be able to provide best-in-class fluid and fluent interactions with LLMs like Llama-2 for their customers. -
Large Language Models: Quick Reference Guide Explanation
By
–
A cheat sheet explanation of how Large Language Models work:
-
Groq’s Sequential Processing Achieves 100 Tokens Per Second
By
–
"Groq’s focus on sequential language processing provides better performance than general-purpose AI chips… when dealing with massive LLMs, speed is a major factor for performance—and nothing yet can compare to 100 tokens per second." – @Forbes http://
groq.link/811forbes -
Scale AI Launches LLM Test and Evaluation Platform
By
–
Today, alongside our collaboration with the @WhiteHouse and @DEFCON in an evaluation of the leading LLMs— @scale_ai is announcing the release of our Test and Evaluation platform and approach to enable for safe and scalable deployment of AI systems. Read thread for more
-
DEFCON Red Teams Leading AI Models for Security Vulnerabilities
By
–
At @DEFCON
, cybersecurity experts will be red teaming leading models from OpenAI, Anthropic, Google, and more. They will be using @scale_ai
’s platform to proactively identify vulnerabilities and report them to the model developers. -
Tidier: AI and Machine Learning Resource Link
By
–
Tidier https://
bit.ly/3DOG5NK
#AI #MachineLearning #DeepLearning #LLMs #DataScience