Finally a video after so long on the channel and that to on DSPy. Going to be a great watch!
LLMS
-
Google Ultra Launch Expected to Trigger OpenAI Response
By
–
As soon as Google drops Ultra, I expect OpenAI to drop a new model. They won’t give up their lead.
-
Evaluating Multimodal LLMs: Generalizability, Trustworthiness and Causality
By
–
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities Lu et al.: https://
arxiv.org/abs/2401.15071 #ArtificialIntelligence #ChatGPT #DeepLearning -
OpenAI GPT mentions, Bard surpasses GPT-4, new AI tools and jobs
By
–
Top stories in AI today: -OpenAI introduces GPT mentions
-X secures Georgia tax break for $700M AI data center
-How to utilize GPTs in your ChatGPT workflows
-Bard surpasses GPT-4 on chatbot leaderboard
-9 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/openai-tags-
in-gpts
… -
10 ChatGPT prompts to boost your business profits
By
–
Copy and paste these 10 ChatGPT prompts to make your business more profitable:
-
Building Enterprise RAG Systems: Key Components and Failure Points
By
–
A very good blog post by @nlpguy_ on "Building Enterprise RAG Systems" that covers Common failure points of RAG systems Guardrails on inputs and outputs Retrieval part including query rewriter, encoder, chunker, reranker. Storage part including indexer, data
-
LLaMA Leak: Open-Source Innovation vs Commercial Legal Risks
By
–
TThe leakage of LLaMA is what started the open-source revolution, so on one side it can foster innovation and accelerate the space. On the other hand, it's definitely important to consider the legal implications, especially if used in a commercial setting.
-
Mistral-Medium 70B Leaked Model Runs Locally at 10 Tokens/Second
By
–
Running the "allegedly" leaked Mistral-Medium 70B locally. This is an extremely good model, which also confirms to be created by Mistral. If this is true, I feel bad for the guys at Mistral AI. It's also crazy how the M3 runs this at 10 tokens per second.
-
Bard Surpasses GPT-4 on Chatbot Arena with Gemini Pro
By
–
Bard moved into second on the Chatbot Arena Leaderboard, surpassing GPT-4 and trailing only GPT-4 T. Impressively, Bard only uses Gemini Pro, the middle tier of Google's LLMs. The updates make me more excited than ever for the launch of Gemini Ultra.
-
GIF explaining how large language models work
By
–
If you were ever wondering how LLMs work, this GIF explains it really well!
— God of Prompt (@godofprompt) 29 janvier 2024
pic.twitter.com/3kpulAe3L4If you were ever wondering how LLMs work, this GIF explains it really well!