Building a platform for generative AI applications https://
huyenchip.com/2024/07/25/gen
ai-platform.html
… After studying how companies deploy generative AI applications, I noticed many similarities in their platforms. This post outlines these common components, what they do, and implementation
GENERATIVE AI
-
Building Generative AI Application Platforms: Common Components
By
–
-
Cohere Rerank 3 Language Models Now Available on Azure
By
–
Leverage Cohere’s enterprise-grade language models today, Rerank 3 English: https://
azuremarketplace.microsoft.com/en-us/marketpl
ace/apps/cohere.cohere-rerank-3-english-offer?tab=Overview
…
Rerank 3 Multilingual: https://
azuremarketplace.microsoft.com/en-us/marketpl
ace/apps/cohere.cohere-rerank-3-multilingual?tab=Overview
… -
TD Bank Partners with Cohere to Explore Advanced Language Models
By
–
And @TD_Canada @TDBank_US recently signed an agreement with Cohere to explore its full suite of large language models (LLMs), including Rerank 3.
-
Rerank 3 Foundation Model Now Available on Azure AI Studio
By
–
Rerank 3 is now available on Microsoft @Azure AI Studio. We’re excited for users to leverage our cutting-edge foundation model for improved search precision through Azure’s robust infrastructure.
-
Cohere Rerank Boosts Atom AI Search Accuracy by 20%
By
–
Customers like @atomicworkhq are using Rerank to power their digital assistant, Atom AI, and saw over 20% improved search accuracy and relevance, providing faster, more precise answers to complex IT support queries. https://
cohere.com/customer-stori
es/atomicwork
… -
Benchmark Saturation Drives Need for Better AI Evaluation Metrics
By
–
Alternative explanation: the asymptote is due to the benchmark saturating. We need better benchmarks! But of course, there is no doubt that both open weights and closed models are pushing the envelope quite drastically. Fun times!
-
Llama 3.0 Previous Checkpoint Release Details
By
–
It's the previous checkpoint they presented when Llama 3.0 was released
-
Negative latency voice models soon
By
–
Pretty soon we’re going to have negative latency on voice models where it just interrupts you half way through your question.
-
Three new small models: favorite? When Haiku 3.5?
By
–
So we got 3 small models in a very short period of time Which one is your favourite and when is Haiku 3.5 so we can finally close this loop of disappointments?
-
AlphaProof Solves Hardest 2024 IMO Problem, AI Dominance Expands
By
–
AI is beating me at the things I love, one step at a time (coding, StarCraft, mathematics, …). AlphaProof solved the most difficult 2024 IMO problem (P6). Answer doesn't fit in this tweet