`langchain-chroma` Partner Package Released! We're really excited to welcome @trychroma
's open source vector store to the LangChain partner packages. Built on top of their newest v4 sdk, huge thanks to @akiradev0x and the Chroma team for implementing. Give it a try
AI
-

LangChain Chroma Partner Package Released
By
–
-

LLMs Vulnerable to Short Token Sequences Manipulation Study
By
–
This is an important paper that demonstrates empirically something that folks like @goodside & I have been warning about. LLMs are easy to fool, and this paper shows that short token sequences are enough to alter the advice of AIs about what product to buy. SEO for AI is here
-

AI-Powered Hair Clipper with Real-Time Camera Technology
By
–
This hair clipper has a real-time camera to make sure you won't mess it up
— Ronald van Loon (@Ronald_vanLoon) 12 avril 2024
via @Fabriziobustama#AI #TechForGood #Tech #Technology #FutureOfWork #Innovation
cc: @pascal_bornet @pbalakrishnarao @ravikikan pic.twitter.com/wBxIFN9C1mThis hair clipper has a real-time camera to make sure you won't mess it up via @Fabriziobustama #AI #TechForGood #Tech #Technology #FutureOfWork #Innovation cc: @pascal_bornet @pbalakrishnarao @ravikikan
-

Apple’s App Store Problem: ChatGPT Knockoffs Confusing Users
By
–
Apple is really falling asleep at the wheel. I am surprised by how many times someone shows me they have “ChatGPT” on their phone and it is one of many other random ripoff apps that come up first when you search for ChatGPT. People don’t know any better and get confused.
-
Cohere Command R+ Achieves 111 Tokens Per Second
By
–
Cohere's Command R+ at 111 tokens/s 😲 https://t.co/swbaGtzsID
— Hugging Face (@huggingface) 12 avril 2024Cohere's Command R+ at 111 tokens/s
-
llm.c versus PyTorch: speed and simplicity comparison
By
–
…"in that llm.c will never be as fast nor as simple as pytorch"
-

Deep Learning Performance Optimization: Complexity and Resources
By
–
This post became popular; Few more thoughts / pointers on the topic for the interested reader. Example of the complexity involved: @cHHillee has a great post "Making Deep Learning Go Brrrr From First Principles" https://
horace.io/brrr_intro.html
I was always struck by this diagram from -
Programming: Thinking Over Syntax, Outsourcing Thinking Fails
By
–
Programming is thinking + syntax. Maybe 90% thinking and 10% syntax. While you can automate away syntax, you can only ever outsource thinking to someone/something that can think. Attempts to outsource thinking to a syntax generator do not end well.
-

Low-Level Code Performance Optimization Zeitgeist
By
–
well that’s exactly what I said; anyway i’m referring to this tweet about performance optimizations, as well as the greater zeitgeist where everyone things it’s faster to write low-level code
-
Unity Catalog: Data Lineage and Feature Store Capabilities
By
–
The technology behind Unity Catalog supports a variety of business outcomes: faster innovation, cost reduction, compliance support & more. Dive into some of the capabilities that make this possible, such as our data lineage, Feature Store, & more!