With #AI, you can automatically optimize your data warehouse performance! Learn how #DatabricksSQL can extend data and AI to your organization for a faster, easier, and more cost-effective data warehousing experience in this on-demand webinar https://
bit.ly/49evlpA
AI
-
Optimize Data Warehouse Performance with Databricks SQL AI
By
–
-

Building RAG Chatbot with Upstash Vector Stack
By
–
Building your own RAG chatbot with Upstash Great blog by the @upstash team on how to build a RAG chatbot with a top tier tech stack: Upstash Vector, Upstash Redis, Hugging Face Inference API, Replicate LLAMA-2-70B Chat model, and Vercel https://
upstash.com/blog/rag-chatb
ot-upstash
… -
XOR Representability vs Efficiency in Program Search
By
–
There's no connection, XOR was a representability issue. It's easy to fit a curve to a XOR dataset. That said, doing so is tremendously inefficient compared to program search over a DSL that just has NOR, for instance. So if you want a parallel, it's there.
-

OpenAI Sora Team Members Are UC Berkeley BAIR Lab Graduates
By
–
The @OpenAI core team behind #Sora, Tim Brooks (
@_tim_brooks
) and Bill Peebles (
@billpeeb
), are recent graduates of @UCBerkeley @berkeley_ai BAIR Lab. Apparently they chose the name Sora because it "evokes the idea of limitless creative potential". -
Gemini’s Impressive Information Filtering from Million Token Context
By
–
Strange, imo most tester were impressed by the capability of Gemini to filter information from the ~1mio token
-
Blood Test Creates Alzheimer’s Diagnosis in Healthy People
By
–
How a blood test (p-Tau217) and drugs that have little efficacy (and major side effects) are creating "#Alzheimers Stage 1" in healthy people with no symptoms or memory deficit https://
latimes.com/science/story/
2024-02-14/inside-controversial-plan-to-diagnose-alzheimers-in-people-without-symptoms
… @MelodyPetersen @latimes @alzassociation -

ReWOO Agents: Reasoning Without Observations Framework
By
–
Agents that Reason WithOut Observations (ReWOO)⍱ Take the “plan + execute” agent design up a notch via variable assignment. Can generate better plans (and avoid re-planning) while letting task executors focus. JS: https://
github.com/langchain-ai/l
anggraphjs/blob/main/examples/rewoo/rewoo.ipynb
…
Python: https://
github.com/langchain-ai/l
anggraph/blob/main/examples/rewoo/rewoo.ipynb
…… -
MKBHD Reports on Major AI Breakthrough and Advancement
By
–
If even @MKBHD reports on the huge leap in AI, that must mean something https://
youtube.com/watch?v=NXpdyA
WLDas
… -

ChemLLM: Specialized LLM Outperforms GPT-4 Chemistry Tasks
By
–
8/ ChemLLM – a dedicated LLM trained for chemistry-related tasks; claims to outperform GPT-3.5 on principal tasks such as name conversion, molecular caption, and reaction prediction; it also surpasses GPT-4 on two of these tasks.
-

Survey of Major LLM Families: GPT, Llama, PaLM
By
–
9/ Survey of LLMs – reviews three popular families of LLMs (GPT, Llama, PaLM), their characteristics, contributions, and limitations; includes a summary of capabilities and techniques developed to build and augment LLM.