Congratulations @jerryjliu0 on the milestone! Would love to integrate @Lutra_AI with @llama_index
@jiquanngiam
-
Data Enrichment Workflow: Airtable LinkedIn Integration Tutorial
By
–
Tutorial and workflow here: https://
lutra.ai/use-cases/data
-enrichment-airtable-linkedin
… You can also easily modify this to use Google spreadsheets. -
Enrich Contact Data with AI-Powered Workflow Automation
By
–
Do you have a list of contacts you want to enrich with more information? Here's how you can pull public data into your spreadsheet, no coding required.
— Jiquan Ngiam (@JiquanNgiam) 21 février 2024
Using @Lutra_AI, you can easily make a workflow that:
1. Connects to you existing @airtable base.
2. For each person listed in… pic.twitter.com/aEY0J9vlRwDo you have a list of contacts you want to enrich with more information? Here's how you can pull public data into your spreadsheet, no coding required. Using @Lutra_AI, you can easily make a workflow that: 1. Connects to you existing @airtable base.
2. For each person listed in -

Groq’s Vertical Integration Strategy in Token-as-Service Pricing
By
–
"We're very comfortable at our current pricing for Token as a Service. Very." — @JonathanRoss321
, re: Groq pricing. Model serving continues to be race to the bottom. The winners are going to be those who are fully vertically integrated – including hardware. #Groqspeed -
AI Self-Verification and Reflection Capabilities Discussion
By
–
That’s incredible. Can you get it to check its work? I wonder how good self reflection will be.
-
Ring Attention on Groq: Fast Long Context Windows
By
–
@tomjaguarpaw will ideas from Ring Attention work well on Groq? Excited to see fast + super long context windows.
-
Groq’s 500 Tokens/sec Enables Production Self-Reflection for LLMs
By
–
@GroqInc at almost 500 tokens/sec makes repeated self-reflection usable in production, changing everything.
— Jiquan Ngiam (@JiquanNgiam) 20 février 2024
A key technique with LLMs is to use self-reflection (Reflexion) to get the model to do better. The problem used to be that it is slow – no longer.
We can now use… pic.twitter.com/d4QSRU9a6u@GroqInc at almost 500 tokens/sec makes repeated self-reflection usable in production, changing everything. A key technique with LLMs is to use self-reflection (Reflexion) to get the model to do better. The problem used to be that it is slow – no longer. We can now use
-
Lutra AI Webhooks Integration with Zapier Now Available
By
–
That's so cool you got this working 🙂 Most of the logic here should be easy to get going with Lutra – let's figure out how to get IT approval! Relatedly, we are rolling out webhooks with @Lutra_AI which allows you to easily integrate Lutra with @zapier
-

RingAttention Communication Overlaps Computation on Google TPU
By
–
"… the communication cost during RingAttention fully overlaps with computation …" Google TPU's fast interconnects are definitely working out well here.
-
Large World Models: Open-Source AI with 1M Context Window
By
–
Large world models by @haoliuhl et al. is worth checking out if you like the Gemini-1.5 and Sora results. It has 1M context window, generates videos, and is open sourced.
— Jiquan Ngiam (@JiquanNgiam) 19 février 2024
1. LWM shows high recall over 1M context window, and performs exceptionally well with video chat as well.… pic.twitter.com/1kGLIHjD4LLarge world models by @haoliuhl et al. is worth checking out if you like the Gemini-1.5 and Sora results. It has 1M context window, generates videos, and is open sourced. 1. LWM shows high recall over 1M context window, and performs exceptionally well with video chat as well.