Nicolay Gerold

@nicolaygerold

All cardsCollections

Include a down regulation after your workouts (longer exhale). 5 min after workouts (e.g. in the shower), 1 min after important parts of your workouts.

Andrew Huberman • Dr. Andy Galpin: How to Build Strength, Muscle Size & Endurance

Introducing Wren Engine

The advent of Trend AI agents has revolutionized the landscape of business intelligence and data management. In the near future, multiple AI agents will be deployed to harness and interpret vast amounts of internal knowledge stored within databases and data warehouses. To facilitate this, a semantic engine is crucial. This... See more

Introducing Wren Engine | WrenAI

RAG and Cool Projects / Repos

The ideal solution for AI-native vectorDB would be something that would would be easy to set up and should integrate with existing APIs for rapid prototyping but should be able to scale without additional changes.

LanceDB is designed with this approach. Being server-less, it requires no setup — just import and start using. Persisted in HDD, allowing... See more

Ayush Chaurasia • LLMs, RAG, & the missing storage layer for AI

📖 Introduction

ReactAgent is an experimental autonomous agent that uses GPT-4 language model to generate and compose React components from user stories. It is built with React, TailwindCSS, Typescript, Radix UI, Shandcn UI, and OpenAI API.

🚀 Features

Generate React Components from user stories

Compose React Components from existing components

Use a

eylonmiz • GitHub - eylonmiz/react-agent: The open-source React.js Autonomous LLM Agent

Agents

I’ve been giving talks and speaking with engineers and non-technical audiences about interpretability since 2022, and I still struggle to explain exactly what a “feature” is. I often use words like “concept” or “style”, or establish metaphors to debugging programs or making fMRI scans of brains. Both metaphors help people outside of the subfield... See more

Shortwave — rajhesh.panchanadhan@gmail.com [Gmail alternative]

LLMs

You’ve got a vector database that has all the right database fundamentals you require, has the right incremental indexing strategy for your use case, has a good story around your metadata filtering needs, and will keep its index up-to-date with latencies you can tolerate. Awesome.

Your ML team (or maybe OpenAI) comes out with a new version of their... See more

6 Hard Problems Scaling Vector Search

RAG

Why is Discord such a good GTM for AI applications?

Text interface. Most users are just generating images, videos, and audio in these Discord servers. Prompts are easily expressible in simple text commands. It’s why we’ve seen image generation strategies like Midjourney (all-in-one) flourish in Discord while more raw diffusion models haven’t grown... See more

Shortwave — rajhesh.panchanadhan@gmail.com [Gmail alternative]

LLMs

Laws of strength and conditioning:1. Progressive Overload: At whatever you want to improve at, you need to progressively overload. Adaptation is a byproduct of stress (more reps, load, higher complexity, shorter time frame,…)2. Exercises themselves do not determine adaptation. The application (sets, reps, load, time) determine it. This precedes the... See more

Andrew Huberman • Dr. Andy Galpin: How to Build Strength, Muscle Size & Endurance

FastStream brokers provide convenient function decorators @broker.subscriber and @broker.publisher to allow you to delegate the actual process of:

consuming and producing data to Event queues, and

decoding and encoding JSON encoded messages

These decorators make it easy to specify the processing logic for your consumers and producers, allowing you to... See more

airtai • GitHub - airtai/faststream: FastStream is a powerful and easy-to-use Python framework for building asynchronous services that interact with event streams such as Apache Kafka and RabbitMQ.

Producing: One part of your system (a producer) wants to send a message, which could be anything like an order from a customer, a sensor reading, a log message, etc. Consuming: Another part of your system (a consumer) wants to receive and process that message. FastStream acts as a postman, ensuring the message is delivered accurately and efficiently from producer to consumer. Applications: E-commerce Platform: When a customer places an order, a message regarding that order needs to be communicated to various services like Order Management, Inventory Management, Payment Gateway, and more. FastStream will handle these messages, validate the order data, and ensure that all relevant microservices are informed in real-time, ensuring a smooth ordering process. IoT Sensor Network: Consider a network of IoT devices sending sensor readings (temperature, humidity, etc.) to a central server. FastStream ensures that all these readings are valid, documented, and are efficiently communicated to the central server for further analysis or action. Financial Transactions: In a financial application, transactions and trading data can be passed through FastStream to validate transactions, communicate them to various analytic and logging microservices, and even trigger alerts or actions based on the data.