Ask HN: How to run Language Models on your own? by sudhirc

As someone who is new to running Language Models, I am struggling to understand the infrastructure needed to run them effectively. I would greatly appreciate any advice you can offer. Could you please help me with the following questions:1. What are the hardware specifications you would recommend for running Language Models?2. What are the building

ByHackTechApril 30, 20230Comments

News

Mental Models by dudzik

Mental Models

ByHackTechApril 20, 20230Comments

News

Timeline of Transformer Models / Large Language Models by vemgar

This is a collection of important papers in the area of Large Language Models and Transformer Models. It focuses on recent development, especially from mid-2022 onwards, and in no way claims to be exhaustive. It is actively updated. See also blog post and paper of Xavier Amatriain which provides an excellent overview over the variety

ByHackTechApril 16, 20230Comments

News

AGI models may “sleep” by fine-tuning aiself by sipex

Something went wrong, but don’t fret — let’s g

ByHackTechApril 8, 20230Comments

News

Making Models in production the norm; how to get 90% of them in prod by mari_lc

TL;DRPutting machine learning (ML) models in production is considered an operational challenge that is performed after all the hard work on training and optimizing the model is completed. In contrast, serverless ML starts with a minimal model, including the operational feature pipeline(s) and inference pipeline. The feature and inference pipelines are needed to ensure the

ByHackTechMarch 7, 20230Comments

News

Foundation Models: The future still isn’t happening fast enough by palakgoel

Well, this is fun. The current pace of activity in artificial intelligence is nothing short of astonishing. Generative AI applications, and a larger category of apps that apply complex reasoning to data, are proliferating based on foundation models. The apps span from the practical (accelerating code development and testing, legal contracting, and the production of

ByHackTechJanuary 27, 20231Comment

News

Ask HN: Why there are new and better AI models on a daily basis? by boredemployee

Be it on HN, linkedin, random blog posts, I see that new models are appearing daily that make the previous model “outdated”.Is it pure coincidence or what is happening for these things to be happening in parallel?I find all this so incredible, it seems that we are living a revolution of our times but the

ByHackTechJanuary 9, 20230Comments

News

How bad models ruin an API (or why design-first is the way to go) by abunuwas

microapis.io | Consulting and teaching for microservice APIs

ByHackTechFebruary 28, 20220Comments

News

Mental Models for Problem-Solving to Avoid Catastrophic Mess by durmonski

Problem-solving rarely comes to mind until we’ve implemented a fix. That’s why we often say: “Oh, I had to do this, instead. Not go with the usual fix.” We think more about alternative solutions after we’ve encountered a problem, not before that. Why this is the common way we act? And can we do something…

ByHackTechJanuary 11, 20220Comments

Sign Up to Our Newsletter