Is the emerging architecture made out to be more complicated than what most of the companies are currently building? Perhaps! But this is most likely the general direction where things will start trending towards as the auxiliary ecosystem matures.
Shameless plug: For fellow Ruby-ists we're building an orchestration layer for building LLM applications, inspired by the original, Langchain.rb: https://github.com/andreibondarev/langchainrb
The accuracy degrades with a larger context size, as pointed out in the article itself:
> Claude offers fast inference, GPT-3.5-level accuracy, more customization options for large customers, and up to a 100k context window (though we’ve found accuracy degrades with the length of input).
People that have contributed on the project thus far each have at least a decade of experience programming in Ruby. We’re trying our best to build an abstraction layer on top all of the common emerging AI/ML techniques, tools, and providers. We’re also focusbig on building an excellent developer experience that Ruby developers love and have gotten to expect.
Unlike the Python project, as it’s been pointed out here a countless number of times, we’d like to avoid deeply nested class structures that make it incredibly difficult to track and extend.
We’ve been pondering over the “what does Rails for Machine Learning look like?” question, and we’re taking a stab at answering this question.
We’re hyper-focused on the open source community and the developer community at large. All feedback/ideas/contributions/criticism are welcome and encouraged!
This is what I've been wondering as well -- For a brand new project, why would anyone even consider using Rails if there's just a slight chance of adding ML/AI capability in the future?
Location: St Louis, MO
Remote: Yes
Willing to relocate: Yes
Technologies: Ruby, Rails, Node.js, Python, JavaScript, Databases, AWS
Skills: Software Development, Product Development, Engineering Leadership, Change Management, Product Strategy, Budgeting, Recruiting & Hiring, Technical Sales, Software Development Life Cycle, Critical Thinking and Problem Solving
Résumé/CV: https://drive.google.com/file/d/1wkwxJt-08m1zUXMXO8TX1E6igIWcXX8V/view?usp=sharing
Email: andrei.bondarev13@gmail.com
Seeking: An engineering leadership (Engineer Manager/Director of Engineering/Head of Engineering) role at a fast growing early-to-mid stage company.
This sounds like plain “false advertising“ to me. Besides — wouldn’t an inventory tracking platform that has actual real AI/ML capabilities end up eventually replacing its “unintelligent” equivalents since it’ll most likely be a better hence more valuable product?
I should have clarified... I followed my partner to St Louis, MO for 1 year so she could complete her fellowship. We're trying to figure out where to go to next when she's done.
Agreed. These types of articles read like “pop-sci” nowadays… How many more decades will it take for any sort of commercialization of this research to take place?
Location: Currently in St Louis, MO until July
Remote: Yes
Willing to relocate: Yes
Technologies: Ruby, Rails, Python, Node.js, Next.js, JavaScript, React, PSQL, MySQL, Mongo, AWS
Résumé/CV: https://drive.google.com/file/d/1zCKgwuiJnY4FhkOD3T9BEneSDZZ9tB8k/view?usp=sharing
Email: andrei@sourcelabs.io
I'm a software engineering consultant with 12 years of experience building various software products for companies of all shapes and sizes. I've helped Y-Combinator/VC backed startups build and bring products to market, overseen and managed integrations of corporate acquisitions, re-architected and led massive rebuilds for products used by the Fortune 500, and hired, managed, and instructed 3-months bootcamp courses.
Shameless plug: For fellow Ruby-ists we're building an orchestration layer for building LLM applications, inspired by the original, Langchain.rb: https://github.com/andreibondarev/langchainrb