akbirkhan

Nice! Excited tools that makes using microservices easier.

Question tho, when will you guys have python support? I’m a ml researcher here and can you tell that most of my work is now pipelines between different services, e.g. Chaining multiple LLM services. Big bottleneck is if one service returns an error and crashes the full chain.

Big fan of this work nevertheless. Just think you have alpha on the table

this is pretty important when you move to LLMs as microservices (e.g. calling gpt-4 for some plan / then 3.5 for easier sub component).

Would be keen for a python implementation

cool to see products which are price optimised and appreciate that you’re likely to be able to swap out frontier models for smaller models with better task decomposition.

On the other hand, scary to see LLM scaffolding move so quickly. May we live in interesting times.

nice to see the infrastructure for automating agent scaffolding reach maturity.

importantly it’s not just focused on working with the latest frontier model, but swapping expensive models out for cheaper ones.

wonder how complex a task you can breakdown into a series of LLM calls. and how much cheaper this will be than just calling gpt4

Location: London, UK

Remote: Yes

Willing to relocate: Yes

Technologies: Machine Learning (Jax/pytorch/tf), Python, Go, Rust

Resume/CV: https://akbir.dev/resume.pdf

Email: [email protected]

I'm really confused. When looking at artificial intelligence it seems that actually we have dominating corporate labs which through integrated services (such as compute and data), totally dominate academia.

It's coming to the point where researchers that want to make a difference are actively choosing corporate research labs over academic ones.