The combination is truly key, how we do it:

- Combining LLMs, gradient boosting, and multiple statistical/heuristic based approaches - For LLMs: rely on (quite) large context length + fine-tuning - The (ML) models are used to extract mathematically provable quality checks

reg. 1) Which one has been used?

We (https://dqc.ai) are doing something in the space, yes. Next to a mixture of ML, and heuristic based approaches, plus link & integrations into source systems. Happy to talk about it, feel free to reach out.

One super interesting startup in this sector: https://www.labtwin.com/ they completely automated lab reporting and made it voice-first

Hehe... hi Lars, long time no "see" ;-) Yes, he is and I was also very happy to see the project getting mentioned here! I used it myself and was always impressed about it!

What is this, class reunion? :D Cheers guys

- padde

Definitely class reunion :D

Omg I just created an account to reply... ;)

Atfarm - https://at.farm - uses satellite data to provide precision fertilization maps for farmers across the globe. (Disclaimer: involvement in the setup)

For all the German fellows: I'll give a talk about "exactly" this topic including a hands-on sample at the "Monster on Rails" Meetup this week in Münster - http://www.meetup.com/Monster-on-Rails-Web-Development-Meetu...

+1 for simplicity

Has one of you tried xhyve? https://coreos.com/blog/coreos-and-xhyve-tech-preview/

Haven't heard but thanks for pointing out. It might be pretty useful actually as I develop on OS X and use CoreOS in production.

And if it is faster than boot2docker with VirtualBox, great!

Thanks rcarmo for bringing this up. You're right, it is a better, and the only right, approach to declare the dependencies like you proposed. I've updated the code!