liorn

Great guide, thanks.

The Case study for me was the most interesting part; it shows that you really have to check all the different options to get to your optimal serving stack, and that there's no single best-solution to your configuration - each workload, traffic and hardware require their own unique mix of engine+configuration.

BTW, the link doesn't work - I think you submitted https://docs.modelplane.ai/main/guides/inference_guide instead of https://docs.modelplane.ai/main/guides/inference-guide.

It's not that easy.

The optimal inference configuration varies according to the model, the specific traffic (which changes in time), and the specific hardware it's running to. The "knowledge" for it doesn't exist yet.

Usually in similar scenarios an agent will try to experiment with various configurations and get to a good result. However, you can't have an agent test out different inference serving configurations/architectures, since every experiment might involves 10-60 minutes of spinning up a model (on very expensive GPUs)...

It's not a one time thing though - onprem inference requires continuous monitoring and tuning to get the most out of your GPUs. Looking at 25-50% performance benefits. Today, it does require dedicated Inference Engineers...

I asked it about Tailwind CSS (since I had problems with Claude not aware of Tailwind 4):

> Which version of tailwind css do you know?

> I have knowledge of Tailwind CSS up to version 3.4, which was the latest stable version as of my knowledge cutoff in January 2025.

Can one even refuse it? If someone just sends tainted coin to my address, am I screwed?

If I were a malicious actor with a good way to attack this, I would wait until this was being used in real applications which deal with larger amounts of ETH, and then attack.

Why should I reveal my cards for $3K?

The cockpit recording from Japan Airlines Flight 123 (which crashed due to improper repairs of tail strike damage 7 years earlier) is chilling. https://www.youtube.com/watch?v=Xfh9-ogUgSQ

This really reminds me of the Introduction to Monkey Island 3: https://www.youtube.com/watch?v=mL0086T-u6A

Python developer here. Here's my rant.

I've been using OrientDB (one of the leading Graph databases) for the last few months; it's been a horrible experience to get it working with Python, as the official Python OrientDB driver is essentially a very thin wrapper around the binary protocol.

Using Gremlin would actually be nice, and save me a lot of nasty queries, but it seems like there is no python ecosystem for it. The presentation mentions "Gremlin-Python". A quick Google search brings up these results:

1. "Bulbs" (http://bulbflow.com/download/) - it's a dead project, last commit being 10 months ago. Look at https://github.com/espeed/bulbs

2. "Gremlin-Python" - https://github.com/pokitdok/gremlin-python . Dead project (last commit 6 months ago), and requires one to install Jython.

I would love to know if I've missed something - did anyone get Python to nicely work with Gremlin?

Try PriceDrop instead to follow Amazon product prices: http://pricedrop.stuffstuff.org . It's not evil.

How do you know it's actually him?

That's Adi Shamir, an Israeli cryptographer. You might know him as the S in RSA.

http://en.wikipedia.org/wiki/Adi_Shamir