I feel the majority of junior job-hopping is due to the fact that they are often hired for really low, and then proposed just an incremental raise after two years. Instead, if they change company, then they got a big jump.

At least, that's what I saw happening here in Hong Kong for juniors I worked with, not sure for other areas.

Thanks, I didn't knew about LiteLLM!

OpenRouter have some interesting providers, like Cerebras, which delivers 2,300 token/s on gpt-oss

The score are really, really close, it might be why

I think the only reason is for legal purpose.

If data is downloaded illegally from space, stored in space and model trained on it... it will be a mess juridically if someone complain.

Same for model inference, it will be hard for a government to put controls on the model output.

It's nice as well for location that are banned to use private US models. Like here in Hong Kong, Google doesn't allow us to subscribe to Gemini Pro. (Same for OpenAI and Claude too actually).

I feel the issue is that now, what would be done by entire teams (networking team, storage team, database team), is now perform by only the same DevOps team.

We have way less time unfortunately to dig into each tech, business is pressing us like lemon on the other side to ship quickly.

It's mostly for AWS context, when you want to host for example your servers in a private subnet, but you want to allow access of small part: you can leverage a NAT Gateway to be the public entrypoint + some security groups as gatekeepers to filter the traffic.

However, the fees from AWS are atrocious on the NAT Gateway.

I am curious: why would you you like to have that? (Genuine question, I am personally so scared about the AI going crazy and putting slop everywhere that I often ask it to focus on a single well defined area first)

Good idea!

I found Gemini have horribly slow for anything

GPT-5 was horrible. It produced AI slop have immense speed, which is quite tough when other coworkers ask to review their PR...