Nijikokun

Hey there, I work on the AI Gateway at ngrok, so take this with the appropriate grain of salt.

"LiteLLM plus a dashboard" is a reasonable thought. Especially since gateways generally share a lot of similar plumbing, and I think LiteLLM is a good open source option. If you only need a translation layer and are happy to operate one on your own I think that LiteLLM would be a good fit for you.

But, ngrok.ai is for teams that want to get started quickly without having to setup and scale anything themselves. I can tell you for certain it is not LiteLLM underneath the hood and relies on the same global networking infrastructure as ngrok.

Since it leverages the ngrok infrastructure, it can route to models running on your own infrastructure in addition to public models and comes baked in with per-key access controls, automatic failover, and usage visibility. How you want to scope your keys is up to you since they can represent people, applications, or environments.

We've definitely put thought into the primitives, and while it's pretty bare bones right now, we're continously improving it every day.

I'm always open to hearing about your needs, what you think we are missing, and how we could improve.

Feel free to reply here or message me at niji@ngrok.com

> only >> recenlty << started happening

can't believe I was baited into reading this slop

/jk

good post actually, and a fair point

I do think many people will argue that you can just not review things though.

Meta is behind a huge amount of it, they have funded the majority of these

thats why i use caddy or ngrok.ai

There was a lot of speculation whether or not the model would use them or even if it would attempt to use them and they noted this months ago. Now they have clear evidence of them doing so. Seems reasonable.

context windows are too small and conversely larger windows are not accurate enough its annoying

Defold is good, been around a very long time, but it's just rough around the edges, once you get used to it it's pretty smooth sailing though.

ngl building a social network isn't hard, getting people to use a social network is the hard part

it performs well with composition, however it seems SD and SDXL excels in capability and quality when intermixed with pipelines and workflows, this doesn't do much to talk about that comparison and whenever i see things like this i think about the overall workflow, like cool you do good composition but you don't fit within the workflow or ecosystem that surrounds that tool and thus i have low expectations around adoption

the biggest issue i've had for things like this is that ai doesn't understand context very well, anything that is beyond a context window creates hallucinations and it starts making up things that may exist in one location but it tries to apply it to a completely unrelated scenario, would be curious if this does understand the connected pieces appropriately and catches things that break those connections, otherwise it's just another linter?

I thought the main site was amazing, then I saw the docs. Absolutely amazing work. Well done. Extremely excited to try out WAAPI.

Type definitions are definitely compiled with CPP. Type erasure only happens with polymorphism types. You can actually view the types with ghidra.

That feels more like you're being abused rather than a framework problem.

His argument is that you are building on the assumption that this is safe:

    "SELECT * FROM foo WHERE bar=?"
    bindParameter(1, userInput);

But what happens when it turns out that isn't safe?

Honestly, I thought this was going to be another AI post. TIL about zola. Looks cool.

We should really prevent people from doing consecutive terms.

Is it worth having your own real estate to do what you want? Yes.

I like this language a lot. I find myself searching for something to make in it.

Never opposed to sacrificing some comfort for learning.

I'm not in the business of cheap. I do care about resource availability though.

Honestly my largest feedback is what does it integrate with? Present this on the homepage instantly. The documentation doesn't cover it, and clicking "+ database" has me sign up. I'm not going to sign up unless I can do what I need to do and I don't know if I can if I don't know how the dataset is configured or what it can pull / be streamed from.

Ultimately, it all comes down to build what you're comfortable with. Additionally, when you're managing large organizations and teams. Build with what you can hire quickly for and easily scale with.

Java is still great, same for PHP and they have only been getting better.

I did not personally find this to be a detractor.

Reducing barrier to entry is not a bad thing

Realistically the reasons are this:

> So while parameterized methods seem clearly useful at first glance, we would have to decide what they mean and how to implement that.

They just didn't want to decide what they mean or how to implement them.

Why do I need an account to make a card? Shouldn't that only be required if I want to share / save the card?

I had the same reaction, it gives you the feeling that the article itself is also AI

Think Obsidian for neovim

It has it's own language (not markdown) and key bindings

I find it harder to use than markdown with wiki link support