Nobody is accusing them of making the models more efficient.

People are complaining they are changing how many tokens you get on a subscription plan.

Why would anyone dislike getting more service for less (or the same) amount of money?

> People are complaining they are changing how many tokens you get on a subscription plan.

They didn't change this. It's the same number of tokens just a different tokenizer.

They absolutely do change this all the time - session limits vary wildly. The most damning proof of this is that there's absolutely no information about how many tokens you get per session with each subscription level, it's just terms like 5x, 20x. But 5x what? Who knows?

That's not proof of anything. Also the usage is not solely based on tokens because you also have to factor in things like prompt caching costs (and savings). So it's based on the actual API cost.

You and I have no way of knowing that.

Except that the API cost is literally logged on disk for every session and it's easy to analyze those logs.

We aren't talking about API costs or number of tokens consumed, we are talking about number of tokens in a monthly subscription.

Again, it is not based on number of tokens. If it was solely based on number of tokens then things like cache misses would not impact the usage so much. It's based on the actual cost which includes things like the caching costs.

The next generation on humans growing up with TikTok autogenerated AI videos written by ChatGPT, generated by Sora and uploaded to the web using OpenClaw or whatever automation tool you wrote using Claude Code.

There are literally people running bots creating such shortform videos as we speak.

And there are millions of kids (and adults) scrolling those same videos as you reading this.

Let that sink in.

> The next generation on humans growing up with TikTok autogenerated AI videos written by ChatGPT

That's other people. I'm not in that cesspol and neither will my children.

"distributed neural network" is just AI-bro speak, most likely generated by an LLM.

So I would just ignore that whole comment.

What you said is the truth.

Cheap, efficient, fast manufacturing process. I am a software dev, I happen to have worked with Chinese software APIs related to manufacturing and logictics. Move fast and ship broken stuff on monday, and forget to fix it - that is the reality, but somehow people expect they maintain some level of quality now.

Just try working with products like TikTok, their APIs and documentation, the endless headache you will get will show you how they do itterate, but quality is still only barely a factor.

I've worked in the automotive industry, as an embedded dev, some years ago.

The software used by the automotive industry, mostly German-written, is absolutely terrible.

Funnily enough, I've worked with some Chinese mobility startups, and I'd say it's exactly the same. Not worse, not better either.

The reason why they do not expose the underlying server schema, is because you aren't supposed to write your own MCP server from zero, in the same way you aren't supposed to write your own GraphQL Server from zero.

Yes, technically you could, but you are "supposed" to just use a library that builds the actual endpoints based on the schema for the version of MCP you are using. And only worry about building your tools, to expose them to a LLM, so it can be consumed (LLM function calling, but with lots of abstractions to make it more developer friendly)

I agree with this, and my preference is generally to use a nice library for such things, but understanding the low level protocol and its capabilities helps me conceptualise the interactions more concretely, and understand more of what a given library is doing for me when I use it. In that way, a clear explanation of a protocol has a lot of value for me.

I can get behind that, but if you’re not supposed to write your MCP server yourself, it makes even more sense to explain how it works so people understand why

Sadly you are right, everything is easy and stupidly made convenient these days ... Or maybe I am just a grumpy guy today! But I do remember when you had to struggle to get software to work, there was no developer experience back then :)