Consider also Chiness EV prices. Unfortunately you can't buy them in the US it seems. https://www.reuters.com/business/autos-transportation/averag...

Note it is easy to confuse "free" with "paid by advertisements".

Motive probabaly doesn't matter in the end, outcome does. But understanding the motive is a good thing.

Maybe the financiers of a project just need it, they need it working, not to generate revenue for them?

What if we had a local server running on the same PC, which then relays the request to some shared server on the internet?

That's what a background worker is: a local server managed by the browser and only accessible to pages of the origin domain.

I'm thinking using a local http-server instead of web-workers . The local http server would do all the server-logic except also passing data that needs to be shared to a non-local server.

True, but that is a great fact to start from, and understand.

Then the next question becomes "HOW do they predict the next token?" There are many ways that can be done, why is this particular algorithm so GOOD?"

When people say "We don't understand how LLM works" isn't it really saying we don't understand how this specific algorithm used to predict the next token works? No, it is not, because "we" do understand how all those algorithms work there are many descriptions of them available.

So the question then really is "Why is the prediction this algorithm makes, so good, as compared to some other statistical algorithms?"

It's not about "Why does AI work so well?". It should be "Why does this particular XYZ algorithm work so well?"

Game of Life comes to mind: Most simple logic, emerging patterns are hard to believe.

Isn't the LLM simply predicting what should be the next sentences after user's input, using its algorithm and data it has exatrcted from existing texts on the internet. The algorithm that does that could have many different designs, some better some worse for the purpose of predicting what output makes most sense next?

So what is it that we don't understand about why theyr work? The algorithm? We have the code. Why the specific algorithm makes such good predictions? I see it as a generalization of trying to predict who wins Kentucky Derby.

LLM is an Oracle

The big breakthrough is we can interact with the agents using natural language - because of the LLM.

It is the combination of LLM and agent-harnesses that make it look really smart. Agent-harness is a programmatic device that lets us tap into the vast knowledge in the LLM.

It is probabaly true that many TV-commentators fail to appreciate this fact and therefore think LLMs are super-intelligent. No, it is the combination of LLM and the programmatic agent-haness that is the breakthrough.

An interesting thought is that the LLM could in theory code the agent-harrness, start it running every time we interact with it. Currently the agent-harrness I think is pretty static I think. In theory it could be dynamically created for every task. Would that make it better don't know.

> The big breakthrough is we can interact with the agents using natural language - because of the LLM.

Without ReAct and tool calling, all you have is a chatbot. That's useful, but it's just a chatbot.

ReAct loops and tool calling is what unblocks high value usecases. It enables systems to actually address free-form problem statements, gather data that is not a part of their training set, inspect the current state of services,and trigger actions in external systems. This goes well beyond mere chatbots.

> It is the combination of LLM and agent-harnesses that make it look really smart.

It's really not about "smart". It's about autonomous systems, and being able to consume and analyze new data, and trigger actions in external systems.

It's not very novel, though, it's a fairly obvious step once you get something that can operate iteratively and largely independent, there were a ton of people trying to get LLMs to loop on their own even before deepseek r1.

And I remember talking about goal directed behavior (which what people are calling "agents" now don't seem to properly have) and autonomous operation decades ago in the intelligent agent course at uni, including react loops.

So no, the huge step with LLMs really was just that attention mechanism from that translation paper everyone forgot until Google brought its marketing to it, everything else is either just optimization/scaling, more money or old ideas suddenly relevant.

> It's not very novel, though (...)

I completely disagree. The rollout of agentic tools, and even support for agent mode in IDEs, is the whole value proposition of AI code assistant services.

Otherwise you'd just have a glorified search engine in a chat window.

> (...) it's a fairly obvious step once you get something that can operate iteratively and largely independent,

There's some confusion in your reply. ReAct loops is exactly what this "operate iteratively and largely independently" represents.