That is the wrong abstraction to think at. The problem is not _which_ tools you give the LLM, the problem is what action it can do.

For example, in the book-a-ticket scenario - I want it to be able to check a few websites to compare prices, and I want it to be able to pay for me.

I don't want it to decide to send me to a 37 hour trip with three stops because it is 3$ cheaper.

Alternatively, I want to be able to lookup my benefits status, but the LLM should physically not be able to provide me any details about the benefits status of my coworkers.

That is the _same_ tool cool, but in a different scope.

For that matter, if I'm in HR - I _should_ be able to look at the benefits status of employees that I am responsible for, of course, but that creates an audit log, etc.

In other words, it isn't the action that matters, but what is the intent.

LLM should be placed in the same box as the user it is acting on-behalf-of.

How did it turn out? Seems like both still have their trademark and everyone lived happily ever after

Not that I agree with bail-outs, but 2008 financial crisis that resulted in a number of bail outs actually netted the treasury a profit.

> In total, U.S. government economic bailouts related to the 2008 financial crisis had federal outflows (expenditures, loans, and investments) of $633.6 billion and inflows (funds returned to the Treasury as interest, dividends, fees, or stock warrant repurchases) of $754.8 billion, for a net profit of $121 billion

https://en.wikipedia.org/wiki/Troubled_Asset_Relief_Program

If Taiwan becomes practically inaccessible, is there any way another country can setup a competing fab (for the latest generation of chip sizes) without years of R&D? As far as I understand, the practical knowledge of how to do it doesn't exist right now. (Neither does the prerequisite tooling)