It seems we agree on the facts, but not on what “useful” or “helpful” means. I honestly have never, ever considered deciding on what food to serve guests be “labor”, but in the interests of replying in good faith I asked an LLM the exact prompt you gave. It gave a long, detailed reply, but here is the first part labeled “1. Welcome / Cocktail Reception”:

Mini prosciutto‑wrapped melon balls • Brie & caramelized onion tartlets (store‑bought puff pastry) • Stuffed mushroom caps (herb cream cheese + breadcrumbs)

I want you to consider that this not actually helpful in the slightest, and is fact creating more work. Consider: is there a vendor nearby that has these items as an an option for event planning? Is this a recipe that even exists? Does this information further my mission of having a wedding in any conceivable way?

Or Perhaps:

• They have a large corpus of context files to help with all aspects of how the output is generated
• They’re using a model with specialised fine tuning for the task attempted
• They have a series of MCP servers with access to relevant tooling available
• They have many many hours of prior experience with the setup and usage of such tools
• They used multiple tools manually and pulled the bits they needed
• They just said “Make me a thing” and it just worked like magic

they mention reinforcement learning, pre-training and other general LLM concepts, but none of these are related back to the tasks they are talking about.

The point is, there was no explanation of how any of this was achieved, which can lead to confusion about what was actually achieved.

The LLM wrote some docs vs the LLM rewrote the library from end to end are very different things.

It’s very much a “Don’t give up on X, look at what can be achieved” but without any actual details on what is required to achieve those results.