[steelframe]

Here is that same exchange with paid Kagi Assistant using Claude 3.5 Haiku:

Me: Who is Trump's paternal grandpa?

Based on the available information, Frederick Trump is Donald Trump's paternal grandfather. Here are some key details about him:

Born as Friedrich Trump on March 14, 1869, in Kallstadt, Germany (then part of the Kingdom of Bavaria).

He immigrated to the United States in 1885.

He was a German-American businessman who amassed considerable wealth during the Klondike Gold Rush by running a restaurant and brothel for miners.

In 1901, he returned to Kallstadt and married Elizabeth Christ the following year.

He is considered the patriarch of the Trump family.

He passed away on May 30, 1918.

Interestingly, the Trump last name has been recorded in Kallstadt since the 18th century, and Frederick Trump is credited with being the founder of the family's initial fortune.

Me: Who is Trump's maternal grandpa?

Based on the provided information, Malcolm MacLeod (also spelled Calum MacLeod) is Donald Trump's maternal grandfather. He was born on December 27, 1866, in Stornoway on the Isle of Lewis in Scotland

While the information provided is limited, it confirms his identity and place of birth. Unfortunately, the passage does not provide additional details about his life or occupation.

---

That looks pretty good to me. Of course Kagi's strategy seems to be to retrieve search results first and then bias the LLM with those results. The LLM then parses, distills, and contextualizes the answer in a succinct and easily-consumable manner. In my opinion this is The Way to go about doing it at the moment.

[iamnotagenius]

RAG works well no one argues, but using RAG completely defeats the purpose of LLMs as their primary goal is to be a smart creative, not a simple summarizer.

[steelframe]

I'd like to take a dig into this notion of "purpose" and "primary goal." To me, LLMs are a phenomenon. They have not intrinsic purpose or goal -- they just are.

Purposes and goals come from you and me. An LLM is a tool, and we get to decide what the tool is good for or how to use it.

If you want "a smart creative," there's nothing wrong with that. It's as good a purpose or goal as any.

However for me I don't want an LLM to try to be "a smart creative." I instead want it to give me cold, hard facts in precisely the format I want them, in precisely the context I am interested in, and with precisely the conciseness that I require to make a specific decision or learn a specific thing. Traditional web search can eventually get me what I want, but I have to sift through the cruft and make associations among a plethora of content to get to the meat of what I want.

I've found that using a good web search (Kagi) together with an LLM processing the results has given me information I needed and then pointed to the sources so I can validate those statements. I wouldn't exactly characterize those results as a "simple" summary. They're usually synthesizing a variety of sources to generate something that no one source had, exactly.