The Killer Use Case for LLMs Is Summarization

The killer use case for large language models (LLMs) is clearly summarization. At least today, in my limited experience, LLMs are incapable of generating unique insights. While LLMs are good at writing creatively regurgitated text based on certain inputs or writing generally about a topic, they’re unlikely to “think” something unique. However, LLMs appear to be quite good at knowing what they do and don’t know, and this is especially true when they are provided with a clear chunk of information or text to summarize.

Thoughts on Change in Liminal Space

Begin. I’m going to experiment with free writing for the first time in a long time. I’m in the back of an Uber right now and it’s not that I don’t want to talk to the driver, it’s just that I’m not in a huge talking mood right now. For that reason, I’m going to experiment with free writing in this altered state of consciousness… We’ll see how it goes.

It's Her.

Some women are… you know, they’re fine. They’re gorgeous and beautiful and smart and they’ve got everything. But they don’t have it. And it’s just… well, I have no idea what it is. It’s just there. And I know it. And she knows it. And she has it. And it’s something there, something under the surface, something sparkling, something that dances around like little crystalline packets of icy snow when they bounce off the ice and skitter all around and shine a thousand twinkling light beams through the aether.

Nostalgia Is a Toxin

Childhood — oh, you are the great universal. You bound me into who I am today, but you are just a shell — I had to shed the dreams you enthralled me with to writhe away from your grasp. That boundless freedom of having every option was a prison all the same, and I knew it. But I miss you still, and sometimes I wonder… Have you forever slipped away from my reach?