luke_cq

I desperately want to be able to get a concrete amount of tokens for my prompt before making a call - things like this make it very hard to request the right amount of max_tokens from longer prompt/generation pairs.

In fact, it's SO knowledgeable, that if you tell it to talk in the accent and slang of people from Sigil, the feature city in the Planescape D&D Setting from the 90s, it will perfectly adopt the character.

Does anyone have any data on how much use Morse Code still gets today? Are there any people still using it actively for communication, or are there literally zero practical applications anymore?

Really interesting, I appreciate Neil writing more about the process and philosophy than simply "we are banning AI tools."

As these models improve, I'm skeptical that we'll be able to differentiate human-written works from an edited work generated by a skilled LLM operator. It's already trivial to generate fiction content that scores as "100% human" on analysis tools.

However, sci-fi short stories are a particularly interesting case - by their very nature they are about investigating uniquely human experiences by using speculation to amplify things humans think, feel, and experience. A machine can never do that wholesale. But, what about a machine in tandem with a human that is articulating how they feel, and a premise?

I think what we're going to see is that all the small startups going for big, broad ideas ("we do AI writing for anything", "your one-stop marketing content automation platform", etc) are going to flat out lose to the big companies. I predict that the startups we'll see survive are the ones that find tight niches and solve for prompt engineering and UX around a very specific problem.

Congrats on the launch. I've been looking at Intercom and considering integrating it with our product, and I hadn't considered the issues you brought up. We're a B2C company, does that mean we aren't a good fit?