WTF-Beta

@Axtremus

I cannot even imagine trying to write up the budget sheet for $400 million.... yikes!

Here’s a personal AI fail. In the fall, I applied for an external grant (budget $400,000) to do an elaborate, multi-year AI research study. I didn’t even get past the internal competition.

That’s ok, I knew it was a long shot.

Looks interesting! What kind of guitar do you have and what kind of guitar music do you want to learn/play?

I played guitar on and off starting in high school, including classical, folk, acoustic and electric. I was playing classical guitar (and not progressing at all) in my late-20s when someone lent me a stage piano (really nice but highly portable Yamaha with weighted keys and sustain pedal). I started teaching myself how to play piano and immediately fell in love with piano. I switched to piano and never looked back. At the time, I remember feeling like piano was waaay easier than guitar. Now I’m not so sure.

But I’ve always had a soft spot for guitar nevertheless

Ick

Vu ja de

@wtg OMG I forgot all about that!!!

déjà vu

Cry

Finder

Boot

Odyssey

Ground

That’s great!

Whole

@wtg said:
I was like WTF?

@CHAS oh dear, that must have been terrifying! I'm glad you're both ok!

@wtg wow!! That’s a lot of drama, and a lot of noise, to then still be able to have that morning coffee. I’m not confident we would have the same positive experience here!

Acorn

I have read about tokens before, and one of the problems is that the definition of a token is pretty fluid (as far as I can tell) and not only is it inconsistent across platforms, it’s inconsistent within the same platform. So it’s not like character count or word count, where the user could monitor their token use with 100% accuracy.

From @axtremus ’s article:

Tokens represent a unit of output, either in text or image, from an LLM. For the Ask Sage tool, a single token equates to about 3.7 characters, according to documents viewed by WIRED

From OpenAI (https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them)

Spaces, punctuation, and partial words all contribute to token counts. This is how the API internally segments your text before generating a response.

One thing that makes it particularly hard to monitor token usage is that the same amount of text could be interpreted as different amounts of tokens, depending on how it’s entered. At least, that’s according to what I’ve read, and the OpenAi article recommends to “break large text into smaller chunks” if you exceed your token limit.

So what does a “chunk” mean? Does that mean that the same prompt content would be interpreted as fewer tokens if you entered it little by little, rather than all at once? It would seem so, but that doesn’t make sense to me.

innocence