[abetlen]

I would add the following two numbers if you're generating realtime text or speech for human consumption:

- Human Reading Speed (English): ~250 words per minute

- Human Speaking Speed (English): ~150 words per minute

Should be treated like the Doherty Threshold [1] for generative content.

[1] https://lawsofux.com/doherty-threshold/

[skykooler]

Human reading speed varies by a factor of 10 or more between individuals, while speaking speed is much more consistent.

[fritzo]

Even my own reading speed even varies by a factor of 5 day to day, depending on how much reading I've been doing, sleep I've gotten, etc.

[irrational]

Plus, whether I am reading light fiction versus technical documentation.

[JohnFen]

> speaking speed is much more consistent.

Is it? I've noticed a huge variance in speaking speed in the US, but it tends to vary more between regions rather than individuals.

[telesilla]

Exceptions for languages where rapidity of speech really varies according to context, such as in Spanish.

[armchairhacker]

But I'd say LLMs produce content faster than I can read or write it, because they can produce content which is really dense.

Ask GPT-4 a question and then answer it yourself. Maybe your answer will be as good or better than GPT-4's but GPT-4 writes its answer a lot faster.

[furyofantares]

It certainly doesn't produce content as fast as I can read it.

[renonce]

Only if you use gpt-4. gpt-3.5-turbo is much faster, and gpt-4 is only going to get faster as GPUs get faster.

[furyofantares]

Yep. I use GPT-4 extensively and exclusively, and the comment I was replying to mentioned GPT-4. I can't wait for it to get faster.

[cubefox]

Bing also uses GPT-4 and it is very fast. Microsoft spends more ok compute.

[furyofantares]

It doesn't exclusively use GPT-4, you might be right anyway that their GPT-4 is much faster but you're also not always seeing GPT-4 with them.

[cubefox]

I'm pretty sure it at least mostly uses GPT-4.

[darknoon]

afaict OpenAI's instance is massively overloaded, you can see with the 32k context model actually being faster in practice rather than slower

[bombolo]

dense content? Not in my experience. It seems to be really overly verbose for me.

[Tostino]

Prompt it to be information dense in its response then.

[bombolo]

So I must specifically ask for it, but it's not at all the default.

[Tostino]

I get it, but it is just about infinitely configurable to your specific needs so it doesn't bother me too much what the default response is.