[malikNF]

> Please if you want to send me a message and feel compelled to use GPT, please just send me whatever you wrote in your prompt instead. I promise I will still read it!

Best bit of the article.

Question for someone who knows more about this stuff. How likely is it to get the same response to the same prompt with gpt ? Does it have some kind of random seed applied behind the scenes?

-edit- Thank you for the responses. TIL.

[maccam912]

There is a parameter called "temperature" that determines randomness. I think there is never a guarantee of the same response, but generally with a low temperature (something like 0.0, the lowest but still not deterministic) I get nearly identical responses, if not actually identical. When temperature is increased though to e.g. default of 1.0 or max of 2.0, the same prompt will give very different responses. The higher the temperature the more creativity that is injected because of the randomness, but also the less determinism.

[ymck]

Honestly, as someone who does this, Bard seems to be much better at writing natural emails. It's just easier to dump some thoughts in to bard and ask it to redraft, then fluff it a little to sound like me.

[hobo_in_library]

Bard may have gotten to train on the entire Gmail corpus

[gkoberger]

It's not a random seed, but it will always be slightly different. It's similar to "prompting" a human... you'll likely get the same general result if you ask the same person the same question a dozen times, but it will have enough variability that it won't be identical.

[thefreeman]

Pretty sure this is entirely dependent upon the "temperature" parameter used when inferring. The higher the temperature the more uniform the response will be.

[drusepth]

Quick fix: the higher the temperature, the more varied the potential responses. For uniform responses, you want the lowest temperature.

[thefreeman]

Oof. I was worried I was going to mess that up.

[low_tech_love]

It's certainly not in any way whatsoever similar to "prompting" a human. And yes there are definitely random processes involved. For an extremely objective prompt you may get very similar results but for general stuff like "write an e-mail about this or that" it will be significantly different each time.

[gkoberger]

Sure, but it's not like they're intentionally randomizing it. You can set parameters (like temperature or penalties), but it's not intentionally randomizing things.

[groestl]

"I promise I will still read it!"

You might read it, but you won't answer the same way as you do when "choose a nice wording." was added to the prompt.

[BlackLotus89]

And how is that? Slightly annoyed?

[et-al]

Seriously. We're going to have ChatGPT inflate content, then readers will use AI summarizers to distill it.

Seems like we should all just be communicating via bullet points grug or Kevin Malone style.

[i2cmaster]

Brevity will be valued once again.

[lannisterstark]

>Best bit of the article.

"Tell the person that he's being an idiot asking me to turn on my cameras during the meetings but be subtle about it, I don't want to offend them."

That'll work.