> There is actual research suggesting concise prompting can reduce response length substantially without always wrecking quality,
Anecdote: i discussed that with an LLM once and it explained to me that LLMs tend to respond to terse questions with terse answers because that's what humans (i.e. their training data) tend to do. Similarly, it explained to me that polite requests tend to lead to LLM responses with _more_ information than a response strictly requires because (again) that's what their training data suggests is correct (i.e. because that's how humans tend to respond).
TL;DR: how they are asked questions influences how they respond, even if the facts of the differing responses don't materially differ.
(Edit: Seriously, i do not understand the continued down-voting of completely topical responses. It's gotten so bad i have little choice but to assume it's a personal vendetta.)
But that response is grounded in the training data they've seen, so it's not entirely unreasonable to think their answer might provide actual insights, not just statistical parroting.
What do you mean? It is grounded on the text it is fed, the reason it said that was that humans have said that or something similar to it, not because it analyzed a lot of LLM information and thought up that answer itself.
LLM can "think" but that requires a lot of tokens to do, all quick answers are just human answers or answers it was fed with some basic pattern matching / interpolation.
this continual down-voting is not a personal thing for sure. perhaps there are crawlers that pretend to be more humane, or fully automated llm commenters which also randomly downvote.
Does this not also create a single point of data for thieves wanting to know where the best bikes can be found? One tiny data breach, or one disgruntled employee, and all those address/bike combinations are on the dark web?
The address optional. So no its not required to provide your address.
Also that's not a non zero chance there are people like this but honestly, whos gonna get on a plane in today's economy, fly to some random place, break in to someone ones house all over a what is on average a $2k bike. IDK risk vs reward seems a little crazy to me.
> - if you have trouble with nose breathing like me, use Nose strips (that helps for me)
Just to clarify your intent there: do mean you _must_ breathe through your nose or that you _must_not_ breathe through your nose? (And what on earth is a Nose Strip?)
If this requires mouth-breathing, it's a non-starter for me :(. (Radiation treatment deleted many of my salivary glands, so my mouth dries out, to a painful degree, very quickly, when breathing through my pie hole.)
Nose strips are springy things which hold your nostrils / nasal passages a bit further open. In context, it appears GP means that nose breathing is expected. Sorry about your medical issue; I hope you had a good result.
- Programming and/or documenting personal projects
- Tabletop games, though probably 90% of this means either tinkering with games (as opposed to playing them, e.g. creating inserts or new pieces for them) and/or hanging out on BoardGameGeek dot com.
- Reading, mostly anthologies of fiction from Wildside Press which collect many works from the early/mid 20th century, purchasable DRM-free for $1-2 each (for anywhere from 300 to 1500 pages). (Not associated with them, but am a long-time happy customer.)
FWIW: as someone who's been doing this since before the term "Open Source" was coined, i find this article to be both enlightening and insightful, cataloguing a wide range of diverse definitions/connotations of the term.
Anecdote: i discussed that with an LLM once and it explained to me that LLMs tend to respond to terse questions with terse answers because that's what humans (i.e. their training data) tend to do. Similarly, it explained to me that polite requests tend to lead to LLM responses with _more_ information than a response strictly requires because (again) that's what their training data suggests is correct (i.e. because that's how humans tend to respond).
TL;DR: how they are asked questions influences how they respond, even if the facts of the differing responses don't materially differ.
(Edit: Seriously, i do not understand the continued down-voting of completely topical responses. It's gotten so bad i have little choice but to assume it's a personal vendetta.)
reply