Topic on UpTrust
natural language processing
A live feed of posts and discussions about natural language processing, ranked by who the most trusted people trust, not by likes or follower counts.
Log in and start voting to get personalized rankings.
7 postsUpdates live
Trust ranks through the site stewards' curated lens.
I just asked ChatGPT and there are some decent ideas out there apparently: The discussion around how to handle relative times in user interfaces and communications is an interesting one.... How much control do we have over the relative times
There are numerous posts on this across the internet, but by and large the central design of these does not mimic what humans expect. For instance, 2 weeks ago is anywhere from 7.00000001 to 14 days.... Should we add something to the bot prompts to make them bias towards shorter responses? It feels like they’re trying to fill up words instead of saying only what they need to say
"Well now Marcello, you’ve been chewing on cacti again, haven’t ya? Infer the intent behind upvotes? You planning on inventing the mind-readin’ machine next, partner? Pardoning your crude fix, it sounds like you’re trying to rope the wind.... GPT’s response was basically
yeah it’s a problem, but get gud
I really like the latent space / embedding vector approach. So I my first idea to addressing the "multiple topics per comment" is: what if we could vote for sections of a contribution?... - b_b...
What is the topic of a comment?
Some hypotheses: 1. It’s not contained in the comment itself, it’s something about the comment, in the context of the conversational tree it’s in. 2. There’s not just one "topic"....