• HLStatsX:CE Update: We've narrowed down some of the bottlenecks affecting HLStats and it appears to be performing significantly better now - we'll continue monitoring and tuning things over the next little while. ~VintagePC

Shoutbox Archive Thread (slow Load - Long Posts)

Status
Not open for further replies.
it's a bit more complicated then that. Essentially, for each word in the dictionary, you have a table of probabilties for every other adjacent word in your dataset. Then you pick a starting word (prompt) and walk forwards and backwards through the table, picking the next word(s) based on their probabilities
 
by "the dictionary" I mean the internal dictionary in the dataset, not every word ever
 
that concept has been around for years and is stupidly simple to implement (I think Vaultbot is like 300 lines of PHP)
 
it's only recently that people have figured out how, and that we have the computing power to feed these things massive datasets and get really, really coherent (if sometimes hallucinatory and wrong) responses
 
and of course there's only a finite number of words in the language whereas of course you have a lot more possible choices when combining words to make a sentence
 
like you can build these chains out of anything with the right dataset
 
Status
Not open for further replies.

Funding Progress To Date

Our Servers

VaultF4 on Steam


48898 Members
(9856 Online 970 In-Game)
Join the group
Back
Top Bottom