|
Sagebrush posted:GearVR! Try it on your face! *makes jerking off motion* Eventually!
|
# ? Sep 30, 2016 03:39 |
|
|
# ? May 9, 2024 22:04 |
|
Captain Foo posted:*makes jerking off motion* Eventually! *claps yosposly*
|
# ? Sep 30, 2016 03:50 |
|
Snapchat A Titty posted:*claps yosposly*
|
# ? Sep 30, 2016 03:50 |
|
Captain Foo posted:*makes jerking off motion* Eventually!
|
# ? Sep 30, 2016 05:15 |
|
https://twitter.com/Markov_Carmack/status/782856521088573440 Markov Carmack getting spookier! PS, I added his .plan files from 1996-2010
|
# ? Oct 3, 2016 16:14 |
|
https://twitter.com/WYR_bot/status/783003788307202053 if only.........
|
# ? Oct 3, 2016 21:17 |
|
my girlfriend is Legos posted:https://twitter.com/WYR_bot/status/783003788307202053 I love this one.
|
# ? Oct 3, 2016 21:18 |
|
i'll give up the internet for life. when i can fly, i'll be so rich i'll hire someone else to do the internet for me
|
# ? Oct 3, 2016 22:24 |
|
"convert today's top ten trending gifs to bluray and have them in the player before I get in tomorrow, charles "
|
# ? Oct 3, 2016 22:36 |
|
or just, like, download them no one says you have to give up computers
|
# ? Oct 3, 2016 22:40 |
|
today my bot said "i was just raped" and i made an empathy noise automatically.
|
# ? Oct 3, 2016 22:48 |
|
WrenP-Complete posted:today my bot said "i was just raped" the gently caress seed file are you working from?
|
# ? Oct 3, 2016 22:55 |
|
theflyingexecutive posted:the gently caress seed file are you working from? i scraped posts of a libertarian who used to post here.
|
# ? Oct 3, 2016 22:57 |
|
Sagebrush posted:or just, like, download them i suppose although honestly it's gotten to the point where if the internet goes out i just look at my computer and go "what the gently caress does this thing even do"
|
# ? Oct 3, 2016 23:50 |
|
just noting that it's definitely worth re-training your RNN if you're using a dataset you can refine and expand; it's really weird seeing what appear to be minor incremental improvements become relatively large increases in certainty/"understanding" over time. originally sampling runs with the word-rnn temperature parameter set to something low like "0.5" would yield "would you rather yes or no" over and over, but now there's some nice variety - still safe/somewhat boring output, but the network is definitely getting a better handle on what sort of word sequences i consider good.
Crusader fucked around with this message at 18:05 on Oct 4, 2016 |
# ? Oct 4, 2016 17:58 |
|
theflyingexecutive posted:the gently caress seed modés
|
# ? Oct 4, 2016 18:51 |
|
Crusader posted:just noting that it's definitely worth re-training your RNN if you're using a dataset you can refine and expand; it's really weird seeing what appear to be minor incremental improvements become relatively large increases in certainty/"understanding" over time. originally sampling runs with the word-rnn temperature parameter set to something low like "0.5" would yield "would you rather yes or no" over and over, but now there's some nice variety - still safe/somewhat boring output, but the network is definitely getting a better handle on what sort of word sequences i consider good. are you training over the original weights? how is it getting feedback on what you consider good?
|
# ? Oct 4, 2016 20:09 |
|
atomicthumbs posted:are you training over the original weights? how is it getting feedback on what you consider good? yep - adding the twitter posts to the training corpus (since i strip out anything that's a match for a corpus line, which seems unnecessary with temperature=1) + re-crawling net sources for new material edit: originally i ran through a bunch of parameters through trial and error (net size, layers, optimization method, dropout rate) that i haven't revisited in a while since just adding more to the corpus has kept improving both qualitative output and the quantitative error rate, but will probably go back and see if there's any gains to be made by tweaking those again Crusader fucked around with this message at 20:28 on Oct 4, 2016 |
# ? Oct 4, 2016 20:18 |
|
Crusader posted:yep - adding the twitter posts to the training corpus (since i strip out anything that's a match for a corpus line, which seems unnecessary with temperature=1) + re-crawling net sources for new material oh, so you're adding its own (curated) input back into the training too? that's cool as hell
|
# ? Oct 4, 2016 21:30 |
|
those arent markov boots but pretty cool imo they trained a thing to generate animated frames, either from scratch or from a static image e:they have a cronenberg training set unpacked robinhood fucked around with this message at 11:05 on Oct 5, 2016 |
# ? Oct 5, 2016 11:00 |
|
Crusader posted:yep - adding the twitter posts to the training corpus (since i strip out anything that's a match for a corpus line, which seems unnecessary with temperature=1) + re-crawling net sources for new material Crusader, we are on the exact same page with what we are doing. I read your post and then checked to see if I was you.
|
# ? Oct 5, 2016 11:17 |
|
unpacked robinhood posted:those arent markov boots but pretty cool imo this is pretty sweet
|
# ? Oct 5, 2016 16:03 |
|
https://twitter.com/WYR_bot/status/783728612285509632 https://twitter.com/WYR_bot/status/783819224582090752 https://twitter.com/WYR_bot/status/783773918503047168 i love u wyrbot
|
# ? Oct 6, 2016 09:59 |
|
Wyrbot is on a gold streak. https://twitter.com/WYR_bot/status/783366169503891462 https://twitter.com/WYR_bot/status/783411475264200706 https://twitter.com/WYR_bot/status/783139643722194944
|
# ? Oct 6, 2016 10:13 |
|
those are all ridiculously good
|
# ? Oct 6, 2016 11:19 |
|
https://twitter.com/WYR_bot/status/784226775077363716 MIKE TYSON'S CLOWN UNIVERSE
|
# ? Oct 7, 2016 05:21 |
|
Synthbuttrange posted:https://twitter.com/WYR_bot/status/784226775077363716 moooooooods
|
# ? Oct 7, 2016 07:57 |
|
rename yospos to mike tyson's clown universe imo
|
# ? Oct 7, 2016 08:07 |
|
Trig Discipline posted:rename yospos to mike tyson's clown universe imo
|
# ? Oct 7, 2016 08:10 |
|
|
# ? Oct 7, 2016 08:35 |
|
wyr_bot finally is sentient
|
# ? Oct 7, 2016 09:04 |
|
Mike Tyson clown universe!!!
|
# ? Oct 7, 2016 12:57 |
|
I'm naming this R work environment Mike Tyson's clown universe. (The last one was named meatspace)
|
# ? Oct 7, 2016 13:02 |
|
mods please rename yospos "mike tyson's clown universe"
|
# ? Oct 7, 2016 13:05 |
|
Yospos is Mike Tyson's clown universe!!! Mods please rename!
|
# ? Oct 7, 2016 13:07 |
|
the more i think about it, the more im convinced that this forum is like if mike tyson ran the universe, but everyone in it was clowns
|
# ? Oct 7, 2016 13:20 |
|
also a sound "mods" from here
|
# ? Oct 7, 2016 15:03 |
|
modsmodsmods
|
# ? Oct 7, 2016 16:09 |
|
WrenP-Complete posted:Yospos is Mike Tyson's clown universe
|
# ? Oct 7, 2016 16:10 |
|
|
# ? May 9, 2024 22:04 |
|
anthonypants posted:http://www.9news.com.au/technology/2016/10/06/15/32/japanese-ai-bot-with-the-personality-of-teen-develops-depression lmao there's some folk in japan that could use your help...
|
# ? Oct 7, 2016 19:25 |