Re:Show HN: Parrot.vc – I forced a bot to read 65,000 VC twe...
by smacktoward on Wednesday December 04, 2019 @08:14PM
(#21709066)
Is the source code available anywhere? I’ve been mulling over a similar project but don’t have a lot of ML experience myself, would be great to look at the innards of a working example...
Re:Show HN: Parrot.vc – I forced a bot to read 65,000 VC twe...
by pequalsnp on Wednesday December 04, 2019 @09:19PM
(#21709390)
An easy way to get started that doesn't use pure ML is Markovify [1]. I used it for a couple of projects last year.
Re:Show HN: Parrot.vc – I forced a bot to read 65,000 VC twe...
by rpvnwnkl on Wednesday December 04, 2019 @09:18PM
(#21709385)
This blog post and associated github give a good enough intro to get simple examples working: http://karpathy.github.io/2015/05/21/rnn-effectiveness/
Re:Show HN: Parrot.vc – I forced a bot to read 65,000 VC twe...
by nloui on Wednesday December 04, 2019 @09:42PM
(#21709527)
I may open source it. It's pretty easy to get started if you leverage pre-existing libraries for Markov chains and Twitter ingestion.
Re:Show HN: Parrot.vc – I forced a bot to read 65,000 VC twe...
by tlrobinson on Wednesday December 04, 2019 @10:59PM
(#21709860)
Now do it with Hacker News comments!
Re:Show HN: Parrot.vc – I forced a bot to read 65,000 VC twe...
by umvi on Wednesday December 04, 2019 @11:35PM
(#21710017)
"In other news, water is wet"
"This has been known for 10 years, this is not a new discovery"
"Title is clickbait, can someone please update it?"
Gavin Belson - hit me up, this is the perfect acquisition for Hooli.
PS - you can follow Parrot.vc on Twitter as well (https://twitter.com/parrot_vc)