goopt2.xyz
Learning and science
ml text generation demo
SHOW HN2020
How HN took it
3 positive, 7 neutral or asking, 0 mixed, 2 critical, out of 12 comments about the project. Thread score 0.00.
Idea: 2 for, 0 againstExecution: 0 for, 1 againstDocs: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fun and funny; the Goop-versus-GPT-2 quiz is entertaining
From 2 comments
I can't believe how bad I am with this! It reminds me of the book "The Most Human Human." Every year, at the competition for the Loebner Prize (a five minute chatbot Turing…
elil17 on HNLooking at the site, and the authors comment, this looks like a quick weekend project made for fun. I wouldn’t spend too much time reading into it or critiquing it’s honesty. It…
avianlyric on HN
Good idea for crowdsourced labeling of data
From 1 comment
Brilliant work. The way you packaged it can be used to label data to improve ML models. I am thinking of such a link being sent out to numerous people to crowdsource labeling.…
r0b05 on HN
Objections
Quotes look cherry-picked, so the results are biased
From 2 comments
After trying a few to get a handle on things, I decided to make guesses based solely on if the sentence makes coherent sense. I judged 14 quotes before getting a repeat, having…
c3534l on HNHeavy curation is unfortunately rampant in the genre of "wow check out this AI"
woah on HN
Server was overloaded by HN traffic
From 1 comment
Hey everyone—looks like HN traffic squeezed my server a little more than I expected. It's upgrading now, but might not be available for about 5 minutes. Sorry about that, and…
calebkaiser on HN
Requests
Add more quotes to the quiz
From 1 comment
Hey HN -- I had a slow weekend and built this thing. It's a little game that displays a sentence, and you decide if you think an ML model generated it, or if it's an actual quote…
calebkaiser on HN
Publish a blog post on how it was built
From 2 comments
I would be interested in learning how you built it, do you have a blog entry about fine tuning the gpt-2 with the scraped text ? Or can you recommend a blog post that does…
bulldog13 on HNYes, very much so. Good luck and thank you!
bulldog13 on HN
Questions
How was the GPT-2 model fine-tuned?
From 2 comments
I would be interested in learning how you built it, do you have a blog entry about fine tuning the gpt-2 with the scraped text ? Or can you recommend a blog post that does…
bulldog13 on HNSee the notes and Colab notebook in the source project repo: https://github.com/minimaxir/gpt-2-simple I am working on a new text generation package which should be even more…
minimaxir on HN
Does it use common sense?
From 1 comment
Brilliant work. The way you packaged it can be used to label data to improve ML models. I am thinking of such a link being sent out to numerous people to crowdsource labeling.…
r0b05 on HN
Alternatives named
SNARXiv (snarxiv.org), a parody of arXiv
From 1 comment
Very similar: http://snarxiv.org/vs-arxiv/
martopix on HN
MAD Magazine catalog parodies
From 1 comment
This reminds me of the time that MAD Magazine did parodies of entries in the old Spencer Gifts catalogs.
DrScump on HN