Twitter | Pretraživanje | |
Pretraživanje Osvježi
Thang Luong 18 h
About data (asked by & others): 1. Only one occurrence of "Hayvard" in the training data. 2. The sentence that contains "Hayvard" has meaning similar to "Guess what, I obtained my bachelor from Hayvard." 3. No occurrence of "cow*" in the same conversation.
Reply Retweet Označi sa "sviđa mi se"
Thang Luong 31. sij
I chatted with about the and her advice is to see a doctor sooner rather than later. I guess it's not a bad one & hope everyone is well! On the other hand, Meena is also excited about technology, especially VR!
Reply Retweet Označi sa "sviđa mi se"
Thang Luong 4. velj
Odgovor korisniku/ci @an_open_mind @quocleix
If this is about , totally understand the sentiment & we are working hard on making sure the community can verify & reproduce. Our research (cc ) has always been very open whenever we can. Btw, conversations here are not cherry picked :)
Reply Retweet Označi sa "sviđa mi se"
Giorgio Robino 23 h
🤭Wow! A true power-saving/green economy successful example of embeddable software! NO! 🥴Huston, we have a problem. An huge computational problem, actually, a linguistic problem, actually, a paradigmatic problem, (with this kind of deeplearning applications)
Reply Retweet Označi sa "sviđa mi se"
Markus Glas 1. velj
Ingredients for a human-like open domain chatbot: 341GB conversation data, 2.6 billion parameters, 2048 TPU Cores and 30 days training time🤯
Reply Retweet Označi sa "sviđa mi se"
Giorgio Robino 4. velj
I'm perplexed by excitements about overrated ask: "Could this become a conversation engine behind at some point?" My thoughts:
Reply Retweet Označi sa "sviđa mi se"
Giorgio Robino 4. velj
weakeness: 1. comparison with @mitsokubot and Cleverbot is misleading. Apples and oranges! is a great scripted chatbot made by a single human author (Sir Steve Warswick). is an old useless game. 2. is not available for peers reviews.
Reply Retweet Označi sa "sviđa mi se"
YourStoryHindi 3 h
की अधिकता के साथ के और के से भरे क्षेत्र में अपना Chatbot लॉन्च करने की तैयारी में है 👇
Reply Retweet Označi sa "sviđa mi se"
Stefanus Hinardi 18 h
Odgovor korisniku/ci @lmthang @GaryMarcus
Would you consider that was able to come up with a novel pun? It would also be interesting to see where the bot is trying to make a pun, but fails to do so
Reply Retweet Označi sa "sviđa mi se"
Andrew Kangpan 20 h
I found out today that a chatbot can make better jokes than I can 😩
Reply Retweet Označi sa "sviđa mi se"
#AboveAndBeyond 4. velj
Odgovor korisniku/ci @GoogleAI @quocleix @lmthang
Not fully convinced, looking forward to whats next Thank you for sharing your research.
Reply Retweet Označi sa "sviđa mi se"
Ali Khanafer 4. velj
Gotta have respect for for calmly answering to critiques in such open platform. I would have gotten agitated wafter reading 5 anonymous reviews of my paper 😅
Reply Retweet Označi sa "sviđa mi se"
Jerome Pesenti 4. velj
Odgovor korisniku/ci @lmthang @quocleix
Thanks . Great to hear the commitment to . Claims asides, is really impressive work. Congrats!
Reply Retweet Označi sa "sviđa mi se"
Marco Mascorro 4. velj
Odgovor korisniku/ci @lmthang @an_open_mind @quocleix
Congrats on the work with , is there an API where I could use it? (sorry if this was published somewhere but I couldn't find it)
Reply Retweet Označi sa "sviđa mi se"
Botomation.io 3. velj
Google’s New Meena Chatbot Imitates Human Conversation and Bad Jokes
Reply Retweet Označi sa "sviđa mi se"
The Panoply 3. velj
Just how big a deal is Google’s new Meena chatbot model? CTO of writes for
Reply Retweet Označi sa "sviđa mi se"
Ami science prospect 3. velj
Reply Retweet Označi sa "sviđa mi se"
RitaJVarga 2. velj
Google’s here to stay and hit the floor
Reply Retweet Označi sa "sviđa mi se"
Steven Engravalle 2. velj
Reply Retweet Označi sa "sviđa mi se"
Stuart Pearson 2. velj
Reply Retweet Označi sa "sviđa mi se"