Check out our most recent Explorable "Can Large Language Models Explain Their Internal Mechanisms?"
pair.withgoogle.com/explorab…
7
183
Can large language models (LLMs) explain their internal mechanisms? Check out the latest AI Explorable on Patchscopes, an inspection framework that uses LLMs to explain the hidden representations of LLMs. Learn more → goo.gle/patchscopes
ALT A visual walkthrough of the patching process for explaining hidden representations of LLMs.
17
146
563
49,604
While large language models appear to have a rich understanding of the world, how do we know they’re not simply regurgitating from training data? Check out the latest AI Explorable on a phenomenon called grokking to learn more about how models learn. → goo.gle/45ohnQh
37
464
1,772
318,833
Nithum retweeted
7 Aug 2023
Do Machine Learning Models Memorize or Generalize?
pair.withgoogle.com/explorab…
An interactive introduction to grokking and mechanistic interpretability w/ @ghandeharioun, @nadamused_, @Nithum, @wattenberg and @iislucas
20
244
1,140
256,642
Nithum retweeted
5 Apr 2023
Some of my thoughts on generative AI... and a reboot of the PAIR blog...
medium.com/people-ai-researc…
#responsibleai #hci #machinelearning #GenerativeAI
1
1
13
1,453
Nithum retweeted
27 Mar 2023
Confidently Incorrect Models to Humble Ensembles by @Nithum, @balajiln and Jasper Snoek
pair.withgoogle.com/explorab…
1
7
30
3,922
ML models sometimes make confidently incorrect predictions when they encounter out of distribution data. Ensembles of models can make better predictions by averaging away mistakes.
pair.withgoogle.com/explorab…
2
74
Nithum retweeted
8 Dec 2022
In partnership with @GoogleMagenta, we invited 13 professional writers to use Wordcraft, our experimental LaMDA-powered AI writing tool. We've published all of the stories written with the tool, along with a discussion on the future of AI and creativity.
g.co/research/wordcraft
3
16
49
Nithum retweeted
9 Nov 2022
Most machine learning models are trained by collecting vast amounts of data on a central server. @nicki_mitch and I looked at how federated learning makes it possible to train models without any user's raw data leaving their device.
pair.withgoogle.com/explorab…
26
64
Nithum retweeted
27 Jun 2022
🤔 We've come a long way with #NLP, but what have language models actually learned?
Watch Senior Software Engineer at Google PAIR, Nithum Thain, discuss AI language model learnings → goo.gle/3HVtolv
16
58
Check out our new explorable on machine learning calibration:
Machine learning models express their uncertainty as model scores, but through calibration we can transform these scores into probabilities for more effective decision making.
pair.withgoogle.com/explorab…
32
118
Nithum retweeted
28 Sep 2018
Beautiful "RNN with attention" tutorial from one of the authors of Google's troll-fighting AI @Nithum. github.com/conversationai/co…. We presented this toxic comment detection model together in the "Tensorflow and modern RNNs without a PhD" talk. Excuse our French 🤬!
14
35
Nithum retweeted
5 Nov 2017
My co-speaker for this session will be @Nithum from Google @JigsawTeam. He fights bad behavior online with neural networks.
1
1
4
Nithum retweeted
4 Nov 2017
"Tensorflow and deep learning without a PhD" continues @Devoxx on Monday 9:30. Deep learning novices welcome, fresh neurons required :-)
4
56
103
Nithum retweeted
24 Feb 2017
2
1
Introducing Perspective, using machine learning to improve discussions online. bit.ly/2lIZEjS
5
81
149
We collected and labeled over 1 million @Wikimedia page edits to determine where personal attacks were made. bit.ly/2lgWfcB
3
17
24
Wikipedia building n-gram models to detect personal attacks and harassment: meta.m.wikimedia.org/wiki/Re… x.com/wikiresearch/status/75…
20 Jul 2016
wikidetox.appspot.com: a demo of algorithmic classification of personal attacks on Wikipedia talk pages
1
3
4
Nithum retweeted
20 Jul 2016
Detecting personal attacks on Wikipedia: some context from the 2015 survey meta.wikimedia.org/wiki/Rese…
3
2