Nithum
@Nithum
Followers
246
Following
25
Media
0
Statuses
31
Joined April 2009
Check out our most recent Explorable "Can Large Language Models Explain Their Internal Mechanisms?" https://t.co/GQ6v9ZptAE
pair.withgoogle.com
An interactive introduction to Patchscopes, an inspection framework for explaining the hidden representations of large language models, with large language models.
0
0
7
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 → https://t.co/mvmix9hKs0
17
149
575
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. → https://t.co/Okc9GvJjuN
38
474
2K
Do Machine Learning Models Memorize or Generalize? https://t.co/Ln3xIZhKLs An interactive introduction to grokking and mechanistic interpretability w/ @ghandeharioun, @nadamused_, @Nithum, @wattenberg and @iislucas
21
245
1K
Some of my thoughts on generative AI... and a reboot of the PAIR blog... https://t.co/lTE67mhDDL
#responsibleai #hci #machinelearning #GenerativeAI
medium.com
Back in 2017, we announced the launch of PAIR by stating, “We believe AI can go much further — and be more useful to all of us — if we…
1
1
13
Confidently Incorrect Models to Humble Ensembles by @Nithum, @balajiln and Jasper Snoek https://t.co/JNVYLq1Bib
1
7
30
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. https://t.co/GkO5tMseoo
pair.withgoogle.com
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.
0
0
2
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. https://t.co/D3KK8DM1Lo
wordcraft-writers-workshop.appspot.com
The Wordcraft Writers Workshop is a collaboration between Google's PAIR and Magenta teams, and 13 professional writers. Together we explore the limits of co-writing with AI.
3
16
49
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. https://t.co/qRHqbJ2VNL
0
27
65
🤔 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 → https://t.co/k1MbtojO9T
0
17
62
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. https://t.co/5fS21WM23A
pair.withgoogle.com
Machine learning models express their uncertainty as model scores, but through calibration we can transform these scores into probabilities for more effective decision making.
0
32
118
Beautiful "RNN with attention" tutorial from one of the authors of Google's troll-fighting AI @Nithum. https://t.co/82bVY0wcEZ. We presented this toxic comment detection model together in the "Tensorflow and modern RNNs without a PhD" talk. Excuse our French 🤬!
0
14
35
@Devoxx My co-speaker for this session will be @Nithum from Google @JigsawTeam. He fights bad behavior online with neural networks.
1
1
4
"Tensorflow and deep learning without a PhD" continues @Devoxx on Monday 9:30. Deep learning novices welcome, fresh neurons required :-)
4
56
104
Introducing Perspective, using machine learning to improve discussions online. https://t.co/XsZS0F5q9I
5
79
151
We collected and labeled over 1 million @Wikimedia page edits to determine where personal attacks were made. https://t.co/TPOFG15y0C
3
18
24
How can we keep extremists from using technology to cause harm? @POTUS and @WIRED asked our very own @yasmind. https://t.co/eTdlcIX9qO
1
25
34
Wikipedia building n-gram models to detect personal attacks and harassment: https://t.co/V1rJns5WRN
meta.wikimedia.org
https://t.co/jaAWVRpfVU: a demo of algorithmic classification of personal attacks on Wikipedia talk pages
1
3
4
Detecting personal attacks on Wikipedia: some context from the 2015 survey https://t.co/t1oQAYtZYQ
0
3
2