Nithum

[Nithum @Nithum]

Check out our most recent Explorable "Can Large Language Models Explain Their Internal Mechanisms?"

https://t.co/GQ6v9ZptAE

[Google AI @GoogleAI]

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

[Google AI @GoogleAI]

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

[Adam Pearce @adamrpearce]

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

[iislucas (Lucas Dixon) @iislucas]

Some of my thoughts on generative AI... and a reboot of the PAIR blog...

https://t.co/lTE67mhDDL

#responsibleai #hci #machinelearning #GenerativeAI

[Adam Pearce @adamrpearce]

Confidently Incorrect Models to Humble Ensembles by @Nithum, @balajiln and Jasper Snoek

https://t.co/JNVYLq1Bib

[Nithum @Nithum]

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

[Andy Coenen @_coenen]

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

[Adam Pearce @adamrpearce]

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

[TensorFlow @TensorFlow]

🤔 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

[Nithum @Nithum]

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

[Martin Görner @martin_gorner]

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 🤬!

[Martin Görner @martin_gorner]

@Devoxx My co-speaker for this session will be @Nithum from Google @JigsawTeam. He fights bad behavior online with neural networks.

[Martin Görner @martin_gorner]

"Tensorflow and deep learning without a PhD" continues @Devoxx on Monday 9:30. Deep learning novices welcome, fresh neurons required :-)

[Sean Mullin @MullinSean]

Awesome work by @adamscj and @nithum! https://t.co/3X2a61Esjl via @WIRED

[Jigsaw @Jigsaw]

Introducing Perspective, using machine learning to improve discussions online. https://t.co/XsZS0F5q9I

[Jigsaw @Jigsaw]

We collected and labeled over 1 million @Wikimedia page edits to determine where personal attacks were made. https://t.co/TPOFG15y0C

[Jigsaw @Jigsaw]

How can we keep extremists from using technology to cause harm? @POTUS and @WIRED asked our very own @yasmind. https://t.co/eTdlcIX9qO

[Nithum @Nithum]

@HitchTheKitch Are you guys open tomorrow? Where will you be?

[Amy Zhang @amyxzh]

Wikipedia building n-gram models to detect personal attacks and harassment: https://t.co/V1rJns5WRN https://t.co/wPQdqf62AU