Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

New Anthropic research: Emotion concepts and their function in a large language model. All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude’s behavior, sometimes in surprising ways.

Anthropic

1,441,575 subscribers

3,904,811 views • 2 months ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

Anthropic

1,570,545 views • 1 year ago

New Anthropic research: Natural Language Autoencoders. Models like Claude talk in words but think in numbers. The numbers—called activations—encode Claude’s thoughts, but not in a language we can read. Here, we train Claude to translate its activations into human-readable text.

New Anthropic research: Natural Language Autoencoders. Models like Claude talk in words but think in numbers. The numbers—called activations—encode Claude’s thoughts, but not in a language we can read. Here, we train Claude to translate its activations into human-readable text.

Anthropic

2,493,986 views • 1 month ago

This is how large language models turn objects to vector representations. In this video, we explore how large language models (LLMs) convert objects into internal representations, especially when translating between languages like English and Hindi. Using real-world examples, we highlight the challenges of gender inference, grammatical structure, and why direct word-to-word translations often fail. If you're curious about how LLMs deal with multilingual contexts and what it takes to improve translation quality across languages, this video is for you. #LLMs #Vectors #LCM

This is how large language models turn objects to vector representations. In this video, we explore how large language models (LLMs) convert objects into internal representations, especially when translating between languages like English and Hindi. Using real-world examples, we highlight the challenges of gender inference, grammatical structure, and why direct word-to-word translations often fail. If you're curious about how LLMs deal with multilingual contexts and what it takes to improve translation quality across languages, this video is for you. #LLMs #Vectors #LCM

Gaurav Sen

27,368 views • 1 year ago

The 72 concepts in the Red Bull model and related practices can be found at the link in the next post. We worked in the Red Bull model, and although the terminology can change slightly from manager to manager, the concepts remain the same.

The 72 concepts in the Red Bull model and related practices can be found at the link in the next post. We worked in the Red Bull model, and although the terminology can change slightly from manager to manager, the concepts remain the same.

Tactx

47,371 views • 1 year ago

What’s left w/ foundation models? We found that they still can't ground modular concepts across domains. We present Logic-Enhanced FMs:🤝FMs & neuro-symbolic concept learners. We learn abstractions of concepts like “left” across domains & do domain-independent reasoning w/ LLMs.

What’s left w/ foundation models? We found that they still can't ground modular concepts across domains. We present Logic-Enhanced FMs:🤝FMs & neuro-symbolic concept learners. We learn abstractions of concepts like “left” across domains & do domain-independent reasoning w/ LLMs.

Joy Hsu

48,289 views • 2 years ago

Today we introduce T-Free, a new paradigm in language processing. Tokenization is one of the core building blocks of large language models (LLMs), transforming natural language into numeric representations for further processing. (1/3) 🔗 #writtenbyalephalpha

Today we introduce T-Free, a new paradigm in language processing. Tokenization is one of the core building blocks of large language models (LLMs), transforming natural language into numeric representations for further processing. (1/3) 🔗 #writtenbyalephalpha

Aleph Alpha

18,096 views • 1 year ago

Sometimes in life it's really tough for everyone to hold their inner self and their true emotions because when they realized that the end is near... 🥹 We all can feel you GOAT 🖤

Sometimes in life it's really tough for everyone to hold their inner self and their true emotions because when they realized that the end is near... 🥹 We all can feel you GOAT 🖤

Friendly Wrestling

544,949 views • 1 year ago

Can we capture emotions in a few universal categories? This seems intuitive... but join this week's Inner Cosmos podcast with guest Lisa Feldman Barrett (Lisa Feldman Barrett) to find out why this textbook model of emotions is the wrong way to think about it. #brain #emotion

Can we capture emotions in a few universal categories? This seems intuitive... but join this week's Inner Cosmos podcast with guest Lisa Feldman Barrett (Lisa Feldman Barrett) to find out why this textbook model of emotions is the wrong way to think about it. #brain #emotion

David Eagleman

13,996 views • 1 year ago

🐹 “Normal” is about an emotion I can relate to. It is about the feelings behind the scenes of all the glamour. So we wanted to talk about those emotions. 🐹 For example, sometimes after our concerts, we can feel a kind of emptiness. 🐹 So we wanted to share those emotions and connect with people.

🐹 “Normal” is about an emotion I can relate to. It is about the feelings behind the scenes of all the glamour. So we wanted to talk about those emotions. 🐹 For example, sometimes after our concerts, we can feel a kind of emptiness. 🐹 So we wanted to share those emotions and connect with people.

jin files

222,779 views • 2 months ago

Artists on how (and why) they're using AI within their creative process. And how doing so can sometimes feel like learning A Whole New Language.

Artists on how (and why) they're using AI within their creative process. And how doing so can sometimes feel like learning A Whole New Language.

Runway

52,192 views • 1 year ago

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,572 views • 2 years ago

sometimes I watch in awe when exploring design concepts with AI still feels surreal that this is possible

sometimes I watch in awe when exploring design concepts with AI still feels surreal that this is possible

Ridd 🤿

45,667 views • 1 month ago

They didn’t have a lot of very dark concepts like ‘your idol’ but they always vocally carried.

They didn’t have a lot of very dark concepts like ‘your idol’ but they always vocally carried.

Ciera 씨에라 ⭐

133,999 views • 11 months ago

Normally, I would be dead against using leftist concepts and language to articulate right-wing arguments, but in the case of Henry Nowak, I think we have a clear exception.

Normally, I would be dead against using leftist concepts and language to articulate right-wing arguments, but in the case of Henry Nowak, I think we have a clear exception.

RAW EGG NATIONALIST

72,189 views • 16 days ago

Time for a new Qubic #Science Demo to understand better some of the many parameters we are recreating at the #Neuraxon BioInspired #TrueAI Model, that will run in the Qubic network with #aigarth Today a deep dive with the NeuroModulators, a fundamental piece of biochemistry that our brains need, and the #NeuraxonMoodMixer will help grasp the key concepts. You can play and learn with the demo here: Meanwhile we keep building the Science: And improving the Research Outcomes, all #OpenScience More updates on research comming soon, and more demos for other concepts the underlaying AI model uses.

Time for a new Qubic #Science Demo to understand better some of the many parameters we are recreating at the #Neuraxon BioInspired #TrueAI Model, that will run in the Qubic network with #aigarth Today a deep dive with the NeuroModulators, a fundamental piece of biochemistry that our brains need, and the #NeuraxonMoodMixer will help grasp the key concepts. You can play and learn with the demo here: Meanwhile we keep building the Science: And improving the Research Outcomes, all #OpenScience More updates on research comming soon, and more demos for other concepts the underlaying AI model uses.

David Vivancos - e/acc

26,217 views • 5 months ago

Should we design a new programming language for LLMs, that LLMs can use more efficiently? Chris Lattner, the creator of Swift and Mojo doesn't think so, and here's why: (cont'd)

Should we design a new programming language for LLMs, that LLMs can use more efficiently? Chris Lattner, the creator of Swift and Mojo doesn't think so, and here's why: (cont'd)

Gergely Orosz

15,416 views • 7 months ago

“Travis is a fierce competitor … sometimes in the heat of battle, emotions show. Sometimes we have confrontations, whether it’s with coaches or players, but I think it’s all out of competitive spirit.” Chris Jones on playing with Travis Kelce.

“Travis is a fierce competitor … sometimes in the heat of battle, emotions show. Sometimes we have confrontations, whether it’s with coaches or players, but I think it’s all out of competitive spirit.” Chris Jones on playing with Travis Kelce.

KC Sports Network

61,327 views • 8 months ago

What if your thoughts aren’t your own? Professors Elan Barenholtz and William Hahn propose that language is not a tool we use but a self-generating organism that uses us. In this mind-bending live discussion at the University of Toronto, they argue that language installs itself in our minds like software, runs autonomously, and shapes behavior at a deeper level than we realize. Drawing on LLMs, autoregression, and cognitive science, they suggest your brain may function like a predictive engine and that “memory,” “self,” and even “God” may just be tokens in an informational system.

What if your thoughts aren’t your own? Professors Elan Barenholtz and William Hahn propose that language is not a tool we use but a self-generating organism that uses us. In this mind-bending live discussion at the University of Toronto, they argue that language installs itself in our minds like software, runs autonomously, and shapes behavior at a deeper level than we realize. Drawing on LLMs, autoregression, and cognitive science, they suggest your brain may function like a predictive engine and that “memory,” “self,” and even “God” may just be tokens in an informational system.

Curt Jaimungal

52,269 views • 11 months ago

Swayman on yelling at the bench when he got pulled from Game 4: "We have an extremely high competitive group, and we all have a standard that we all carry ourselves to, and it wasn't met so that was just emotion." "You definitely pick and choose times that especially a goalie can show emotion, but we win as a team, we lose as a team."

Swayman on yelling at the bench when he got pulled from Game 4: "We have an extremely high competitive group, and we all have a standard that we all carry ourselves to, and it wasn't met so that was just emotion." "You definitely pick and choose times that especially a goalie can show emotion, but we win as a team, we lose as a team."

Bridgette Proulx

26,718 views • 1 month ago

We can teach LLMs to write better robot code through natural language feedback. But can LLMs remember what they were taught and improve their teachability over time? Introducing our latest work, Learning to Learn Faster from Human Feedback with Language Model Predictive Control

We can teach LLMs to write better robot code through natural language feedback. But can LLMs remember what they were taught and improve their teachability over time? Introducing our latest work, Learning to Learn Faster from Human Feedback with Language Model Predictive Control

Jacky Liang

86,652 views • 2 years ago