Загрузка видео...

Не удалось загрузить видео

На главную

Non-robustness hints at paradigm failures. Reasoning can improve robustness. Alexander Wei explores reasoning-based defenses that let models ‘think’ before responding, helping counter adversarial attacks and strengthen AI safety."

farairesearch's profile picture

FAR.AI

16,518 subscribers

508,419 просмотров • 1 год назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 2

Фото профиля FAR.AI
FAR.AI1 год назад

Follow us for AI safety insights And watch the full video

Фото профиля Hooman Malekmohammadi
Hooman Malekmohammadi1 год назад

@alexwei_ آیا هوش مصنوعی میتواند به مرور زمان تبدیل به یک دشمن شود ؟

Похожие видео

🛡 Is AI robustness possible, or are adversarial attacks unavoidable? We tested three defenses to make superhuman Go AIs robust. Our defenses manage to protect against known threats, but unfortunately new adversaries bypass them, sometimes using qualitatively new attacks! 🧵
1:12

🛡 Is AI robustness possible, or are adversarial attacks unavoidable? We tested three defenses to make superhuman Go AIs robust. Our defenses manage to protect against known threats, but unfortunately new adversaries bypass them, sometimes using qualitatively new attacks! 🧵

FAR.AI

193,980 просмотров • 2 лет назад

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!
1:29

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Jiafei Duan

48,739 просмотров • 1 год назад

Apple's AI Reasoning Model Paper Explained Apple’s disruptive new AI reasoning model research paper, “The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models” explained, and what it means for AGI.
3:22

Apple's AI Reasoning Model Paper Explained Apple’s disruptive new AI reasoning model research paper, “The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models” explained, and what it means for AGI.

Harper Carroll

37,956 просмотров • 1 год назад

2.5 models are thinking models, capable of reasoning through thoughts before responding. The result is enhanced performance and improved accuracy. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.
0:29

2.5 models are thinking models, capable of reasoning through thoughts before responding. The result is enhanced performance and improved accuracy. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.

Google

31,023 просмотров • 1 год назад

While others fight, we ship 🚀 Agno’s ReasoningTools are now live on the Playground — giving non-reasoning models the ability to "think", "analyze", and outperform Reasoning Models on Agentic workloads. If you haven't tried `ReasoningTools` yet - you definitely should 👇
1:18

While others fight, we ship 🚀 Agno’s ReasoningTools are now live on the Playground — giving non-reasoning models the ability to "think", "analyze", and outperform Reasoning Models on Agentic workloads. If you haven't tried `ReasoningTools` yet - you definitely should 👇

Ashpreet Bedi

27,864 просмотров • 1 год назад

Yesterday at #GoogleIO, we introduced Gemini 2.5 Pro Deep Think 🧠, pushing the frontiers of AI reasoning. This enhanced reasoning mode is built to tackle drastically complex problems – like USAMO problems that stumped previous models. Super proud of the GDM team for this one!
0:30

Yesterday at #GoogleIO, we introduced Gemini 2.5 Pro Deep Think 🧠, pushing the frontiers of AI reasoning. This enhanced reasoning mode is built to tackle drastically complex problems – like USAMO problems that stumped previous models. Super proud of the GDM team for this one!

Oriol Vinyals

86,776 просмотров • 1 год назад

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.
2:00

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.

Microsoft Research

11,672 просмотров • 3 месяцев назад

Reasoning models tailored for diverse AI tasks. 🚀 Meet Amazon Nova 2 foundation models, supporting fast, cost-effective reasoning to multimodal capabilities. Power versatile tasks like AI agents, code-generation, and Conversational AI. Choose the perfect match for your workload.
0:29

Reasoning models tailored for diverse AI tasks. 🚀 Meet Amazon Nova 2 foundation models, supporting fast, cost-effective reasoning to multimodal capabilities. Power versatile tasks like AI agents, code-generation, and Conversational AI. Choose the perfect match for your workload.

Amazon Web Services

2,074,714 просмотров • 7 месяцев назад

Turn any AI Model into Reasoning Model with Deepseek r1 <thinking> Architecture. Models like GPT4o and Sonnet 3.5 are Implementation Models But a new breakthrough with Deepseek can make them a Reasoning model. Here's a step-by-step Explanation: 🧵
0:28

Turn any AI Model into Reasoning Model with Deepseek r1 <thinking> Architecture. Models like GPT4o and Sonnet 3.5 are Implementation Models But a new breakthrough with Deepseek can make them a Reasoning model. Here's a step-by-step Explanation: 🧵

CJ Zafir

192,667 просмотров • 1 год назад

“Reasoning has fundamentally changed the economics of these frontier models.” Gavin Baker says reasoning lets scaled user bases unlock a new flywheel. Users improve the model, and the model improves the product. Gavin Baker
1:03

“Reasoning has fundamentally changed the economics of these frontier models.” Gavin Baker says reasoning lets scaled user bases unlock a new flywheel. Users improve the model, and the model improves the product. Gavin Baker

a16z

23,671 просмотров • 8 месяцев назад

We cover early times at OpenAI, the era of ChatGPT, “reasoning” models, safety that scales. We discuss why building systems people can trust isn’t optional and is also fundamental to making them useful. YouTube: Spotify: Apple Podcasts:
0:51

We cover early times at OpenAI, the era of ChatGPT, “reasoning” models, safety that scales. We discuss why building systems people can trust isn’t optional and is also fundamental to making them useful. YouTube: Spotify: Apple Podcasts:

Aleksander Madry

22,084 просмотров • 11 месяцев назад

New research from Meta FAIR: Large Concept Models (LCM) is a fundamentally different paradigm for language modeling that decouples reasoning from language representation, inspired by how humans can plan high-level thoughts to communicate.
0:36

New research from Meta FAIR: Large Concept Models (LCM) is a fundamentally different paradigm for language modeling that decouples reasoning from language representation, inspired by how humans can plan high-level thoughts to communicate.

AI at Meta

531,550 просмотров • 1 год назад

Understanding OpenAI o1: Noam Brown on integrating reasoning into the model. Takeaways: - Avoid MCTS and current paradigm of using processes outside of the model during inference - Think about how to directly integrate reasoning into the model architecture
0:59

Understanding OpenAI o1: Noam Brown on integrating reasoning into the model. Takeaways: - Avoid MCTS and current paradigm of using processes outside of the model during inference - Think about how to directly integrate reasoning into the model architecture

Casper Hansen

313,291 просмотров • 1 год назад

Can VLMs build Spatial Mental Models like humans? Reasoning from limited views? Reasoning from partial observations? Reasoning about unseen objects behind furniture / beyond current view? Check out MindCube! 🌐 📰 🤗 👩‍💻
1:26

Can VLMs build Spatial Mental Models like humans? Reasoning from limited views? Reasoning from partial observations? Reasoning about unseen objects behind furniture / beyond current view? Check out MindCube! 🌐 📰 🤗 👩‍💻

Manling Li

40,959 просмотров • 1 год назад

Gemini 3 Deep Think is here. Deep Think is our most advanced reasoning mode that explores multiple hypotheses simultaneously to give you an even more sophisticated output.
0:26

Gemini 3 Deep Think is here. Deep Think is our most advanced reasoning mode that explores multiple hypotheses simultaneously to give you an even more sophisticated output.

Google Gemini

7,712,834 просмотров • 6 месяцев назад

With Glass's new Workspace feature, clinicians can use AI to complete complex diagnostic reasoning, treatment planning, and documentation workflows more effectively than ever before. Available now at #AI #AICDS #healthcareinnovation
0:54

With Glass's new Workspace feature, clinicians can use AI to complete complex diagnostic reasoning, treatment planning, and documentation workflows more effectively than ever before. Available now at #AI #AICDS #healthcareinnovation

Glass Health

22,135 просмотров • 1 год назад

NEWS: NVIDIA just announced Alpamayo, what CEO Jensen Huang calls the world’s first thinking, reasoning autonomous vehicle AI, launching on U.S. roads later this year, starting with the Mercedes CLA. Jensen: "It's trained end-to-end. Literally from camera in to actuation out; It reasons what action it is about to take, the reason by which is came about that action, and the trajectory." Alpamayo introduces Vision-Language-Action (VLA) models, which enable self-driving systems to interpret what they see, reason about complex driving scenarios, and generate driving actions. The platform includes large reasoning models, simulation tools for testing rare and edge-case scenarios, and open datasets for training and validation. NVIDIA says the approach improves transparency, safety, and robustness in autonomous systems, particularly in complex real-world environments, and supports progress toward higher levels of vehicle autonomy: "With a 10-billion-parameter architecture, Alpamayo 1 uses video input to generate trajectories alongside reasoning traces, showing the logic behind each decision. Developers can adapt Alpamayo 1 into smaller runtime models for vehicle development, or use it as a foundation for AV development tools such as reasoning-based evaluators and auto-labeling systems. Alpamayo 1 provides open model weights and open-source inferencing scripts. Future models in the family will feature larger parameter counts, more detailed reasoning capabilities, more input and output flexibility, and options for commercial usage."
2:41

NEWS: NVIDIA just announced Alpamayo, what CEO Jensen Huang calls the world’s first thinking, reasoning autonomous vehicle AI, launching on U.S. roads later this year, starting with the Mercedes CLA. Jensen: "It's trained end-to-end. Literally from camera in to actuation out; It reasons what action it is about to take, the reason by which is came about that action, and the trajectory." Alpamayo introduces Vision-Language-Action (VLA) models, which enable self-driving systems to interpret what they see, reason about complex driving scenarios, and generate driving actions. The platform includes large reasoning models, simulation tools for testing rare and edge-case scenarios, and open datasets for training and validation. NVIDIA says the approach improves transparency, safety, and robustness in autonomous systems, particularly in complex real-world environments, and supports progress toward higher levels of vehicle autonomy: "With a 10-billion-parameter architecture, Alpamayo 1 uses video input to generate trajectories alongside reasoning traces, showing the logic behind each decision. Developers can adapt Alpamayo 1 into smaller runtime models for vehicle development, or use it as a foundation for AV development tools such as reasoning-based evaluators and auto-labeling systems. Alpamayo 1 provides open model weights and open-source inferencing scripts. Future models in the family will feature larger parameter counts, more detailed reasoning capabilities, more input and output flexibility, and options for commercial usage."

Sawyer Merritt

1,603,163 просмотров • 5 месяцев назад

still shadowbanned 🥱 guess it's time to let you all in on a little secret as models get faster and faster at reasoning, so too will AI operators need to improve their own decision-making speed/reaction time in order to keep up and remain useful nodes "in-the-loop" the future of prompting will likely not be text-based and that is why I study the blade ⚔️
2:00

still shadowbanned 🥱 guess it's time to let you all in on a little secret as models get faster and faster at reasoning, so too will AI operators need to improve their own decision-making speed/reaction time in order to keep up and remain useful nodes "in-the-loop" the future of prompting will likely not be text-based and that is why I study the blade ⚔️

Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭

22,326 просмотров • 2 лет назад

Introducing Collaborative Reasoner: a framework to improve collaborative reasoning in language models. Collaborative Reasoner paves the way for developing social agents that can partner with humans and other agents. Read the research paper and download the code.
1:36

Introducing Collaborative Reasoner: a framework to improve collaborative reasoning in language models. Collaborative Reasoner paves the way for developing social agents that can partner with humans and other agents. Read the research paper and download the code.

AI at Meta

58,510 просмотров • 1 год назад