Канал: The Inside View

Owain Evans - AI Situational Awareness, LLM Out-of-Context Reasoning

Owain Evans - AI Situational Awareness, LLM Out-of-Context Reasoning

The Trillion-Dollar AI Race Against the CCP

The Trillion-Dollar AI Race Against the CCP

Coping with AI Doom

Coping with AI Doom

The Economics of AGI Automation

The Economics of AGI Automation

AGI Takeoff By 2036

AGI Takeoff By 2036

2040: The Year of Full AI Automation

2040: The Year of Full AI Automation

How to Justify the Safety of Advanced AI Systems? (Walkthrough)

How to Justify the Safety of Advanced AI Systems? (Walkthrough)

Paul Christiano AI, Zelda Treachous Turn, Quantilizers (Walkthrough)

Paul Christiano AI, Zelda Treachous Turn, Quantilizers (Walkthrough)

AI Control: Humanity's Final Line Of Defense (Walkthrough)

AI Control: Humanity's Final Line Of Defense (Walkthrough)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (Walkthrough)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training (Walkthrough)

Anthropic Caught Their Backdoored Models (Walkthrough)

Anthropic Caught Their Backdoored Models (Walkthrough)

Anthropic Solved Interpretability Again? (Walkthrough)

Anthropic Solved Interpretability Again? (Walkthrough)

I Jammed with Claude Opus Via Voice

I Jammed with Claude Opus Via Voice

Sleeper Agents Explained - Part 4 - Every Single Figure (1-5)

Sleeper Agents Explained - Part 4 - Every Single Figure (1-5)

Sleeper Agents Explained - Part 3 - Chain-of-Thought Backdoors

Sleeper Agents Explained - Part 3 - Chain-of-Thought Backdoors

Sleeper Agents Explained - Part 2 - Deceptive Instrumental Alignment, Model Poisoning

Sleeper Agents Explained - Part 2 - Deceptive Instrumental Alignment, Model Poisoning

Sleeper Agents Explained - Part 1 - Safety Training

Sleeper Agents Explained - Part 1 - Safety Training

Adam Gleave - Vulnerabilities in GPT-4 APIs & Superhuman Go AIs

Adam Gleave - Vulnerabilities in GPT-4 APIs & Superhuman Go AIs

Nathan Labenz - AI Biology Could Spiral Out Of Control

Nathan Labenz - AI Biology Could Spiral Out Of Control

I Talked To AI Therapists Everyday For A Week

I Talked To AI Therapists Everyday For A Week

I Talked To GPT-4o (Not Multimodal) Via Voice - Day 3

I Talked To GPT-4o (Not Multimodal) Via Voice - Day 3

Using An AI Therapist For 7 Days - Day 2

Using An AI Therapist For 7 Days - Day 2

Using An AI Therapist For 7 Days - Day 1

Using An AI Therapist For 7 Days - Day 1

daily uploads are back

daily uploads are back

Ethan Perez (Anthropic) - Bottom-Up Alignment Research

Ethan Perez (Anthropic) - Bottom-Up Alignment Research

2024: The Year Of Artificial General Intelligence

2024: The Year Of Artificial General Intelligence

Emil Wallner—Sora, Text-to-video, AGI optimism

Emil Wallner—Sora, Text-to-video, AGI optimism

This was made by AI? #ai #agi #westworld #texttovideoai

This was made by AI? #ai #agi #westworld #texttovideoai

This Trailer Was AI-Generated (OpenAI Sora)

This Trailer Was AI-Generated (OpenAI Sora)

Evan Hubinger (Anthropic)—Deception, Sleeper Agents, Responsible Scaling

Evan Hubinger (Anthropic)—Deception, Sleeper Agents, Responsible Scaling

Guess Which Image Is AI Win $20 #ai #art #midjourney #stablediffusion #berkeley

Guess Which Image Is AI Win $20 #ai #art #midjourney #stablediffusion #berkeley

Jeffrey Ladish–AI Cyberwarfare, Compute Monitoring

Jeffrey Ladish–AI Cyberwarfare, Compute Monitoring

what's Artificial General Intelligence? #agi #ai

what's Artificial General Intelligence? #agi #ai

Holly Elmore—Pausing Frontier AI Development

Holly Elmore—Pausing Frontier AI Development

Guess Which Image Is Made By AI Win $20 #ai #art #midjourney #dalle #stablediffusion

Guess Which Image Is Made By AI Win $20 #ai #art #midjourney #dalle #stablediffusion

Guess Which Image Is Made By AI Win $20

Guess Which Image Is Made By AI Win $20

Guess Which Image Is Made By AI Win $20 #ai #art #midjourney #dalle #stablediffusion #dalle2

Guess Which Image Is Made By AI Win $20 #ai #art #midjourney #dalle #stablediffusion #dalle2

update

update

GPT-2 Teaches GPT-4: Weak-to-Strong Generalization

GPT-2 Teaches GPT-4: Weak-to-Strong Generalization

How to Catch an AI Liar

How to Catch an AI Liar

Anthropic Solved Interpretability?

Anthropic Solved Interpretability?

Brian Zhan—Investing In AI Applications

Brian Zhan—Investing In AI Applications

Poster Presentations—AI Alignment & Coordination

Poster Presentations—AI Alignment & Coordination

We Beat The Strongest Go AI

We Beat The Strongest Go AI

Paul Christiano's Views on AI Doom (ft. Robert Miles)

Paul Christiano's Views on AI Doom (ft. Robert Miles)

Neel Nanda–Mechanistic Interpretability, Superposition, Grokking

Neel Nanda–Mechanistic Interpretability, Superposition, Grokking

Joscha Bach—How to Stop Worrying and Love AI

Joscha Bach—How to Stop Worrying and Love AI

Erik Jones—Automatically Auditing Large Language Models

Erik Jones—Automatically Auditing Large Language Models

Dylan Patel—GPU Shortage, Nvidia, Semiconductor Supply Chain

Dylan Patel—GPU Shortage, Nvidia, Semiconductor Supply Chain

Andi Peng—A Human-in-the-Loop Framework for Test-Time Policy Adaptation

Andi Peng—A Human-in-the-Loop Framework for Test-Time Policy Adaptation

Hailey Schoelkopf—Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Hailey Schoelkopf—Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Tomek Korbak—Pretraining Language Models with Human Preferences

Tomek Korbak—Pretraining Language Models with Human Preferences

Tim Dettmers—k-bit Inference Scaling Laws

Tim Dettmers—k-bit Inference Scaling Laws

Eric Wallace—Poisoning Language Models During Instruction Tuning

Eric Wallace—Poisoning Language Models During Instruction Tuning

Tony Wang—Beating Superhuman Go AIs

Tony Wang—Beating Superhuman Go AIs

David Bau—Editing Facts in GPT, Interpretability

David Bau—Editing Facts in GPT, Interpretability

Alexander Pan–Are AIs Machiavellian?

Alexander Pan–Are AIs Machiavellian?

Vincent Weisser–Funding Alignment Research

Vincent Weisser–Funding Alignment Research

International Conference on Machine Learning Vlog #1

International Conference on Machine Learning Vlog #1

Aran Komatsuzaki–Scaling, GPT-J

Aran Komatsuzaki–Scaling, GPT-J

Curtis Huebner—AGI by 2028, 90% Doom

Curtis Huebner—AGI by 2028, 90% Doom

Forecasting Transformative AI—The Four Biological Anchors

Forecasting Transformative AI—The Four Biological Anchors

Musk reveals xAI, Anthropic launches Claude 2, OpenAI starts Superalignment

Musk reveals xAI, Anthropic launches Claude 2, OpenAI starts Superalignment

Eric Michaud—Scaling, Grokking, Quantum Interpretability

Eric Michaud—Scaling, Grokking, Quantum Interpretability

Defining Transformative AI—Episode 2

Defining Transformative AI—Episode 2

Introduction to AI Timelines—Episode 1

Introduction to AI Timelines—Episode 1

Daniel Filan–AXRP, LLMs, Interpretability

Daniel Filan–AXRP, LLMs, Interpretability

Existential Risk From AI Is Higher Than 10%—Change My Mind

Existential Risk From AI Is Higher Than 10%—Change My Mind

Jesse Hoogland–AI Risk, Interpretability

Jesse Hoogland–AI Risk, Interpretability

addressing youtube comments (day 3)

addressing youtube comments (day 3)

this subscriber thinks compute is all you need (day 2)

this subscriber thinks compute is all you need (day 2)

30 videos in 30 days (day 1)

30 videos in 30 days (day 1)

Clarifying and predicting AGI

Clarifying and predicting AGI

Alan Chan and Max Kaufmann–Model Evaluations, Timelines, Coordination

Alan Chan and Max Kaufmann–Model Evaluations, Timelines, Coordination

Breandan Considine–AI Timelines, Coding AI, Neuro Symbolic AI

Breandan Considine–AI Timelines, Coding AI, Neuro Symbolic AI

Christoph Schuhmann–Open Source AI, Misuse, Existential risk

Christoph Schuhmann–Open Source AI, Misuse, Existential risk

NeurIPS Vlog–Governing AI, Sentience, FishAI

NeurIPS Vlog–Governing AI, Sentience, FishAI

Simeon Campos–Short Timelines, AI Governance, Field Building

Simeon Campos–Short Timelines, AI Governance, Field Building

ML Street Talk–AI Existential Risk

ML Street Talk–AI Existential Risk

ML Street Talk–Takeoff Speeds

ML Street Talk–Takeoff Speeds

Collin Burns–Making GPT-N Honest

Collin Burns–Making GPT-N Honest

Victoria Krakovna–AGI Ruin, Sharp Left Turn, Paradigms of AI Alignment

Victoria Krakovna–AGI Ruin, Sharp Left Turn, Paradigms of AI Alignment

David Krueger—Coordination, AI Alignment, Academia

David Krueger—Coordination, AI Alignment, Academia

Scale Is All You Need: Change My Mind

Scale Is All You Need: Change My Mind

Ethan Caballero–Broken Neural Scaling Laws

Ethan Caballero–Broken Neural Scaling Laws

Irina Rish—AGI, Scaling, Alignment

Irina Rish—AGI, Scaling, Alignment

Guess Which Images Are Made By AI Win T-Shirts

Guess Which Images Are Made By AI Win T-Shirts

Shahar Avin–AI Governance

Shahar Avin–AI Governance

Katja Grace—Slowing Down AI, Forecasting AI Risk

Katja Grace—Slowing Down AI, Forecasting AI Risk

Markus Anderljung–Regulating Advanced AI

Markus Anderljung–Regulating Advanced AI

Alex Lawsen—Forecasting AI Progress

Alex Lawsen—Forecasting AI Progress

Robert Long–Artificial Sentience, Digital Minds

Robert Long–Artificial Sentience, Digital Minds

Ethan Perez–Inverse Scaling, Red Teaming

Ethan Perez–Inverse Scaling, Red Teaming

Robert Miles–Youtube, Doom

Robert Miles–Youtube, Doom

Connor Leahy–EleutherAI, Conjecture

Connor Leahy–EleutherAI, Conjecture

Guess Which Image Is Made by AI, Win 20€

Guess Which Image Is Made by AI, Win 20€

Raphaël Millière–Contra Scaling Maximalism

Raphaël Millière–Contra Scaling Maximalism

Blake Richards—AGI Does Not Exist

Blake Richards—AGI Does Not Exist

Ethan Caballero–Scale Is All You Need

Ethan Caballero–Scale Is All You Need

The Inside View #10–Peter Wildeford–Forecasting

The Inside View #10–Peter Wildeford–Forecasting

The Inside View #9–Emil Wallner–Building a €25000 ML Rig

The Inside View #9–Emil Wallner–Building a €25000 ML Rig

The Inside View #8–Sonia Joseph–NFTs, Web3 and AI Safety

The Inside View #8–Sonia Joseph–NFTs, Web3 and AI Safety

The Inside View #7—Phil Trammell—Economic Growth, Transformative AI

The Inside View #7—Phil Trammell—Economic Growth, Transformative AI

The Inside View #6—Slava Bobrov—Brain Computer Interfaces

The Inside View #6—Slava Bobrov—Brain Computer Interfaces

The Inside View #5–Charlie Snell–DALL-E & CLIP

The Inside View #5–Charlie Snell–DALL-E & CLIP

Copilot Solves My Coding Tests

Copilot Solves My Coding Tests

The Inside View #4—Sav Sidorov—Learning, Contrarianism and Robotics

The Inside View #4—Sav Sidorov—Learning, Contrarianism and Robotics

The Inside View #3–Evan Hubinger—Takeoff speeds, Risks from learned optimization & Interpretability

The Inside View #3–Evan Hubinger—Takeoff speeds, Risks from learned optimization & Interpretability

The Inside View #2–Connor Leahy

The Inside View #2–Connor Leahy

The Inside View #1—Does the world really need another podcast?

The Inside View #1—Does the world really need another podcast?