•

NaN / NaN
Back
Search with your voice
Sign in

Apart - Safe AI

@apartresearch
•
857 subscribers•76 videos
Apart Research researches and facilitates the safe development of artificial intelligence. We strive to share our work and engage ML researchers and enthusiasts in safety for AI systems. apartresearch.comand 6 more links
Home
Videos
Live
Playlists
Posts
 

👩‍💻 Alignment Jam Talks
Play all

Talks from Apart Research's Alignment Jam hackathons and research sprints.
1:06:55
1:06:55
Now playing

Keynote Talk AI Control Hackathon with Tyler Tracy and Buck Shlegaris

Apart - Safe AI
Apart - Safe AI
124 viewsStreamed 3 weeks ago
43:25
43:25
Now playing

Women in AI Safety Hackathon Keynote Talk with Nakshathra Suresh

Apart - Safe AI
Apart - Safe AI
98 viewsStreamed 1 month ago
30:01
30:01
Now playing

Hacktalk with Joshua Landes

Apart - Safe AI
Apart - Safe AI
108 viewsStreamed 1 month ago
31:35
31:35
Now playing

AI interpretability with Myra Deng

Apart - Safe AI
Apart - Safe AI
195 viewsStreamed 1 month ago
46:01
46:01
Now playing

Intro to AI Assurance Technology with Kristian Rönn

Apart - Safe AI
Apart - Safe AI
106 viewsStreamed 3 months ago
49:03
49:03
Now playing

Accelerating AI Safety with Finn Metz

Apart - Safe AI
Apart - Safe AI
100 viewsStreamed 3 months ago

👩‍🔬 Apart Lab Talks
Play all

Talks about the projects that come out of the research labs of the Alignment Jam research workshops.
1:00:35
1:00:35
Now playing

Can an LLM Hack You? - Benchmarking Cybersecurity - Andrey Anurin

Apart - Safe AI
Apart - Safe AI
418 views11 months ago
53:26
53:26
Now playing

Uncovering Limitations of LLM Memory Editing - Jason Hoelscher-Obermaier

Apart - Safe AI
Apart - Safe AI
327 views1 year ago
53:32
53:32
Now playing

Neuron to Graph - Alex Foote

Apart - Safe AI
Apart - Safe AI
126 views1 year ago
47:05
47:05
Now playing

Do Models Cheat on Tests? - Jacob Haimes

Apart - Safe AI
Apart - Safe AI
70 views9 months ago

Popular videos

1:23:50
1:23:50
Now playing

Interpretability Hackathon 0.0 Keynote w/ Neel Nanda
662 views2 years ago
54:36
54:36
Now playing

Mechanistic Interpretability 1.0 Hackathon - Neel Nanda
578 views1 year ago
1:00:35
1:00:35
Now playing

Can an LLM Hack You? - Benchmarking Cybersecurity - Andrey Anurin
418 views11 months ago
47:32
47:32
Now playing

Bad LLM Agents - Simon Lermen
333 views11 months ago
53:26
53:26
Now playing

Uncovering Limitations of LLM Memory Editing - Jason Hoelscher-Obermaier
327 views1 year ago
47:37
47:37
Now playing

Safety Testing for AGI Systems - Bo Li
307 views10 months ago

Videos

34:08
34:08
Now playing

Engineering a World Designed for Safe Superintelligence
117 views12 days ago
1:10:01
1:10:01
Now playing

Award Ceremony: Reprogramming AI Models Hackathon
99 views3 months ago
23:57
23:57
Now playing

Researcher Spotlight: Jacob Haimes
111 views4 months ago
34:35
34:35
Now playing

Jacques Thibodeau: Mastering Cursor
150 views4 months ago
24:29
24:29
Now playing

Chandler Smith on the Concordia Contest
79 views5 months ago
50:24
50:24
Now playing

Introduction to Research Augmentation for Alignment - Jacques Thibodeau
111 views8 months ago

 …

NaN / NaN