Safety Alignment Should be Made More Than Just a Few Tokens Deep (Paper Explained)

  Рет қаралды 10,292

Yannic Kilcher

Yannic Kilcher

Күн бұрын

Пікірлер: 53
Byte Latent Transformer: Patches Scale Better Than Tokens (Paper Explained)
36:15
Byte Latent Transformer: Patches Scale Better Than Tokens (Paper Explained)
Yannic Kilcher
Рет қаралды 37 М.
Were RNNs All We Needed? (Paper Explained)
27:48
Were RNNs All We Needed? (Paper Explained)
Yannic Kilcher
Рет қаралды 54 М.
coco在求救？ #小丑 #天使 #shorts
00:29
coco在求救？ #小丑 #天使 #shorts
好人小丑
Рет қаралды 120 МЛН
IL'HAN - Qalqam | Official Music Video
03:17
IL'HAN - Qalqam | Official Music Video
Ilhan Ihsanov
Рет қаралды 700 М.
Қылмыскерді таптым… | QARGA 2 | 3 серия | КОНКУРС
31:30
Қылмыскерді таптым… | QARGA 2 | 3 серия | КОНКУРС
OMIR
Рет қаралды 594 М.
BAYGUYSTAN | 1 СЕРИЯ | bayGUYS
36:55
BAYGUYSTAN | 1 СЕРИЯ | bayGUYS
bayGUYS
Рет қаралды 1,9 МЛН
The Strange Physics Principle That Shapes Reality
32:44
The Strange Physics Principle That Shapes Reality
Veritasium
Рет қаралды 8 МЛН
Can we keep AI honest? [Mechanistic Interpretability]
24:09
Can we keep AI honest? [Mechanistic Interpretability]
Welch Labs
Рет қаралды 141 М.
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)
1:11:58
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)
Yannic Kilcher
Рет қаралды 38 М.
The Mathematician So Strange the FBI Thought He Was a Spy
13:11
The Mathematician So Strange the FBI Thought He Was a Spy
Tibees
Рет қаралды 189 М.
Finally: Grokking Solved - It's Not What You Think
27:02
Finally: Grokking Solved - It's Not What You Think
Discover AI
Рет қаралды 14 М.
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
Grant Sanderson
Рет қаралды 320 М.
xLSTM: Extended Long Short-Term Memory
57:00
xLSTM: Extended Long Short-Term Memory
Yannic Kilcher
Рет қаралды 39 М.
Stanford Webinar - Large Language Models Get the Hype, but Compound Systems Are the Future of AI
58:06
Stanford Webinar - Large Language Models Get the Hype, but Compound Systems Are the Future of AI
Stanford Online
Рет қаралды 98 М.
Gemini 2.0 and the evolution of agentic AI with Oriol Vinyals
51:57
Gemini 2.0 and the evolution of agentic AI with Oriol Vinyals
Google DeepMind
Рет қаралды 79 М.
The Trillion Dollar Equation
31:22
The Trillion Dollar Equation
Veritasium
Рет қаралды 10 МЛН
coco在求救？ #小丑 #天使 #shorts
00:29
coco在求救？ #小丑 #天使 #shorts
好人小丑
Рет қаралды 120 МЛН