filmov
tv
Demystifying LLMs with Mechanistic Interpretability Researcher Arthur Conmy
Показать описание
TIMESTAMPS:
(00:00) Episode Preview
(04:40) What attracted Arthur to mechanistic interpretability?
(07:49) LLM information processing: General Understanding vs Stochastic Parrot Paradigm
(14:45) Sponsors: NetSuite | Omneky
(24:30) Putting together data sets
(32:39) How to intervene in LLMs network activity
(36:00) Setting metrics to evaluate the production of correct completions
(44:20) The future of the mechanistic interpretability research
(50:00) Extracting upstream activations in the ACDC project and evaluating impact on downstream components.
(56:00) Anthropic research findings
(01:08:00) 3-Step process of the ACDC approach
(01:22:00) Setting a threshold and validation
(01:27:00) Goal of the approach
(01:32:00) Compute requirements
*Correction at 1:33:00 Arthur meant to say = "quadratic in nodes"
(01:35:30) Scaling laws for mechanistic interpretability
(01:40:00) Accessibility of this research for casual enthusiasts
(01:46:00) Emergence discourse
(01:56:00) Path to AI safety
LINKS:
SOCIAL MEDIA:
@labenz (Nathan)
@arthurconmy (Arthur)
@cogrev_podcast
SPONSORS: NetSuite | Omneky
-Omneky is an omnichannel creative generation platform that lets you launch hundreds of thousands of ad iterations that *actually work* customized across all platforms, with a click of a button. Omneky combines generative AI and real-time advertising data. Mention "Cog Rev" for 10% off.
Music license:
VTPHPIMGIQFU2HXZ
2:13:07
Demystifying LLMs with Mechanistic Interpretability Researcher Arthur Conmy
0:03:13
What is mechanistic interpretability? Neel Nanda explains.
1:06:52
Demystifying LLMs and Threats My Journey
0:55:27
Open Problems in Mechanistic Interpretability: A Whirlwind Tour
0:03:03
Demystifying AI: How Anthropic Cracks the Code of Large Language Models (LLMs)
0:54:10
Cohere For AI - Community Talks - Catherine Olsson on Mechanistic Interpretability: Getting Started
0:15:30
Provably Safe AGI - MIT Mechanistic Interpretability Conference - May 7, 2023
3:09:21
What the hell is going on inside neural networks? | Chris Olah
0:01:17
The Dark Side of Large Language Models: The Stochastic Parrot Phenomenon
0:57:20
A Walkthrough of Interpretability in the Wild Part 1/2: Overview (w/ authors Kevin, Arthur, Alex)
0:41:34
Graph-of-Thoughts (GoT) for AI reasoning Agents
0:01:49
Discussing AI sentience and stochastic parrots 🦜
1:24:54
How AI Really Works - Intro to Open Source Large Language Models
0:33:43
David Chalmers: Understanding Understanding Through Conceptual Engineering
0:47:41
Hella New AI Papers - Aug 24, 2024
0:44:25
A Walkthrough of Automated Circuit Discovery w/ Arthur Conmy Part 2/3
1:33:57
AI Scouting Report – Part 1 of 3: Fundamentals
0:59:41
The AI Copilot Revolution with Div Garg of MULTI·ON
1:45:46
The Future of Software Development with Tyler Angert of Replit
0:54:17
DataFAIR 2023: GPT & Drug Discovery: Rise of Generative Models
1:01:58
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Комментарии