Emanuele Fabbiani

Inside the Mind of an LLM

An LLM leaking private data isn't a bug, it's a core feature. Learn why deep learning models are fundamentally designed to memorize unique information.

Inside the Mind of an LLM
#1about 7 minutes

Understanding the risks of large language models

LLMs are often used without understanding their inner workings, leading to factual errors and the generation of insecure code.

#2about 8 minutes

How large language models are trained

A four-phase process explains how models learn language through pre-training, are taught tasks, aligned with human preferences, and refined using reinforcement learning.

#3about 5 minutes

Why Llama 2 models think in English

Research on Llama 2 models reveals they use English as an internal representation for all tasks due to its prevalence in the training data.

#4about 4 minutes

Controlling LLM behavior with monosemantic features

By identifying and amplifying single-meaning concepts, or monosemantic features, it is possible to deterministically control a model's output on specific topics.

#5about 2 minutes

Why LLMs memorize and leak private data

Deep learning models inherently memorize unique outlier data from their training set, which explains why LLMs can leak personal information and pose a privacy risk.

Related jobs
Jobs that call for the skills explored in this talk.

Matching moments

Addressing the key challenges of large language models
02:55 MIN

Addressing the key challenges of large language models

Large Language Models ❤️ Knowledge Graphs

Addressing the core challenges of large language models
05:18 MIN

Addressing the core challenges of large language models

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps

Considering local LLMs for security and summarizing key learnings
03:10 MIN

Considering local LLMs for security and summarizing key learnings

Leveraging Large Language Models for Legacy Code Translation: Challenges and Solutions

Understanding the core capabilities of large language models
02:26 MIN

Understanding the core capabilities of large language models

Data Privacy in LLMs: Challenges and Best Practices

Understanding the problem of LLM hallucinations
02:29 MIN

Understanding the problem of LLM hallucinations

Martin O'Hanlon - Make LLMs make sense with GraphRAG

Understanding the dual nature of large language models
02:18 MIN

Understanding the dual nature of large language models

Lies, Damned Lies and Large Language Models

Addressing data privacy and security in AI systems
01:40 MIN

Addressing data privacy and security in AI systems

Graphs and RAGs Everywhere... But What Are They? - Andreas Kollegger - Neo4j

Understanding the limitations of large language models
02:20 MIN

Understanding the limitations of large language models

Knowledge graph based chatbot

Featured Partners

Related Videos

See all videos
Three years of putting LLMs into Software - Lessons learned26:30

Three years of putting LLMs into Software - Lessons learned

Simon A.T. Jiménez

Adding knowledge to open-source LLMs25:35

Adding knowledge to open-source LLMs

Sergio Perez & Harshita Seth

Self-Hosted LLMs: From Zero to Inference30:04

Self-Hosted LLMs: From Zero to Inference

Roberto Carratalá & Cedric Clyburn

Data Privacy in LLMs: Challenges and Best Practices23:50

Data Privacy in LLMs: Challenges and Best Practices

Aditi Godbole

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails29:00

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails

Alex Soto

Unlocking the Power of AI: Accessible Language Model Tuning for All31:50

Unlocking the Power of AI: Accessible Language Model Tuning for All

Cedric Clyburn & Legare Kerrison

Using LLMs in your Product31:12

Using LLMs in your Product

Daniel Töws

Exploring LLMs across clouds28:38

Exploring LLMs across clouds

Tomislav Tipurić

Related Articles

View all articles
LM
Luis Minvielle
What Are Large Language Models?
Developers and writers can finally agree on one thing: Large Language Models, the subset of AIs that drive ChatGPT and its competitors, are stunning tech creations. Developers enjoying the likes of GitHub Copilot know the feeling: this new kind of te...
What Are Large Language Models?
BR
Benjamin Ruschin
Who Owns Your Content in the Age of LLMs?
AI has changed the web forever. Large language models (LLMs) are changing how information is produced, shared and consumed on the web. In fact, estimates suggest that now more than half of all web traffic is made up of bots , with a sizable amount of...
Who Owns Your Content in the Age of LLMs?
DC
Daniel Cranney
Dev Digest 210: AI Agents Are Go! Is MCP Dead? LLMs Crack Anonymity
Inside last week’s Dev Digest 210 . 🪦 Is MCP already dead? 🐍 Secure snake on the CLI 🏗️ The architecture behind open source LLMs ⚖️ AI companies and governments at odds 🦫 Is Go the best language for AI agents? 🕵️ “Security research” bot hacks Micros...
Dev Digest 210: AI Agents Are Go! Is MCP Dead? LLMs Crack Anonymity

From learning to earning

Jobs that call for the skills explored in this talk.