Категории

LLM Security and Control With Hugging Face and WhyLabs

Опубликовано: 06 Июнь 2026
на канале: WhyLabs
323
14

Here are the links for the workshop:

​​- Colab notebook: https://bit.ly/whylabs-hf-ipynb
LangKit GitHub (give us a star!): https://github.com/whylabs/langkit
Sign up for a free WhyLabs account: https://whylabs.ai/free
​​- Presentation slides: https://bit.ly/wl-hf-slides

Keeping up with the fast-paced world of AI requires the ability to monitor and control large language models (LLMs). WhyLabs now offers enhanced tools to guard and redirect LLM-powered applications during transactions, providing a new level of security and oversight.

Join our workshop designed to equip you with the knowledge and skills to use LangKit with public Hugging Face models. Guided by WhyLabs Senior Data Scientist Bernease Herman, you'll learn how to evaluate, troubleshoot, and safeguard LLMs.

This workshop will cover how to:

Evaluate user interactions to monitor prompts, responses, and user interactions
Configure acceptable limits to indicate things like malicious prompts, toxic responses, hallucinations, and jailbreak attempts.
Set up monitors and alerts to help prevent undesirable behavior

play_arrow
3,685
168

Kyouka 🤤 - Gall Khaas | Kyouka Uzen | Chained Soldier |

Kyouka 🤤 - Gall Khaas | Kyouka Uzen | Chained Soldier |

play_arrow
1,071
29

Thriftin' for Movies - Episode 9: Flea Market Failure

Thriftin' for Movies - Episode 9: Flea Market Failure
play_arrow
236,632
5.5 тыс

Must Read Rumi, Shams Tabrizi, and Hafez Quotes

Must Read Rumi, Shams Tabrizi, and Hafez Quotes
play_arrow
510
11

Уникальное предложение от ТМ Буржуй

Уникальное предложение от ТМ Буржуй
play_arrow
4
0

Jolly 3 Part 1, Part 2

Jolly 3 Part 1, Part 2
play_arrow
14,219
506

DEAD BLOW MALLET: I Turned My 30 Year Old Joiners Mallet into a Dead Blow Mallet

DEAD BLOW MALLET: I Turned My 30 Year Old Joiners Mallet into a Dead Blow Mallet
play_arrow
38
9

обры по пополитре

обры по пополитре
play_arrow
28,109
195

Resurrection: Ertuğrul Full Episode 24

Resurrection: Ertuğrul Full Episode 24
Похожие видео
play_arrow
Current state-of-the-art on LLM Prompt Injections and Jailbreaks

Current state-of-the-art on LLM Prompt Injections and Jailbreaks
play_arrow
Finding the Right Datasets and Metrics for Evaluating LLM Performance

Finding the Right Datasets and Metrics for Evaluating LLM Performance
play_arrow
Monitoring Distributed ML Systems at Massive Scale with Spark & Databricks

Monitoring Distributed ML Systems at Massive Scale with Spark & Databricks
play_arrow
Safety in LLMs Using Chain-of-Thought: Lessons From Constitutional AI

Safety in LLMs Using Chain-of-Thought: Lessons From Constitutional AI
play_arrow
LLM Security and Control With Hugging Face and WhyLabs

LLM Security and Control With Hugging Face and WhyLabs
play_arrow
Securing and Controlling LLM Applications With LangChain and WhyLabs

Securing and Controlling LLM Applications With LangChain and WhyLabs
play_arrow
WhyLabs AI Control Center

WhyLabs AI Control Center
play_arrow
WhyLabs AI Control Center: Demo and Q&A

WhyLabs AI Control Center: Demo and Q&A
play_arrow
Reacting in Real-Time: Guardrails and Active Monitoring for LLMs

Reacting in Real-Time: Guardrails and Active Monitoring for LLMs
play_arrow
Monitoring LLMs in Production using LangChain and WhyLabs

Monitoring LLMs in Production using LangChain and WhyLabs
play_arrow
Mitigating LLM Risk in Insurance: Chatbots and Data Collection

Mitigating LLM Risk in Insurance: Chatbots and Data Collection
play_arrow
Preventing Threats to LLMs: Detecting Prompt Injections & Jailbreak Attacks

Preventing Threats to LLMs: Detecting Prompt Injections & Jailbreak Attacks
play_arrow
Decode, Detect, Diagnose Your LLM: Troubleshooting User Behavior Changes & Performance Drift

Decode, Detect, Diagnose Your LLM: Troubleshooting User Behavior Changes & Performance Drift
play_arrow
Monitoring LLMs in Production using LangChain and WhyLabs

Monitoring LLMs in Production using LangChain and WhyLabs
play_arrow
From Eyeballing to Excellence: 7 Ways to Evaluate & Monitor LLM Performance

From Eyeballing to Excellence: 7 Ways to Evaluate & Monitor LLM Performance
play_arrow
Monitoring LLMs in Production with Hugging Face and WhyLabs

Monitoring LLMs in Production with Hugging Face and WhyLabs
play_arrow
Intro to LLM Security - OWASP Top 10 for Large Language Models (LLMs)

Intro to LLM Security - OWASP Top 10 for Large Language Models (LLMs)
play_arrow
New course with WhyLabs and DeepLearning.AI: Quality and Safety for LLM Applications

New course with WhyLabs and DeepLearning.AI: Quality and Safety for LLM Applications
play_arrow
Intro to LLM Security - OWASP Top 10 for Large Language Models (LLMs)

Intro to LLM Security - OWASP Top 10 for Large Language Models (LLMs)
play_arrow
Create and Monitor LLM Summarization Apps using OpenAI and WhyLabs

Create and Monitor LLM Summarization Apps using OpenAI and WhyLabs
play_arrow
Intro to ML Monitoring: Data Drift, Quality, Bias and Explainability

Intro to ML Monitoring: Data Drift, Quality, Bias and Explainability
play_arrow
Intro to LLM Monitoring in Production with LangKit & WhyLabs

Intro to LLM Monitoring in Production with LangKit & WhyLabs
play_arrow
Monitoring AI Models for Bias & Fairness with Segmentation

Monitoring AI Models for Bias & Fairness with Segmentation
play_arrow
Monitoring LLMs in Production using OpenAI, LangChain & WhyLabs

Monitoring LLMs in Production using OpenAI, LangChain & WhyLabs