Subscribe
Sign in
Home
Podcast
Notes
Archive
About
Safety Benchmark of Meta Llama 3.x Models
Why didn't Meta meet their own Llama 3.0 Safety benchmark? Why does Llama 3.2 generate drastically more unsafe responses?
Oct 3, 2024
•
Jitendra
Latest
Top
Discussions
Build Secure SOC AI Incident Investigation Agent, Part 1
Mitigate Prompt Injections, Jailbreaks, Data Leaks and Misalignment Issues
Jun 30
•
Jitendra
1
Guardrails in Practice: Measuring Llama-PG vs. Detoxio’s 300 M ‘AI Firewall'
What 20 adversarial prompts reveal about modern safety stacks
Jun 23
•
Jitendra
AI Attack Surface: A Red Teamer’s Perspective
AI adoption is a reality. Are you prepared?
May 22
•
Jitendra
Myth vs. Reality: What Detoxio AI Uncovered About Meta’s Llama-Guard-4-12B
Enterprises can deploy Detoxio AI Hardened Meta LLama Guard to reduce jailbreak success, significantly. in live deployments
May 17
•
Jitendra
The Evolution of AI Agents
From LLMs to Autonomous Intelligence
May 2
•
Jitendra
9:14
Hands-On AI Red Teaming Course
Coming Soon
Feb 9
•
Jitendra
1
1
Distilled Deepseek Models
Safety Evaluation Report
Jan 30
•
Jitendra
See all
Detoxio AI
Making GenAI Safe and Reliable for Enterprises
Subscribe
Recommendations
Gradient Flow
Ben Lorica 罗瑞卡
Software Analyst Cyber Research
Francis Odum
The Security Industry
Richard Stiennon
Marc Andreessen Substack
Marc Andreessen
The Cyber Why
Tyler Shields
Home
Home
Detoxio AI
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
