Media Summary: Detecting and correcting errors before run-time is increasingly important in today's ubiquitous computing environment. Decision ... In this episode of , we dive into a subtle but critical question: Does adding Speaker: Laura Kovacs In this talk Laura Kovacs will present recent advancement in automated

Reasoning About Reliability And Security - Detailed Analysis & Overview

Detecting and correcting errors before run-time is increasingly important in today's ubiquitous computing environment. Decision ... In this episode of , we dive into a subtle but critical question: Does adding Speaker: Laura Kovacs In this talk Laura Kovacs will present recent advancement in automated Chirag Agarwal presents the talk "The (Un) In this episode, we dissect five cutting-edge research papers that are reshaping the AI landscape. We kick things off with a ... In this episode, Nathan chats with Josh Albrecht, CTO of Imbue. They discuss how to create agents for

In this insightful talk from the Exner Lectures 2025, Laura Kovacs (TU Wien) explores the critical field of Automated Title: Code as Agent Harness: The Future of Autonomous AI In this video, we explore a transformative perspective on AI ... 2025 AI tool-using models are more capable, but real-world Google just introduced Mangle, a powerful new AI Triad Logic (TL) is a practical framework for keeping

Photo Gallery

Reasoning about Reliability and Security Using Boolean Methods
Reasoning Can Hurt LLM Safety?! Rethinking Accuracy in AI Systems (EACL 2026)
sec4dev 2020 – Automated Reasoning for System Security and Privacy
The (Un)Reliability of Reasoning in Frontier Models
AI Breakthroughs: Reasoning, Reliability, and Recommendations
Imbue CTO Josh Albrecht on Creating AI Agents for Reasoning, Reliability, and Robustness
The Future of Reliable IT: Automated Reasoning explained | Laura Kovacs | Wilhelm Exner Medal
The Big Lie About AI Reasoning: Why LLMs Are "Stateless" and Useless Alone
AI Reasoning Models in 2025: Tool Use, Reliability, and Safety Trade-offs
Safety in Large Reasoning Models: A Survey
Google Unveils Mangle – A Game-Changing AI Reasoning Language
Episode 187: Automated Reasoning Meets AI
View Detailed Profile
Reasoning about Reliability and Security Using Boolean Methods

Reasoning about Reliability and Security Using Boolean Methods

Detecting and correcting errors before run-time is increasingly important in today's ubiquitous computing environment. Decision ...

Reasoning Can Hurt LLM Safety?! Rethinking Accuracy in AI Systems (EACL 2026)

Reasoning Can Hurt LLM Safety?! Rethinking Accuracy in AI Systems (EACL 2026)

In this episode of #WiAIRpodcast, we dive into a subtle but critical question: Does adding

sec4dev 2020 – Automated Reasoning for System Security and Privacy

sec4dev 2020 – Automated Reasoning for System Security and Privacy

Speaker: Laura Kovacs In this talk Laura Kovacs will present recent advancement in automated

The (Un)Reliability of Reasoning in Frontier Models

The (Un)Reliability of Reasoning in Frontier Models

Chirag Agarwal presents the talk "The (Un)

AI Breakthroughs: Reasoning, Reliability, and Recommendations

AI Breakthroughs: Reasoning, Reliability, and Recommendations

In this episode, we dissect five cutting-edge research papers that are reshaping the AI landscape. We kick things off with a ...

Imbue CTO Josh Albrecht on Creating AI Agents for Reasoning, Reliability, and Robustness

Imbue CTO Josh Albrecht on Creating AI Agents for Reasoning, Reliability, and Robustness

In this episode, Nathan chats with Josh Albrecht, CTO of Imbue. They discuss how to create agents for

The Future of Reliable IT: Automated Reasoning explained | Laura Kovacs | Wilhelm Exner Medal

The Future of Reliable IT: Automated Reasoning explained | Laura Kovacs | Wilhelm Exner Medal

In this insightful talk from the Exner Lectures 2025, Laura Kovacs (TU Wien) explores the critical field of Automated

The Big Lie About AI Reasoning: Why LLMs Are "Stateless" and Useless Alone

The Big Lie About AI Reasoning: Why LLMs Are "Stateless" and Useless Alone

Title: Code as Agent Harness: The Future of Autonomous AI In this video, we explore a transformative perspective on AI ...

AI Reasoning Models in 2025: Tool Use, Reliability, and Safety Trade-offs

AI Reasoning Models in 2025: Tool Use, Reliability, and Safety Trade-offs

2025 AI tool-using models are more capable, but real-world

Safety in Large Reasoning Models: A Survey

Safety in Large Reasoning Models: A Survey

Paper PDF: http://arxiv.org/pdf/2504.17704v1 Check my merch: https://dragonprof-2.creator-spring.com Large

Google Unveils Mangle – A Game-Changing AI Reasoning Language

Google Unveils Mangle – A Game-Changing AI Reasoning Language

Google just introduced Mangle, a powerful new AI

Episode 187: Automated Reasoning Meets AI

Episode 187: Automated Reasoning Meets AI

... strong guarantees of

Triad Logic: Reliability Before Reasoning

Triad Logic: Reliability Before Reasoning

Triad Logic (TL) is a practical framework for keeping