Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678

Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678

Today we're joined by Jonas Geiping, a research group leader at the ELLIS Institute, to explore his paper: "Coercing LLMs to Do and Reveal (Almost) Anything". Jonas explains how neural networks can be exploited, highlighting the risk of deploying LLM agents that interact with the real world. We discuss the role of open models in enabling security research, the challenges of optimizing over certain constraints, and the ongoing difficulties in achieving robustness in neural networks. Finally, we delve into the future of AI security, and the need for a better approach to mitigate the risks posed by optimized adversarial attacks. The complete show notes for this episode can be found at twimlai.com/go/678.

Avsnitt(778)

LLMs for Equities Feature Forecasting at Two Sigma with Ben Wellington - #736

LLMs for Equities Feature Forecasting at Two Sigma with Ben Wellington - #736

Today, we're joined by Ben Wellington, deputy head of feature forecasting at Two Sigma. We dig into the team’s end-to-end approach to leveraging AI in equities feature forecasting, covering how they i...

17 Juni 202559min

Zero-Shot Auto-Labeling: The End of Annotation for Computer Vision with Jason Corso - #735

Zero-Shot Auto-Labeling: The End of Annotation for Computer Vision with Jason Corso - #735

Today, we're joined by Jason Corso, co-founder of Voxel51 and professor at the University of Michigan, to explore automated labeling in computer vision. Jason introduces FiftyOne, an open-source platf...

10 Juni 202556min

Grokking, Generalization Collapse, and the Dynamics of Training Deep Neural Networks with Charles Martin - #734

Grokking, Generalization Collapse, and the Dynamics of Training Deep Neural Networks with Charles Martin - #734

Today, we're joined by Charles Martin, founder of Calculation Consulting, to discuss Weight Watcher, an open-source tool for analyzing and improving Deep Neural Networks (DNNs) based on principles fro...

5 Juni 20251h 25min

Google I/O 2025 Special Edition - #733

Google I/O 2025 Special Edition - #733

Today, I’m excited to share a special crossover edition of the podcast recorded live from Google I/O 2025! In this episode, I join Shawn Wang aka Swyx from the Latent Space Podcast, to interview Logan...

28 Maj 202526min

RAG Risks: Why Retrieval-Augmented LLMs are Not Safer with Sebastian Gehrmann - #732

RAG Risks: Why Retrieval-Augmented LLMs are Not Safer with Sebastian Gehrmann - #732

Today, we're joined by Sebastian Gehrmann, head of responsible AI in the Office of the CTO at Bloomberg, to discuss AI safety in retrieval-augmented generation (RAG) systems and generative AI in high-...

21 Maj 202557min

From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731

From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731

Today, we're joined by Mahesh Sathiamoorthy, co-founder and CEO of Bespoke Labs, to discuss how reinforcement learning (RL) is reshaping the way we build custom agents on top of foundation models. Mah...

13 Maj 20251h 1min

How OpenAI Builds AI Agents That Think and Act with Josh Tobin - #730

How OpenAI Builds AI Agents That Think and Act with Josh Tobin - #730

Today, we're joined by Josh Tobin, member of technical staff at OpenAI, to discuss the company’s approach to building AI agents. We cover OpenAI's three agentic offerings—Deep Research for comprehensi...

6 Maj 20251h 7min

CTIBench: Evaluating LLMs in Cyber Threat Intelligence with Nidhi Rastogi - #729

CTIBench: Evaluating LLMs in Cyber Threat Intelligence with Nidhi Rastogi - #729

Today, we're joined by Nidhi Rastogi, assistant professor at Rochester Institute of Technology to discuss Cyber Threat Intelligence (CTI), focusing on her recent project CTIBench—a benchmark for evalu...

30 Apr 202556min

Populärt inom Politik & nyheter

p3-krim
svenska-fall
rss-krimstad
flashback-forever
motiv
rss-viva-fotboll
spar
rss-sanning-konsekvens
aftonbladet-daily
aftonbladet-krim
rss-krimreportrarna
olyckan-inifran
rss-frandfors-horna
rss-vad-fan-hande
fordomspodden
dagens-eko
rss-flodet
politiken
svd-ledarredaktionen
blenda-2