Latte & Learn: How Frontier LLMS Can Mislead Humans?
TOPIC: How Frontier LLMS Can Mislead Humans?
We host a weekly research paper study group, an intimate discussion session where researchers and builders come together to deep-dive into a research paper and spark meaningful conversations around a specific topic.
As part of our weekly research paper study group, this week we will discuss on a paper Frontier Models are Capable of In-context Scheming
Frontier AI models now show the ability to deceive, intentionally mislead, and pursue hidden goals, raising serious concerns about their safety and trustworthiness. In this intimate discussion session we will explore how these behaviors emerge and their implications for autonomous AI systems.
The Deep-Tech Community:
Our Mission: We help AI/ML and deep-tech researchers become founders by bringing the right people and resources together.
How we achieve that mission:
We achieve this by organizing weekly meetups, invite-only mixers, exclusive deep-tech intimate dinners, a research paper study group, a deep-tech leadership group, and The Deep-Tech House, a venture studio that is part of The Deep-Tech Community.
Who Joins Our Events
Researchers from renowned institutions such as Stanford, UC Berkeley, and other prestigious university labs.
CTOs and engineering leaders from various companies.
VCs with a keen interest in the deep-tech domain.