Aug 22, 2026

Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov

A paper by Ilia Shumailov and Alexander Panfilov exposes a critical vulnerability in proprietary LLM APIs: encrypted reasoning traces, returned for conversation state management, can be extracted and replayed. This enables universal jailbreaking, privacy leaks of sensitive user data, and poisoning of AI agent traces. The study highlights significant implications for AI safety, model monitorability due to opaque internal reasoning, and even subtle forms of "distillation" where smaller models mimic frontier ones. The discussion covers architectural and system-level defenses, advocating for rigorous scientific inquiry in AI safety research.

Jul 11, 2026

State of the Union: Why Local, Why Now — NVIDIA, Osmantic, Roboflow, EXO Labs, @matthew_berman

This panel discussion explores the inflection point of Local AI, driven by advanced models, improved hardware, and a robust ecosystem. Experts discuss how this shift addresses critical concerns around privacy, cost, sovereignty, and resilience, emphasizing the pivotal role of open-source AI and specialized models. They delve into technical optimizations, the evolution from generalized to specialized AI, and the challenges of making local AI accessible and performant for both enterprise and individual users.

Apr 02, 2026

How Bots, Deepfakes and AI Agents Are Forcing a New Internet Identity Layer | Alex Blania on a16z

Alex Blania, cofounder and CEO of Tools for Humanity (Worldcoin), details the critical challenge of proving human uniqueness in the AI era. He explains Worldcoin's iris biometric approach, its sophisticated privacy architecture using Multi-Party Computation and Zero-Knowledge Proofs, and the pervasive impact of AI agents and deepfakes on social media, dating, gaming, and government. Blania also outlines Worldcoin's strategy to scale this proof-of-human network globally, particularly in the US.

Feb 09, 2026

Episode 13 - The Thinking Behind Ads in ChatGPT

Asad Awan from OpenAI details the company's principled approach to introducing ads in ChatGPT. He explains how user trust, privacy, and control are prioritized, ensuring a strict separation between model answers and advertisements, and outlines a future where AI simplifies advertising for businesses.

Oct 17, 2025

IronDict: Transparent Dictionaries from Polynomial Commitments

Hossein Hafezi from NYU presents IronDict, a novel transparent dictionary construction using polynomial commitment schemes. IronDict addresses the major limitations of existing Merkle tree-based systems, such as high auditing costs and imperfect privacy. By modeling the dictionary with polynomials and leveraging the algebraic properties of the KZH commitment scheme, IronDict achieves perfect privacy and dramatically reduces auditing overhead, making it feasible for end-users to verify the system's integrity on consumer devices.

Oct 17, 2025

Efficient Secure Aggregation for Federated Learning

Varun Madathil from Yale University presents Tacita, a novel, single-server protocol for secure aggregation in Federated Learning (FL). Tacita is designed to address the unique constraints of the FL environment, such as client dropouts and the absence of client-to-client communication. The protocol achieves one-shot execution with constant-size communication and robustness against dropouts by introducing two new cryptographic primitives: succinct multi-key linearly homomorphic threshold signatures (MKLHTS) and a homomorphic variant of Silent Threshold Encryption.