Latest Interviews

Trustworthy Human-AI Collaboration in a Live Type-Theoretic Computational Commons

Cyrus Omar

Hazel addresses the "gap problem" in traditional programming by implementing a live execution environment that uses visual "holes" for error recovery and instant probes to provide immediate feedback on code changes. The system enforces a pure functional design with incremental memoization to enable real-time data flow analysis, while integrating advanced security measures like object capabilities and formal verification to safely coordinate human-AI collaboration. Future iterations aim to solve scalability challenges in multi-agent development through content-addressed versioning and semantic models, ultimately supporting a computational commons where code and data evolve together in a shared, verifiable state.

Dwarkesh Goes Inside Jane Street's Latest AI Data Center

Dwarkesh, Ron Minsky, Daniel Pontecorvo, Mark Mirchandani

Jane Street transformed a Texas data center into a high-density liquid-cooled facility housing 4,032 GPUs to execute large language model training and custom trading architectures. The retrofit replaces legacy air-cooling with an 18°C fluid distribution system that manages 140 kW per cabinet while utilizing proprietary software to dynamically redistribute power and prevent breaker trips during peak loads. Engineering safeguards now focus on mitigating new liquid-cooling risks like biological growth and leaks, enabling sub-100-nanosecond latency required for modern algorithmic trading compared to the millisecond scales of its historical "Hive" cluster.

Effective Programming: Adding an Effect System to OCaml

This presentation details a comprehensive framework for algebraic effects that separates effect specification from implementation by treating operations like concurrency and state as explicit, resumable interruptions. It contrasts this approach with traditional monads to eliminate boilerplate and demonstrates a full conversion of the OCaml standard library, introducing syntax for tracking purity, region-based locality, and effect polymorphism directly in the type system. The work culminates in a runtime model where effect handlers manage heap-allocated call stacks while future extensions aim to enforce region safety and support multi-handler compositions for complex scenarios.