09/28/24: Hacking an LLM Using the Z3 Theorem Prover with Ian Bicking

Boston Computation Club
28/09/2024 54 min

Listen "09/28/24: Hacking an LLM Using the Z3 Theorem Prover with Ian Bicking"

Descargar episodio Ver en sitio original

Episode Synopsis

Ian Bicking is an engineer at Brilliant, which is also what he is. (Sorry, dad joke). Ian joined us today to talk about his super charming (and extremely interesting) weekend of experiments hacking various LLMs to solve puzzles using z3. The presentation was roughly the first 2/3 of the event and the remaining third presented a fantastic conversation about the future of AI, tool use, chain and tree of thought, o1, and more. Thanks again for joining us Ian!

More episodes of the podcast Boston Computation Club

Infecting Generative AI with Viruses - David A. Noever and Forrest McKee 15/09/2025
08/15/25: An LLM Agent for Functional Bug Detection in Network Protocols with Mingwei Zheng 15/08/2025
08/01/25: Formal Reasoning Meets LLMs: Toward AI for Mathematics and Verification with Kaiyu Yang 02/08/2025
07/25/25: RefinedC: Automating the Foundational Verification of C Code with Refined Ownership Types with Michael Sammler 25/07/2025
06/20/25: TypeScript Types Can Run DOOM with Dimitri Mitropoulos 22/06/2025
06/13/25: Gradual Verification with Jenna DiVincenzo 14/06/2025
05/07/25: Exploring Zero-Shot Prompting for Generating Data Format Descriptions, Prashant Anantharaman 08/05/2025
04/18/25: Descriptive Complexity with Ramit Das 19/04/2025
03/21/24: How and Why to extend First Order Logic for Knowledge-Based Systems with Marc Denecker 05/04/2025
04/04/25: Constrained Decoding for Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars with Daniel Melcer 05/04/2025
© 2003-2025 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA