Episode Details

Back to Episodes
Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum

Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum

Episode 332 Published 4 weeks ago
Description

James Dooley speaks with Benjamin Tannenbaum from AISO about the personalisation of large language models and why identical prompts in ChatGPT, Gemini and other AI search systems can produce different answers. Benjamin Tannenbaum explains the difference between true personalisation and simple probabilistic variability, showing how response volatility often comes from token selection rather than user history. The conversation breaks down location signals, memory settings, login state, and how query fan out becomes weighted by personal attributes. They also explore why personalisation can reduce randomness by narrowing candidate sets, how share of voice replaces fixed rankings in AI visibility tracking, and why optimising for LLMs increases probability rather than guaranteeing deterministic results.


Where to Listen to This Episode

Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum is available across all major podcast platforms. Choose your preferred platform below.

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

 Support Us