EPISODE · Jun 19, 2026 · 15 MIN
Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum
from James Dooley Podcast · host James Dooley
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 EpisodePersonalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum is available across all major podcast platforms. Choose your preferred platform below.Listen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on TransistorListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Pocket CastsListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Amazon MusicListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on SpotifyListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on PodverseListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Pod.linkListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on CastroListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on CastboxListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Podcast AddictListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on DeezerListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Listen NotesListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Podcast GuruListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on PodchaserListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on StenoListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on MetacastListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Entity Home
What this episode covers
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 EpisodePersonalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum is available across all major podcast platforms. Choose your preferred platform below.Listen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on TransistorListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Pocket CastsListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Amazon MusicListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on SpotifyListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on PodverseListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Pod.linkListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on CastroListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on CastboxListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Podcast AddictListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on DeezerListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Listen NotesListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Podcast GuruListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on PodchaserListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on StenoListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on MetacastListen to Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum on Entity Home
NOW PLAYING
Personalizing LLMs: How Your ChatGPT & Gemini Differ | James Dooley x Benjamin Tannenbaum
No transcript for this episode yet
Similar Episodes
Mar 26, 2026 ·1m
Jan 2, 2026 ·47m
Dec 21, 2025 ·46m