---
title: "Tinkering with LLMs"
description: "Explore key challenges of building AI chatbots: data privacy, response rates, latency impact, and UX tradeoffs. Real insights from VC experimentation with LLMs."
categories: ["AI","product"]
keywords: ["Tomasz Tunguz","Theory Ventures","AI chatbots","LLMs","machine learning","data privacy","user experience","response rates","SaaS","technology innovation"]
ai_summary: "Explore challenges in building AI chatbots, focusing on data privacy, response rates, and user experience tradeoffs."
date: 2023-05-08
lastmod: 2026-07-27
canonical_url: https://www.tomtunguz.com/llm-tinkering/
author: "Tomasz Tunguz"
---

I've been tinkering with [LLMs](https://en.wikipedia.org/wiki/Large_language_model).

First, I created a chatbot using all my blog posts. Then I created a model to produce blog entries based on my writing.

As I went through this process, I asked myself some questions along the way : 

- Does the ML model ingest my posts & keep them? What if I'd like to remove them from the logs or training set or output for others?
- The blogbot often returned no answers for questions I thought would be straightforward. How can I ensure the response rate is 99%+ before launching?
- Which post is better : hand-written, ChatGPT, or custom-trained models? How would I judge? More views? Written in my voice with alliteration & [rhetoric](https://tomtunguz.com/words-like-loaded-pistols/)? Use of the [& instead of "and"](https://tomtunguz.com/the-missing-letter/)? Injects links to other related posts?
- When is a blogbot a better user experience than search? With search, I can know that I've plumbed the depths of the blog, looking at every relevant post for an answer. How do I do that with a bot?
- The latency for both is significant : 5 to 25 seconds depending on the query. Google observed [400ms increase in latency decreases traffic by 20%](https://arxiv.org/pdf/2101.09086.pdf#:~:text=In%20a%20similar%20vein%2C%20Google,and%20diminished%20traffic%20by%2020%25.). Will users be more patient with bots than with search?
- What if I reimagined the home page of tomtunguz.com as a chatbot interface rather than a list of all posts? That UI would personalize the experience for each visitor & each session, but it would hamper browsing? Which is the more important use case?

I imagine many product teams are asking analogous questions about how to leverage these new models. 

Within the answers to those questions lies business opportunity for startups - enabling product & engineering teams to build new product experiences with confidence.