Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

Building AI products — Benedict Evans

Jun 10, 2024 - ben-evans.com
The author discusses the limitations of language learning models (LLMs) like ChatGPT, emphasizing that they are probabilistic systems and not databases, hence they cannot provide precise factual answers. The author argues that while these models can provide answers that look good or are roughly right, they cannot be relied upon for completely accurate answers. The author suggests two ways to address this issue: treating it as a science problem, where the models will improve over time, or as a product problem, where the focus is on building useful mass-market products around these models.

The author further breaks down the product problem into two aspects: the product design communicating certainty when the model is inherently uncertain, and the product not indicating what kind of questions can be asked. The author suggests three approaches to tackle these issues: creating a general-purpose chatbot, narrowing down the product to a specific domain with a custom UI, or abstracting the input and output as functions within another thing. The author concludes by stating that while LLMs are a general-purpose technology, the best way to deploy them might be to unbundle them into single-purpose tools and experiences.

Key takeaways:

  • Generative AI models like ChatGPT are not databases and do not produce precise factual answers, they are probabilistic systems and cannot guarantee completely accurate answers.
  • There are two ways to solve the problem of AI inaccuracies: treating it as a science problem where models will get better over time, or treating it as a product problem where we build useful products around models that may get things wrong.
  • Product design can mislead users by communicating certainty when the model is inherently uncertain. The product should communicate what it can and can't do and what good questions might be.
  • There are different approaches to using AI: narrowing the product to a specific domain with a custom UI, or abstracting the input and output as functions inside some other thing. The latter approach allows the user to not know that this is generative AI at all.
View Full Article

Comments (0)

Be the first to comment!