We’re releasing Squiggle AI, a tool that generates probabilistic models using the Squiggle language. This can provide early cost-effectiveness models and other kinds of probabilistic programs.

No prior Squiggle knowledge is required to use Squiggle AI. Simply ask for whatever you want to estimate, and the results should be fairly understandable. The Squiggle programming language acts as an adjustable backend, but isn’t mandatory to learn.

Beyond being directly useful, we’re interested in Squiggle AI as an experiment in epistemic reasoning with LLMs. We hope it will help highlight potential strengths, weaknesses, and directions for the field.

Screenshots

---

Outline:

(00:44) Screenshots

(01:13) Motivation

(02:51) Description

(04:04) Example Outputs

(07:07) How Good Is It?

(08:52) Alternatives

(09:42) Using Squiggle AI

(11:24) Recommended Tips for Better Results

(13:00) Complementary Tools

(14:11) Privacy

(14:34) Technical Details

(14:37) Performance and Costs

(15:41) State Machine Details

(17:26) Conclusion

(17:54) Appendix: Lessons Learned During Development

(18:00) LLM cost-effective estimates seem tractable

(18:53) LLMs are willing to estimate more than you might expect, with some prompting

(19:41) Specialized Steps Improve Results

(20:25) It's difficult to make complex models understandable

(21:39) Prompt engineering can be a lot of work

The original text contained 1 image which was described by AI.

---

First published:

Source:

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.