Summary

Can LLMs science? The answer to this question can tell us important things about timelines to AGI. In this small pilot experiment, we test frontier LLMs on their ability to perform a minimal version of scientific research, where they must discover a hidden rule about lists of integers by iteratively generating and testing hypotheses. Results are ambiguous: they're mostly pretty bad at it but top systems show apparent signs of life. We're working on a larger, more rigorous experiment in progress and we really want your input.

Structure

In this post we:

• Describe an experiment on general reasoning and scientific research ability in LLMs.
• Describe the main research project for which this is a pilot project.
• Ask for your predictions on the outcome of the main project and what you believe it will say about general reasoning in LLMs.

This is followed by appendices with more detail [...]

---

Outline:

(00:06) Summary

(00:45) Structure

(01:17) Introduction

(02:36) The experiment

(05:53) Results

(08:41) Full experiment (in progress)

(08:46) Key advantages over the pilot

(09:40) Procedure

(12:23) What we want from you

(14:26) Conclusion

(16:56) Appendices

(17:05) A. Acknowledgments

(17:31) B. Related work

(19:06) C. Limitations

(20:40) D. Full list of tested rules

(22:17) E. Full prompt

(25:15) F. Minimal human baseline

(25:53) G. Example successes and failures

(26:04) Example of success

(47:40) Example of failure

The original text contained 7 footnotes which were omitted from this narration.

The original text contained 2 images which were 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.