Episode Details

Summary: One area we plan to explore at Resolution is personas and character training, operationalized as finding and controlling low-dimensional structure in models that emerges in pretraining and flows through post-training to superintelligence. The hope is to expand and systematize phenomena such as emergent misalignment, subliminal learning, and other empirical persona research, then intervene on this structure without accidentally hiding undesirable behavior elsewhere. If this approach resonates with you, considering working with us.

Glimmers of low-dimensional structure

Our understanding of AI training and alignment as a field is very poor. If sufficient alignment of superintelligent AI agents requires pinning down the precise meaning of alignment and turning that meaning into high-accuracy training data and algorithms, we are likely to fail. Modern LLMs have trillions of parameters: our understanding is unlikely to be sufficient to pin down a trillion separate numbers.

Happily, there is a growing literature on such low-dimensional structure in AI models, showing that intervening on one aspect of model behavior has strong downstream effects on other aspects:

Topic

Description

Emergent misalignment

Betley et al. 2025 found that LLMs fine-tuned to output insecure code can become broadly misaligned across many other behaviors. MacDiarmid et al. 2025 found [...]

---

Outline:

(00:42) Glimmers of low-dimensional structure

(03:57) Intervening without hiding the structure

(06:34) Toy models of modern training

(09:03) Pretraining structure → superintelligent structure

(12:01) Different AI labs take different approaches

(15:08) Conclusion

(15:56) Acknowledgements

---

First published:
July 30th, 2026

Source:
https://www.lesswrong.com/posts/sFhW3ZnPMJdnB4Dd6/thousand-dimensional-structure-1

---

Narrated by TYPE III AUDIO.

---

Images from the article:

---

---

Apple Podcasts and Spotify do not show images in the episode description. Try

Listen Now