The BaseEssayLessWrong
Slouching Towards Interpretability: Thinking About Computation in Neural Networks
According to the excerpt, a LessWrong essay by CarolusRenniusVitellius, written under the Iliad Fellowship, says the author changed their view on how circuits relate to gradient descent and now argues for a clearer account of what computation in neural networks is.
Why it matters
The same thing, for different readers.
For researchers
A LessWrong author says the picture of circuits as units that resist gradient descent skips the harder question of how to define a circuit at all.
The record
- Questions
- Can AI systems act beyond what people intended or allowed?
- People
- CarolusRenniusVitellius (Wrote it)
- What we read
- We have read only the description the publisher gives. No quotations until someone reads the source itself.
- Found by
- The Radar, run of November 15, 2026, via
lesswrong(tier 1: the source’s own channel or an official record) - Cite this
- LessWrong, “Slouching Towards Interpretability: Thinking About Computation in Neural Networks”, November 15, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/lesswrong-2026-11-15-slouching-towards-interpretability
Our notesLight lane: excerpt only; the argument is summarised from its opening.