Blog

Check out my LessWrong profile for a more up-to-date list of writings.

SLT for AI Safety

SLT for AI Safety

2025-07-01
Timaeus in 2024

Timaeus in 2024

2025-02-20
Jesse Hoogland, Stan van Wingerden, Alexander Gietelink Oldenziel, Daniel Murfet
Brainrot

Brainrot

2025-01-26

Timaeus is hiring researchers & engineers

2025-01-17
Jesse Hoogland, Stan van Wingerden
o1: A Technical Primer

o1: A Technical Primer

2024-12-09
New o1-like model (QwQ) beats Claude 3.5 Sonnet with only 32B parameters

New o1-like model (QwQ) beats Claude 3.5 Sonnet with only 32B parameters

2024-11-27
Timaeus is hiring!

Timaeus is hiring!

2024-07-12
Jesse Hoogland, Stan van Wingerden, Alexander Gietelink Oldenziel, Daniel Murfet
Stagewise Development in Neural Networks

Stagewise Development in Neural Networks

2024-03-20
Jesse Hoogland, Liam Carroll, Daniel Murfet

Timaeus's First Four Months

2024-02-28
Jesse Hoogland, Stan van Wingerden, Alexander Gietelink Oldenziel, Daniel Murfet
Generalization, from thermodynamics to statistical physics

Generalization, from thermodynamics to statistical physics

2023-11-30
Announcing Timaeus

Announcing Timaeus

2023-10-22
Jesse Hoogland, Daniel Murfet, Stan van Wingerden, Alexander Gietelink Oldenziel
You’re Measuring Model Complexity Wrong

You’re Measuring Model Complexity Wrong

2023-10-11
Jesse Hoogland, Stan van Wingerden

Open Call for Research Assistants in Developmental Interpretability

2023-08-30
Jesse Hoogland, Daniel Murfet, Stan van Wingerden, Alexander Gietelink Oldenziel

2023-Q2

2023-07-16
Towards Developmental Interpretability

Towards Developmental Interpretability

2023-07-12
Jesse Hoogland, Alexander Gietelink Oldenziel, Daniel Murfet, Stan van Wingerden
Approximation is expensive, but the lunch is cheap

Approximation is expensive, but the lunch is cheap

2023-04-19

2023-Q1

2023-04-11
Singularities against the Singularity: Announcing Workshop on Singular Learning Theory and Alignment

Singularities against the Singularity: Announcing Workshop on Singular Learning Theory and Alignment

2023-04-01
Jesse Hoogland, Alexander Gietelink Oldenziel, Daniel Murfet
Empirical risk minimization is fundamentally confused

Empirical risk minimization is fundamentally confused

2023-03-22
The shallow reality of 'deep learning theory'

The shallow reality of 'deep learning theory'

2023-02-22
Gradient surfing: the hidden role of regularization

Gradient surfing: the hidden role of regularization

2023-02-06
Spooky action at a distance in the loss landscape

Spooky action at a distance in the loss landscape

2023-01-28
Neural networks generalize because of this one weird trick

Neural networks generalize because of this one weird trick

2023-01-18

Beyond Bayes

2023-01-13

2022 Review

2023-01-08

2022-M11

2022-12-02

2022-M10

2022-10-31

2022-Q3

2022-10-01
No, human brains are not (much) more efficient than computers

No, human brains are not (much) more efficient than computers

2022-09-06
A Starter-kit for Rationality Space

A Starter-kit for Rationality Space

2022-09-01

2022-Q2

2022-08-05

2022-M2

2022-03-06

2022-M3

2022-03-06

2021 Review

2022-01-20

2022

2022-01-20

2022-M1

2022-01-01

2021-Q3

2021-10-02

2021-Q2

2021-07-12

2021

2021-02-26

Atomic SRS

2020-12-11

Why write?

2020-12-08

Reviews

1998-08-20