Welcome to Dan’s brain
The contents of my head are not useful if they stay in there, so I regularly copy-paste them onto the internet, into this very website. Here you can find most of the things I am thinking about, in the form of a higgledy heap of half-finished notebooks and occasional polished essays. Themes include whatever shiny thing distracted me into taking notes about it, including, but not limited to,
- statistical inference in areas I am interested in such as pragmatics of reasoning machines physical models, and high-dimensional Bayesian inference…
- philosophy of science and consciousness etc in the light of the above,
- survival tips, broadly construed, for wherever I am living, and
You might be after information about me generally, or what I am doing right now.
☞ Show whimsical blog map
Generative art with language+diffusion models
buzzword
computers are awful
generative art
machine learning
making things
music
neural nets
photon choreography
UI
Code generation, programming assistants
faster pussycat
language
machine learning
making things
neural nets
NLP
signal processing
stringology
UI
Neural nets that do symbolic mathematics, logic and other reasoning tasks
compsci
language
machine learning
meta learning
networks
neural nets
NLP
stringology
Syncthing
computers are awful
computers are awful together
concurrency hell
distributed
diy
P2P
Causal abstraction
approximation
Bayes
causal
generative
graphical models
language
machine learning
meta learning
neural nets
NLP
probabilistic algorithms
probability
statistics
stringology
time series
Mechanistic interpretability
adversarial
classification
communicating
feature construction
statmech
stochastic processes
high d
language
machine learning
metrics
mind
NLP
sparser than thou
Developmental interpretability
adversarial
Bayes
classification
dynamical systems
feature construction
high d
language
machine learning
metrics
mind
NLP
sparser than thou
statmech
stochastic processes
uv, the python package manager
computers are awful
python
standards
Python packaging, environment and dependency management
computers are awful
python
standards
Research discovery and synthesis
academe
collective knowledge
faster pussycat
how do science
institutions
mind
networks
provenance
sociology
wonk
Pip-like python environment management
computers are awful
python
standards
Multi agent causality
adaptive
agents
causal
cooperation
economics
evolution
extended self
game theory
graphical models
incentive mechanisms
learning
mind
networks
social graph
utility
wonk
Neural PDE operator learning on domains with interesting geometry
calculus
dynamical systems
geometry
Hilbert space
how do science
Lévy processes
machine learning
neural nets
PDEs
physics
regression
sciml
SDEs
signal processing
statistics
statmech
stochastic processes
surrogate
time series
uncertainty
Neural PDE operator learning
Especially forward operators. Image-to-image regression, where the images encode a physical process.
calculus
dynamical systems
geometry
Hilbert space
how do science
Lévy processes
machine learning
neural nets
PDEs
physics
regression
sciml
SDEs
signal processing
statistics
statmech
stochastic processes
surrogate
time series
uncertainty
The AI tech soap opera
agents
bounded compute
collective knowledge
economics
edge computing
extended self
faster pussycat
incentive mechanisms
innovation
language
machine learning
neural nets
NLP
swarm
technology
UI
when to compute
Feed readers
academe
computers are awful together
doing internet
faster pussycat
learning
provenance
UI
workflow
Learning with conservation laws, invariances and symmetries
algebra
how do science
information
machine learning
networks
physics
probability
sciml
statistics
statmech
Git tricks
computers are awful
provenance
workflow
Human domestication
agents
cooperation
culture
distributed
economics
evolution
extended self
incentive mechanisms
language
mind
utility
wonk
Causality, agency, decisions
adaptive
agents
causal
cooperation
economics
evolution
extended self
game theory
graphical models
incentive mechanisms
learning
mind
networks
social graph
utility
wonk
Aligning AI systems
adversarial
classification
communicating
feature construction
game theory
high d
language
machine learning
metrics
mind
NLP
Conda-like Python environments
computers are awful
python
standards
Poetry, the python package manager
computers are awful
python
standards
Contemporary rationalists
catastrophe
culture
ethics
history
language
mind
wonk
Leadership
incentive mechanisms
institutions
mind
wonk
Reading ebooks
academe
computers are awful
faster pussycat
learning
provenance
UI
workflow
Computational complexity of Bayesian inference
Bayes
how do science
statistics
Neural PDE operator learning using transformers
calculus
dynamical systems
geometry
Hilbert space
how do science
Lévy processes
machine learning
neural nets
PDEs
physics
regression
sciml
SDEs
signal processing
statistics
statmech
stochastic processes
surrogate
time series
uncertainty
Adaptive design of experiments
functional analysis
how do science
model selection
optimization
surrogate
when to compute
Australia in data
data sets
place
Southeast Asia
straya
Data sets for machine learning for partial differential equations
calculus
data sets
dynamical systems
geometry
machine learning
neural nets
PDEs
physics
regression
sciml
SDEs
signal processing
statistics
statmech
stochastic processes
surrogate
time series
Causal Bayesian networks via probability trees
algebra
causal
graphical models
how do science
machine learning
measure
networks
probability
statistics
Inference from disorder
causal
compsci
dynamical systems
networks
physics
probability
pseudorandomness
statistics
statmech
stochastic processes
Garbled highlights from ICLR 2025
neural nets
South East Asia
statistics
Artificial agency
adaptive
agents
cooperation
economics
evolution
extended self
game theory
incentive mechanisms
learning
mind
networks
utility
wonk
Neural codecs and compression algorithms
compsci
computers are awful
information
metrics
music
photon choreography
standards
Machine learning for partial differential equations via flows
calculus
dynamical systems
geometry
Hilbert space
how do science
Lévy processes
machine learning
neural nets
PDEs
physics
regression
sciml
SDEs
signal processing
statistics
statmech
stochastic processes
surrogate
time series
uncertainty
Machine learning for partial differential equations using diffusion models
calculus
dynamical systems
geometry
Hilbert space
how do science
Lévy processes
machine learning
neural nets
PDEs
physics
regression
sciml
SDEs
signal processing
statistics
statmech
stochastic processes
surrogate
time series
uncertainty
Causal inference on DAGs
algebra
causal
graphical models
how do science
machine learning
networks
probability
statistics
Scaling laws for very large neural nets
bounded compute
functional analysis
machine learning
model selection
optimization
statmech
when to compute
The simplest thing
culture
economics
faster pussycat
institutions
mind
networks
standards
Bayesian and causal inference by foundation models
approximation
Bayes
causal
generative
language
machine learning
meta learning
Monte Carlo
neural nets
NLP
optimization
probabilistic algorithms
probability
statistics
stringology
time series
Neural denoising diffusion models
approximation
Bayes
generative
Monte Carlo
neural nets
optimization
probabilistic algorithms
probability
score function
statistics
Data summarization
approximation
estimator distribution
functional analysis
information
linear algebra
model selection
optimization
probabilistic algorithms
probability
signal processing
sparser than thou
statistics
when to compute
Extraversion
communicating
cooperation
gene
health
learning
mind
neuron
personality
utility
ML benchmarks and their pitfalls
economics
game theory
how do science
incentive mechanisms
institutions
machine learning
neural nets
statistics
Causal inference under feedback
algebra
causal
graphical models
how do science
machine learning
networks
neural nets
probability
statistics
No matching items