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, physics-constrained world models, and high-dimensional Bayesian inference…
- philosophy of science and mind in the light of the above, and
- survival tips, broadly construed, for wherever I am living.
You might be after information about me generally, or what I am doing right now.
☞ Show whimsical blog map
“Opponent shaping” as a model for manipulation and cooperation
adaptive
agents
bandit problems
bounded compute
collective knowledge
control
cooperation
distributed
economics
evolution
extended self
game theory
incentive mechanisms
learning
machine learning
mind
networks
utility
Australian authoritarianism
confidentiality
Southeast Asia
straya
wonk
Distributed community NN training
bounded compute
collective knowledge
concurrency hell
distributed
diy
economics
edge computing
extended self
faster pussycat
incentive mechanisms
innovation
language
machine learning
model selection
neural nets
NLP
optimization
premature optimization
statmech
technology
UI
Creating scientific knowledge
adaptive
bounded compute
collective knowledge
distributed
economics
how do science
incentive mechanisms
institutions
learning
mind
networks
provenance
sociology
standards
Building and Running Scientific Institutions
adaptive
bounded compute
collective knowledge
distributed
economics
how do science
incentive mechanisms
institutions
learning
mind
networks
provenance
sociology
standards
A Scientist's Survival Guide
academe
adaptive
collective knowledge
diy
how do science
mind
Degrees of freedom in NNs
estimator distribution
information
likelihood
model selection
statistics
The deep history of intelligence
adversarial
AI safety
catastrophe
economics
faster pussycat
innovation
language
machine learning
mind
neural nets
NLP
security
technology
Quasi-gradients of discrete parameters
calculus
classification
optimization
probabilistic algorithms
probability
score function
statistics
Discretizing and quantizing neural nets
edge computing
machine learning
model selection
neural nets
sparser than thou
Foundation models for geoscience
dynamical systems
machine learning
neural nets
sciml
SDEs
signal processing
spatial
stochastic processes
time series
Fine tuning foundation models
adaptive
agents
approximation
bandit problems
Bayes
control
generative
incentive mechanisms
language
learning
machine learning
meta learning
networks
neural nets
NLP
optimization
stochastic processes
stringology
time series
utility
Conditioning neural denoising diffusion models
approximation
Bayes
generative
Monte Carlo
neural nets
optimization
probabilistic algorithms
probability
score function
statistics
Backprop-free methods for training neural networks
Bayes
dynamical systems
likelihood free
linear algebra
machine learning
Monte Carlo
neural nets
nonparametric
particle
probability
sciml
signal processing
sparser than thou
statistics
statmech
uncertainty
Numerical Python
compsci
computers are awful
premature optimization
python
Architecture and construction (doing it)
design
the rather superior sort of city
cooperation
culture
diy
economics
housing
making things
Utopian governance
economics
extended self
incentive mechanisms
institutions
markets
money
wonk
Democratization of generative AI
agents
bounded compute
collective knowledge
concurrency hell
distributed
economics
edge computing
extended self
faster pussycat
incentive mechanisms
innovation
language
machine learning
neural nets
NLP
technology
UI
Cooperation in evolutionary context
adaptive
cooperation
culture
economics
evolution
gene
incentive mechanisms
wonk
Explorables and interactives
academe
communicating
computers are awful
data sets
dataviz
faster pussycat
generative art
how do science
learning
making things
mind
number crunching
photon choreography
statistics
UI
workflow
Zotero
academe
collective knowledge
computers are awful
faster pussycat
how do science
workflow
Innovation
economics
innovation
intellectual property
making things
policy
sociology
spatial
technology
the rather superior sort of city
The Predictive Approach to Bayesian Inference
Bayes
how do science
likelihood free
probability
statistics
Neural Bayes posteriors
Bayes
convolution
density
how do science
likelihood free
machine learning
neural nets
nonparametric
sparser than thou
statistics
uncertainty
Big history
adaptive
collective knowledge
economics
evolution
game theory
networks
social graph
sociology
Singular Learning Theory
AI safety
dynamical systems
machine learning
neural nets
physics
pseudorandomness
sciml
statistics
statmech
stochastic processes
Multi-level agency
agents
AI safety
bounded compute
collective knowledge
computers are awful together
concurrency hell
distributed
economics
edge computing
extended self
game theory
incentive mechanisms
machine learning
networks
Models of human cultural reproduction
adaptive
collective knowledge
economics
evolution
game theory
networks
social graph
sociology
Android hacks
computers are awful
portable
Internet for the occasionally online
computers are awful
computers are awful together
confidentiality
distributed
diy
economics
Betting and prediction markets
catastrophe
economics
how do science
incentive mechanisms
markets
probability
tail risk
Common knowledge/shared knowledge
bandit problems
cooperation
culture
democracy
economics
ethics
mind
rhetoric
snarks
sociology
wonk
Worker- and founder-ownership
economics
ethics
incentive mechanisms
institutions
markets
money
Innovation, science, technology research in Australia
how do science
policy
straya
wonk
Inductive biases
functional analysis
how do science
meta learning
model selection
optimization
statmech
Configuring machine learning experiments
computers are awful
faster pussycat
how do science
premature optimization
provenance
python
Retirement saving in Australia
diy
economics
money
Southeast Asia
utility
Dilemmas of collective action
bounded compute
distributed
economics
game theory
networks
squad
wonk
World models arising in foundation models.
approximation
Bayes
generative
language
machine learning
meta learning
Monte Carlo
neural nets
NLP
optimization
probabilistic algorithms
probability
statistics
stringology
time series
AI persuasion, AI manipulation
adversarial
AI safety
bounded compute
communicating
cooperation
culture
economics
faster pussycat
language
machine learning
mind
neural nets
NLP
security
technology
wonk
Spamularity
adversarial
AI safety
bounded compute
communicating
cooperation
culture
economics
faster pussycat
language
machine learning
mind
neural nets
NLP
security
technology
wonk
Image file formats
computers are awful
generative art
making things
photon choreography
Probabilistic neural nets
Bayes
convolution
density
likelihood free
machine learning
neural nets
nonparametric
sparser than thou
uncertainty
Procedurally generated diagrams
communicating
computers are awful
dataviz
faster pussycat
photon choreography
plain text
typography
UI
workflow
Configuring machine learning experiments with Fiddle
computers are awful
faster pussycat
how do science
premature optimization
provenance
python
No matching items