sk8ordie84

404 bio not found

Joined on Apr 20, 2026 http://www.falsify.dev

sk8ordie84

May 29

Model cards vs pre-registration: what counts as evidence under the EU AI Act

#machinelearning #compliance #ai #mlops

4 min read

Want to connect with sk8ordie84?

Create an account to connect with sk8ordie84. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

sk8ordie84

May 29

Lock #2: the first thing PRML falsified was its own distribution hypothesis

#machinelearning #opensource #compliance #ai

2 min read

sk8ordie84

May 21

I audited our CMS and 86% of our articles were invisible. A Sanity gotcha.

#sanity #nextjs #webdev #debugging

4 min read

sk8ordie84

May 4

What writing the same spec in four languages taught me about YAML

#showdev #opensource #machinelearning #rust

5 min read

sk8ordie84

May 1

"I implemented PRML in two languages. Three things broke that the spec didn't warn about." published: true

#javascript #opensource #ai #machinelearning

6 min read

sk8ordie84

May 1

Why ML accuracy numbers are unfalsifiable, and what a 1287-line Python tool does about it" published: false

#machinelearning #ai #python #opensource

7 min read

sk8ordie84

Apr 29

I built a CLI that hashes your ML accuracy claims before the experiment runs

#showdev #python #machinelearning #opensource

4 min read

sk8ordie84

Apr 20

I built a film camera simulator in a single HTML file here's how

#showdev #javascript #webdev #canvas

1 min read

DEV Community

sk8ordie84

Badges

Writing Debut

Model cards vs pre-registration: what counts as evidence under the EU AI Act

Want to connect with sk8ordie84?

Lock #2: the first thing PRML falsified was its own distribution hypothesis

I audited our CMS and 86% of our articles were invisible. A Sanity gotcha.

What writing the same spec in four languages taught me about YAML

"I implemented PRML in two languages. Three things broke that the spec didn't warn about." published: true

Why ML accuracy numbers are unfalsifiable, and what a 1287-line Python tool does about it" published: false

I built a CLI that hashes your ML accuracy claims before the experiment runs

I built a film camera simulator in a single HTML file here's how