Measurement

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Seth Wheeler

Oct 3

How a Pluralisation Rule Broke a Correct Answer

#codegeneration #measurement #python #verification

7 min read

Seth Wheeler

Oct 2

Taking the Language Model Out of a Build Planner

#measurement #llm #codegeneration #verification

8 min read

Seth Wheeler

Oct 1

A Ceiling That Was Measuring My Test Harness

#measurement #verification #codegeneration

8 min read

yutianle

Oct 1

Distributing the Risk: What Global Docker Exposure Numbers Do and Do Not Show

#docker #measurement #risk #zoomeye

3 min read

Dylan Merigaud

Sep 30

I Published a Perfect Recall. Then I Measured Dust.

#evals #measurement #python #docverification

7 min read

Seth Wheeler

Sep 30

Code Completion From Your Own Repository's Statistics

#codecompletion #statistics #node #measurement

5 min read

Seth Wheeler

Sep 29

Pinning What a Function Answers Across Rewrites and Time

#verification #python #measurement

4 min read

Seth Wheeler

Sep 27

Measuring How Cost Scales by Counting Instead of Timing

#measurement #statistics #python #node

5 min read

Zenovay

Sep 30

The 19-year visit that wasn't real

#analytics #measurement #engagement #engineering

3 min read

Seth Wheeler

Sep 26

A Curve Fitter That Refuses to Answer

#statistics #measurement #python #node

4 min read

Seth Wheeler

Sep 24

Breaking CI Guards on Purpose to Prove They Can Fail

#verification #python #measurement

4 min read

Seth Wheeler

Sep 21

A Determinism Check Has to Leave the Process

#python #verification #measurement

4 min read

Seth Wheeler

Sep 19

What Mutation Testing Frameworks Do When a Timeout Kills Them

#mutationtesting #verification #measurement

6 min read

Seth Wheeler

Sep 20

Ten Packages, One Rule: A Check Must Be Able to Fail

#verification #measurement #python #node

7 min read

Debashish Ghosal

Sep 13

My Extraction Score Was 0.08 and the Model Was Innocent: Rebuilding the Ruler

#ai #llm #measurement #agents

8 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.