Backpropagation

Tech Deep DiveOpenAILast reported March 2026High Frequency
Reported
10× across candidate reports
First seen
February 2025
Last reported
March 2026
Reported outcome
mixed

Problem Overview

An ML coding interview (typically 60–75 minutes) at OpenAI Research covering basic linear algebra and backpropagation. The 60-minute version uses Excalidraw (or similar whiteboard tool) plus CoderPad and requires NumPy and Python 3.7. It has two explicit components: (1) converting conceptual understanding of linear algebra and neural network training into…

  • 4 candidate-reported follow-ups — the exact probes interviewers asked, with the trigger for each
  • The rest of the problem statement — full requirements, constraints, and edge cases
  • Approach and trade-offs — what passing candidates did, and the mistakes that sink people
Unlock the full OpenAI catalog
Full problem statements, candidate-reported follow-ups, and walkthroughs — for every OpenAI question.
Unlock with Pro
Already a member? Sign in
Verified Source
Every question is reconstructed from multiple independent candidate reports. Verbatim follow-ups, not invented ones.
Codex Fact-Checked
Technical claims, formulas, and scale numbers are reviewed against primary sources.
Interviewer Follow-ups
The exact follow-ups reported by candidates, with the trigger that prompts each one — plus the mistakes that sink people.
Is this helpful?