AINewsnow

Reproducing a paper in Python: a random seed is only the first step

You follow a machine learning or experimental paper, run the code, and the loss curve or the reported metric doesn't match. You move the same script to another machine, and the numbers move again. The first guess is almost always: I forgot to set a random seed. So you add torch.manual_seed(0) , and…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-11-10 14:35 · DEV Community — Machine Learning
    Reproducing a paper in Python: a random seed is only the first step

More stories

  1. Anthropic launches Claude Fable 5.2 and Mythos 5.2 with coding gains and 20% price cut — Anthropic (X)
  2. Anthropic kicks off IPO roadshow targeting valuation of up to $1.4 trillion — Wall Street Journal Technology
  3. Nvidia CEO Jensen Huang Admits to Affair With Executive Alleged to Be Chinese Spy — Axios AI+
  4. Google DeepMind's AlphaProof Code Formally Verifies Signal Protocol Security — Google DeepMind Blog
  5. Google Cloud launches Gemini for healthcare to unify clinical data and automate workflows — Google Cloud AI Blog
  6. DeepSeek's Harness agent app reaches 1.54 million daily users — Bloomberg AI
  7. Meta expands AI age-estimation globally to extend Instagram Teen Account protections — Meta Newsroom
  8. Australia To Adopt 'Mandatory' AI Safeguards — Barron's

Get the daily brief of stories like this at 6:30 every morning →