from Hacker News

Finding Signal in the Noise: Machine Learning and the Markets (Jane Street)

by lewiscarson on 3/14/25, 11:10 AM with 146 comments

  • by czhu12 on 3/16/25, 1:24 AM

    Been following signals and threads for a while, and it’s amazing. Have to be in a learning mood, but it gets pretty technical. Podcasts are a tough medium to do that in but if you really zone in, signals and threads is fantastic
  • by laidoffamazon on 3/16/25, 1:48 AM

    > In Young Cho thought she was going to be a doctor but fell into a trading internship at Jane Street

    Genuinely perplexing how they always try to show each multi-million earning engineer as some normal person and not someone that went to Exeter and Harvard

  • by hardwaregeek on 3/16/25, 2:06 AM

    I love this podcast but I can’t listen to it while running. It’s too interesting so I risk falling off the treadmill :D
  • by polygot on 3/16/25, 5:28 AM

    Very interesting podcast, I find that the guest was very candid so it was great to hear what it is really like working at Jane Street.

    The reproducible-Python notebook problem/notebook for researchers mentioned in the podcast inspired me to create a new project, branch-pad https://github.com/alexyorke/branch-pad which is an interactive Python notebook environment that allows you to create and explore multiple branches of code execution.

  • by brcmthrowaway on 3/16/25, 1:55 AM

    Ten years ago, all the $1mn+ earning engineers were in trading. Now they are in LLM/AI. Glad to see this happen, Jane Street has increased their advertising here because of this.
  • by __mharrison__ on 3/16/25, 3:02 AM

    I read this and think: "I would love to spend a day with Jane Street and teach them how to use notebooks." So much effort is wasted because of knowledge gaps or systems that don't encourage best practices.

    I just taught a course to a client this week helping them with this (and other best practices for Python).

  • by 1oooqooq on 3/16/25, 10:34 AM

    Keynesian for machines
  • by mhh__ on 3/16/25, 4:09 PM

    Notebooks: just use Marimo. They've fixed python notebooks.
  • by Workaccount2 on 3/16/25, 1:48 AM

    I will eternally find it sad how much talent is wasted on trading. So much money, so much intelligence, so much time and effort, all the provide almost no tangible value to society.