Stories

Complex, but Robust Human Moral Decisions from Moral Machine

Article news.ycombinator.com

Complex, but Robust Human Moral Decisions from Moral Machine

Consider a dataset D', which is a noisier version of 'ground truth' dataset D. If this dataset is sufficiently large, a model can be trained on it and be a better estimate of D than D' itself.

I applied this in cognitive science in graduate school [1] [2]. We would train a machine learning model on a large behavioral dataset (e.g. Moral Machine [3]), and then compare this ML model with a choice model (read: logistic regression) and identify residuals which we would use to featurize the choice model.

This let us find some complex, but robust empirical phenomena:

1. Age of Responsibility

Consider the dilemma when choosing to save an old person versus a child (gender matched). Similarly, consider the dilemma when choosing to save an old person plus an adult versus a child plus an adult. A linear utility model considers these two dilemmas to be equivalent. Do people?

They do when the young side is crossing legally or there is no crossing signal. But, when it's just the child crossing illegally, they are not penalized as much as a child and an adult crossing illegally. This is controlled when changing car side and gender. This suggests some preferential moral status of kids, in line with many legal norms.

2. Asymmetric Notions of Responsibility

Now, consider choosing between a high-value individual versus a low-value individual. By the Moral Machine standards, two axes of value are woman-man and fit-fat. Consider three scenarios when heading towards the high-valued individual.

a. The high-value individual is crossing legally.

b. There is no crossing signal

c. The high-value individual is crossing illegally.

Interestingly, the empirical proportion of (b) is the mean of (a) and (c).

However, this does not generalize when the car is headed towards the low-value individual. In that case, the lower-valued individual is saved at a rate almost identical to when they are crossing illegally. This suggests some type of motivated reasoning.

We applied a similar methodology to build an integrative theory of risky choice that combines prospect theory and expected utility theory [2].

[1] https://www.pnas.org/doi/full/10.1073/pnas.1915841117

[2] https://www.science.org/doi/10.1126/science.abe2629

[3] https://www.nature.com/articles/s41586-018-0637-6

Discussion 2 comments · 1 points · timshell · 2024-06-26
Open on HN
Loading the discussion…

Domain filters

Stories from these domains are hidden from every list. Subdomains match too: blocking substack.com also hides danluu.substack.com.

    About YAVCHN

    YAVCHN is a reader for Hacker News and Lobsters, with articles and discussions in separate windows or Classic pages.

    Created by Paul Parks and built with PUDL.

    YAVCHN source code on GitHub

    Help

    Keyboard

    j / k
    Move down and up the story list. The arrow keys scroll whatever has focus.
    Enter
    Read the marked story in the article reader.
    ]
    Read the next story in the same article-reader applet. Back returns to the previous story.
    p
    Pin or unpin the marked story, which keeps it in Pinned.
    n / N
    Move to the next or previous top-level comment in the window in front.
    c
    Collapse or expand that comment.
    f
    Hide or show the story list.
    Esc
    Close a menu or this help.
    Access key m
    Go to the menu bar. Most browsers take it with Alt on Windows and Linux, and Safari with Control and Option.
    ?
    Show this help.

    Windows

    Each story opens in a window holding its article above its discussion; drag the bar between them to share the room differently. A window can be moved by its title bar, resized from any edge, snapped to a half or a corner by dragging it there, maximised, or minimised to the bar at the foot of the page. Use Window > New reader window to open an empty reader, or Story > Open in new reader window to open another reader for the current article. Docked readers keep their articles when you select another story from the sidebar. Minimized readers can be restored and reused for their site. A window's Next story link reads on down the list in the same window.

    A link in a comment or an article to another Hacker News or Lobsters thread opens that thread in a window too. A link to a single HN comment opens the comment above its replies.

    While a story's window is in front, the Story and Discussion menus in the menu bar hold its commands: pinning, Next story, sorting, collapsing every thread, jumping to the first new comment. Each window also remembers where you were in its article and discussion, so a reload, or Back to a story that Next took you past, finds your place again. Closing a window forgets it.

    The whole arrangement lives in the address, so a bookmark or a shared link brings it back, and Back undoes the last change. Moving between Hacker News, Lobsters, their lists, Pinned and Find changes only the list, and leaves the windows open.

    The list

    The pin at the start of a row keeps the story in Pinned, and the cross at its end hides it. Pinned can be narrowed by words in the title, site or author, by source, and to the stories you haven't opened yet, and ordered by when you pinned them, by points or by comments; the filters are part of the address, so a filtered view can be bookmarked. Scroll past the end of the list to load more. Domain filters, in the View menu, hide every story from a site.

    Browsing view

    View > Windowed and View > Classic select the browsing view and save your default in this browser. Window view reuses a reader for each feed. Classic view opens stories and applets as pages. Open as a page is a one-off action that does not change your saved default. Use the Windowed selector to return an article to a window. Direct page links always open as pages.

    Applets

    The Applets menu in the menu bar holds three tools, each a window of its own. Replies to me takes your Hacker News user name and lists the replies to your last thirty comments and stories, checking again every three minutes while it is open, and marking what is new since you last marked them read. Look up a user opens a profile on Hacker News or Lobsters, with their submissions and recent comments, as a commenter's name in any discussion does; the bar at the top of a profile looks up someone else in the same window, and Back returns to the one before. Who is hiring? filters the posts of HN's monthly hiring threads by the words you type.

    They read only what the sites publish to everyone, so none of them asks for a login, and your user name stays in this browser.

    Find

    Find takes any link and lists every time it was submitted to Hacker News and Lobsters, so you can read each discussion of it.

    About

    YAVCHN never sees your Hacker News or Lobsters login. The discussion is fetched from each site's public API; to vote or reply, follow the link above the discussion, or the arrow beside a comment, to the source's own site. Pins, hidden stories, filters and layout are kept in this browser only.

    Open source: github.com/paulmooreparks/yavchn. Built with PUDL.