12 Angry Agents

12 Angry Agents

12 angry men is a very thought-provoking film, and there is nothing quite like it. Its premise is just 12 people sitting in the jury room and sharing their experiences and judgment on a very sensitive case. They need to decide whether a boy is innocent or guilty of a crime.

I have been playing around with a thought experiment where agents play human roles and come to a conclusion. I created agents for each jury, and the judge is another agent that can make an informed decision based on what the juries come up with. I fed the movie script into the setup, and each jury uses the Recall tools to refine their belief, and how they came to a conclusion.

I built this using Polign Recall - https://github.com/Polign/recall , langGraph and agent-sandbox.

1. Each jury agent processes the conversation in its own terms.

2. The memory gets folded, and contradiction and change of mind get processed as part of their own belief system.

3. The judge decides how each juror finally concluded their belief and whether they came to be with an informed decision or were coerced into the decision.

--------------------------------------------------------------------------------

Here is the conclusion by the judge (This is AI generated for a reason) -

As the judge, I'd rule: not guilty, and the verdict stands. The prosecution's case was meant to prove guilt beyond reasonable doubt, and each piece of it fails once tested in the jury room:

The knife isn't unique. Juror 8 bought an identical switchblade in the boy's neighborhood, so the "one of a kind" weapon ties no one to the killing.

The old man couldn't have seen the boy run. He had had a stroke and drags one leg. Walked out in the jury room, he couldn't reach his door in the 15 seconds he claimed.

The woman across the street wasn't wearing her glasses. She had marks on her nose from glasses, and she saw the stabbing from bed, at night, through the windows of a passing train. She wouldn't have been wearing them in bed. "I'm going to kill you" couldn't be heard. The train was passing at that moment, and it's loud enough to drown out speech.

The stab wound doesn't fit. The wound angled downward, but someone experienced with a switchblade stabs underhand. A shorter boy stabbing downward at a taller man is unlikely. The boy forgetting the movie proves little. Juror 3, sitting calmly in the jury room, can't remember a film he saw days earlier.

Did the boy kill his father? Neither the film nor the record answers that, and a judge doesn't rule on it. A judge rules on whether the state proved its case. On this record it didn't: every eyewitness account and every piece of physical evidence fails. Not guilty is the definite answer the evidence supports.

--------------------------------------------------------------------------------

The premise behind the memory updates and storage-

A change of mind is a correction: When a later scene changes what a juror believes, Recall keeps the newer belief as current and keeps the older one as what it replaced, with the scene it came from. A juror who moves from guilty to not guilty carries both beliefs, the scene where each began, and the scene where the first one ended. Recall's diff returns exactly what started and stopped being believed in the final act.

Opinions from memory alone: At the end, each juror is asked what they make of the outcome. The model gets that juror's memory from Recall, and not the script. It answers in the juror's voice and cites the scene behind every belief. If a juror was misled and never found out, they still believe it.

A conclusion from separate minds: The last step reads the final pages and every juror's memory, side by side, and names the question the film leaves open. It answers that question with evidence that names the juror and the remembered scene, for example, a late change of mind, or something one juror knows that another does not. Because each memory was kept apart, the conclusion can see where the jurors disagree.

Discussion 0 comments · 1 points · anuptalwalkar · 10h
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. Type a domain, or paste a link to block its site, and press Enter.

New collection

Delete this collection?

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

Privacy policy · Terms of use

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 story above or below in the list, in the same article reader. Back returns to the story you came from.
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 Previous and Next buttons read up and 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, Previous and 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.

Collections are named lists of stories. Story > Add to collection files the story in front into one or more of them, and the Collections feed shows them all or one at a time; the menu that chooses collections also creates, renames, and deletes them. A note is your own text on a story. Choose Add note in a story's toolbar to write one; it saves as you type. Rows with a note carry the note mark, and the Notes feed lists every noted story and searches the text of your notes.

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 anonymously and is included in retained applet state when signed in.

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. Without a YAVCHN account, your data stays in this browser. When signed in, pins, collections, notes, blocked domains, and retained reading state are stored with your account and synchronized across devices. Hidden stories and layout stay in this browser. The privacy policy has the details.

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