Dev Chair : A geek solution to the writers strike

by Alex Hung Jan 27th 2008

As the Writer's Strike continues into the end of January with no real end in sight, most people are running out of quality TV programs to watch. Heck, we're even running out of quality-less programs to watch. Unless you are a fan of reality shows such as Gladiator, there isn't much coming in the next month or so, if at all, for this rapidly evaporating season.

I think it is time we in the software industry step up to the plate and offer our help. With what we know about artificial intelligence (AI), genetic algorithms, and natural-language parsing, it should be possible to develop a software program where TV scripts are created based on previous episodes.

What we need are:

Characters in the series and their attributes (gender, personality, etc.)
Tons of previous scripts
The series formula, e.g. The new clue to solve the case between minutes 39 and 40 in Law & Order, or CSI.
A genetic algorithm that learns the characteristic of the series through all the existing episodes, e.g. how each character behaves, their favorite catchphrases, and how the general plot line evolves. For many shows, just the catchphrase would suffice.
A software bot to trawl the net for bizarre news as seed to generate new stories.

The scripts generated by this AI program would probably not very good at first -- but hey, neither was Seinfeld -- they might not make sense at all. But, after some teaching sessions by a human -- perhaps volunteers from the audience? It's all about crowd-sourcing these days, right? -- some reasonable scripts should result.

Granted this strategy would not work for proper drama like 24, Dexter, Weeds, etc. which all have major story arcs running through entire seasons but, it should work great for formulaic shows such as Law & Order, CSI, Numbers, Psych, where almost everything stays the same from episode to episode with only minor plot device differences in between.

How much effort would it take to develop this AI program? I don't have the faintest idea. I just suggest stuff, it's up to other people to handle the sticky details of implementation. I can imagine modifying an existing AI algorithm to accept TV scripts instead of whatever scientific research data, let it run on some beefy servers (may be run it as adistributed project like SETI@home? New TV shows are at least as important as finding aliens, maybe moreso.), and see what comes out at the other end.

Remember, this idea is hardly new. It has already been done with financial news by Thomson Financial as reported by Wired back in 2006. Is it such a big leap from news to formulaic drama?

Come on, doesn't this sound like a fantastic final year college project? Surely the prospect of getting your final assignment done and being the hero who breaks the Writer's Strike deadlock sounds appealing to someone?

More interesting question is: Which one is smarter? Law & Order, or an artificial intelligence program? With Fred Thompson dropping out of the presidential race, our money is on the AI.

Tags: 24, dexter, numbers, psych, script, tv, weeds, wired, writer's strike, Writer'sStrike

Reader Comments (Page 1 of 1)

James said 6:56AM on 1-28-2008

Could be a neat way to automate blogs :p

Rhys said 4:58PM on 1-28-2008

http://www.roalddahlfans.com/shortstories/greata.php

Lauri Suoperä said 8:14PM on 2-01-2008

"Granted this strategy would not work for proper drama like 24"
man - you sure know how to crack me up. :P
Next time, just stick to using Dexter as the example of "proper" drama.

alex dante said 6:04AM on 2-06-2008

"Come on, doesn't this sound like a fantastic final year college project? Surely the prospect of getting your final assignment done and being the hero who breaks the Writer's Strike deadlock sounds appealing to someone?"

Firstly, most TV is bad enough when there _is_ intelligence behind it.

But honestly, I don't know which is worse: the arrogance of a developer thinking his AI code can produce comparable works to _professionals in another field_ (when the current state of AI at this level _still can't produce realistic results in the areas they _have_ been focusing_) or the disdain towards those writing professionals who are trying to make a _fair and reasonable_ living. C'mon, they want to be paid for the profits made _everywhere_ on their works... who doesn't?

Featured Time Waster

Civiballs is a beautiful, soothing physics puzzle Time Waster

I have an absolute weakness for physics games, and while Civiballs isn't the strongest physics-based game, what it lacks in the physics department it makes up for a few times over in style and fun.

In Civiballs, you are presented with a few colored balls, and your goal is to get those balls into the same-colored urn on the level. The "civi" part of Civiballs is that there are 3 sets of levels to play, each representing a different civilization. While the civilization doesn't affect gameplay, the artwork for each level is beautifully themed to it's appropriate era.

To play the game, you are given only one tool - a sword with which to cut the chains that are holding the balls. The puzzle part of the game is in figuring out what order, and with what timing to cut each chain. Do it right, and all the right balls end up in the right urns, with no stray balls entering an urn (a no-no). Do it wrong, and you get to start over again.

Civiballs is not terribly deep on gameplay; the entire game can be completed in about 15 minutes. But if you enjoy this type of game, it will be a very enjoyable 15 minutes.

View more Time Wasters