HackerTube.dev

Sunspring | A Sci-Fi Short Film Starring Thomas Middleditch

Ars Technica · 1.5M views · 2016-06-09 · 9:03

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

Sunspring is a sci-fi short film starring Thomas Middleditch. Its screenplay was written by an LSTM neural network trained on sci-fi scripts, and the team shot and edited it in 48 hours.

On Hacker News

HN cites it as an early, quirky example of machine-generated screenplays and what LSTMs could do.

Recommended by 1 HN people across 1 months · HN mentions 2016–2017

Topics

Search by tags

What people said

drewwwwww · 2016-09 · Recommendation

Check out this rather entertaining talk from GitHub universe about the use of an LSTM to generate a film script: [LINK] and the short film they made, using that script: [VIDEO] (disclosure: i work for github on events/AV)

Read the original HN comment ↗
eggpy · 2017-10 · Reference

But this part isn't science fiction, we already have AIs that do this. See AIVA for pretty good musical composition[0], new sites are using AI to write and compress news stories[1], and screeplays are being written via machine learning[2]. Obviously these are still in their infancy, but doesn't this perfectly encapsulate your point? There's not really an interesting story or thought piece there, because people are working on these in all sorts of fields all over the world, today. If we can build AIs that create "good" art, is it much of a stretch to teach a super AI what "better" means? By default a super intelligence doesn't have to start out as super intelligence, just have the capability to improve. [0] [LINK] [1] [LINK] [2] [VIDEO]

Read the original HN comment ↗
thegeomaster · 2017-08 · Criticism

I guess this is close: [VIDEO] . It's a script written by an RNN acted out as a short sci-fi film, and Thomas Middleditch is in it. Don't expect too much, though. I was reading an article on it and was excited to watch it, but it's too incoherent, in the usual fashion of today's RNNs.

Read the original HN comment ↗

Sources

Video by Ars Technica, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Matches the configured criteria
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources