HackerTube.dev

I made a talking banana

Useless Duck Company · 621.6K views · 2018-05-15 · 17:41

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

A maker builds a talking banana that reads YouTube and Twitch comments aloud on stream, then fights viewers who abuse it with profanity. He ends up building a pronunciation-based filter to catch bad words.

On Hacker News

HN shares it as a funny, technical story about phonetic profanity filtering, relevant to Soundex and content moderation threads.

Recommended by 3 HN people across 3 months · HN mentions 2018–2023

Topics

Search by tags

What people said

hbosch · 2018-06 · Strong recommendation

You might enjoy this video. It’s part humor and part technical discussion on how his talking “Banana” bot was brigades by users on Twitch in an effort to make him say racist words and phrases. After he got a strike on Twitch, he patched the software and then it got circumvented... terrific little video about the battle between him and his viewers and ultimately ends with his approach to sterilizing input so that the banana couldn’t speak anything harmful. I thought it was great. * [VIDEO]

Read the original HN comment ↗
tonfreed · 2021-10 · Recommendation

You say that there's no "non-hacky" way, but... [VIDEO] He made a filter that did analysis of the pronunciation of the messages that were being sent. His breakdown of it starts at around 13:30

Read the original HN comment ↗
rasz · 2018-05 · Recommendation

If you are interested in phonetic algorithms, sorting, recognizing and filtering, you will enjoy Talking Banana Twitch ban story by Useless Duck Company : [VIDEO]

Read the original HN comment ↗

Sources

Video by Useless Duck Company, 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: Topic keywords do not match
  • 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