"In a YouTube video titled "Amazon cancels my account after exposing account lockout for 'racist doorbell'," the speaker shares his experience of Amazon cancelling his seven-year-old affiliate program account, claiming he violated their operating agreement. Despite using the same links to promote products on his YouTube channel for seven years and earning meagre profits, Amazon cancelled his account without any reasonable vetting. The speaker argues that Amazon's decision is an example of the lack of accountability of big companies as they become more powerful, and invites viewers to share their feedback on the issue in the comments section." [1]

Easy way to use tools to achieve something similar:

yt-dlp (YouTube video downloader), whisper.ai (STT), and then you can use e.g. ChatGPT to summarize the text data.

[1] https://www.summarize.tech/www.youtube.com/watch?v=Kcohq313q...

<from whisper.ai website> Notice: Whisper has made the decision to complete a voluntary market withdrawal of our Hearing Systems as our business direction changes, effective June 8th, 2023. There are no known safety concerns with the devices, but this means we will no longer service or produce the Whisper Hearing System

whisper.ai is apparently something completely different, I’m pretty sure OP meant OpenAI’s whisper [0] which is mainly used with whisper.cpp [1] I think.

[0]: https://github.com/openai/whisper

[1]: https://github.com/ggerganov/whisper.cpp

Skip the speech-to-text step, grab the subtitles from youtube.

Good one! Not always reliable, but pretty good (this video it does not seem to work with, says no subs). Not sure if Whisper.cpp (yes I did mean OpenAI Whisper) is better though, or has similar issues on the edge cases I encountered with YouTube subs.

Here's the output by Whisper.cpp

> $ whisper --verbose False --language English --output_format txt transcribe_me.wav

> [...] (removed, comment too long)

> $ cat transcribe_me.txt | mods -f "summarize this in Simple English"

> The speaker discusses how Amazon accused a customer of racism due to something a robotic doorbell said. They also talk about the concept of companies limiting how fixable devices are, and how this limits the freedom and sovereignty of consumers. They mention that Amazon canceled their seven-year affiliate program account, claiming that they violated terms of service by having employees and friends use the links to buy items. The speaker argues that Amazon overreacted and that this demonstrates the problem of companies becoming less accountable as they gain more power. They call for more scrutiny of such behavior.

> $ cat transcribe_me.txt | mods -f "summarize this in English"

> The creator discusses how Amazon accused a customer of racism because a delivery driver claimed that he heard something racist from a robotic doorbell. The creator explains they often discuss the concept of "right to repair" and how companies are making devices less fixable over time, requiring customers to buy new ones or rely on the manufacturer for service. The creator talks about how having a system in your house that can be turned off by Amazon if an employee claims that your device said something racist to them is concerning. They also receive an email canceling their Amazon Affiliate account that has been open since 2016, claiming that the purchases resulting from special links are in violation of the operating agreement. The creator disputes these claims and argues that such actions demonstrate the problem of companies becoming less accountable as they become more powerful.

Note, mods requires OPENAI_API_KEY to be set.

Just FYI, use:

yt-dlp --write-auto-sub --sub-format json3 --sub-lang en

I don't know why automatic subs require a different flag, but they do.

What's that "mods" CLI?

Nice yeah I suppose I would use format vtt and then convert that to text e.g. with [1]

mods is a CLI interface to GPT-4 [2]

[1] https://webvtt-py.readthedocs.io/en/latest/

[2] https://github.com/charmbracelet/mods

I haven't watched the video and was very happy to have a summary. What makes you question it was written by an AI?

I thought it was helpful too, but read like it was written by AI. So I wanted to know if it was. What's wrong with asking a question?

Sarcasm is hard to detect in written form.

Not that hard /s

and also, if the summary was good, why would it matter whether it was written by an AI or not?

In your view, is the summary accurate and complete?

Because it's poorly written, poorly readable and misses things. It's essentially bot spam with a human clicking the submit button.

It's pretty good, but misses out that it's a Louis Rossmann video, who is a big spokesman for consumer rights against tech companies (also a very popular vlogger and highly skilled electronics tutor). I feel like an AI would be less likely to pick up on this wider context, but possibly the OP just didn't realise who it was.

It’s pretty obvious.

For the downvoters, if you can’t tell this is an AI you’re gonna be in real trouble if these models actually get good.

The giveaway for me was the sentence "While not excusing Amazon's actions, he questions whether enough vetting was done before canceling his account." It makes no sense - why would questioning whether enough vetting was done be interpretable by anyone as "excusing Amazon's actions"? It obviously goes in the other direction; the sentence might have read "While not directly condemning Amazon's actions, he questions whether enough vetting was done before canceling his account."

The briefest of looks at their comment history suggest they are simply helpful.

Or a spammer.

I basically never click a link if I can see that it leads to youtube, because I'm rarely in a situation where it's convenient to watch a video, and even if I am, it's usually the most noisy & inefficient way to receive a given piece of information. So a summary is incredibly useful, whether it's written by AI or not. What makes you refer to it as spam?

That and it was a 9 minute video that a 10 second read is more efficient.

For me, it’s the time spent on these banalities. The concept is interesting but this YouTuber has an audience that likes long videos about short subjects and it’s not for me.

I like the summary because it helps me understand and choose to watch or not.

Please think about what you say before you say it.

I thought exactly what I said.

You clearly didn't - that person doesnt spam or otherwise repeat comments