lee/hpr-knowledge-base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit: HPR Knowledge Base MCP Server

Browse Source 
- MCP server with stdio transport for local use
- Search episodes, transcripts, hosts, and series
- 4,511 episodes with metadata and transcripts
- Data loader with in-memory JSON storage

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Lee Hanken
2025-10-26 10:54:13 +00:00
commit 7c8efd2228
4494 changed files with 1705541 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

134
hpr_transcripts/hpr3983.txt Normal file
View File

@@ -0,0 +1,134 @@
Episode: 3983
Title: HPR3983: ChatGPT Output is not compatible with CC-BY-SA
Source: https://hub.hackerpublicradio.org/ccdn.php?filename=/eps/hpr3983/hpr3983.mp3
Transcribed: 2025-10-25 18:14:38
---
This is Hacker Public Radio Episode 3983 for Wednesday the 8th of November 2023.
Today's show is entitled, Chat GPT, Output is not compatible with Creative Commons
Attribution Share alike for International License.
It is hosted by Ken Fallon and is about 9 minutes long.
It carries a clean flag.
The summary is, Ken is not a lawyer but is fairly sure that Chat GPT is not compatible
with Creative Commons.
Hi everybody, my name is Ken Fallon and you're listening to another episode of Hacker Public
Radio.
Today I'm recording this with a Jabber headset, so be interesting to see what the quality
is like.
The reason I'm doing it is that I've had to reject a show.
I'm submissive to HPR, I'm recording this as a janitor, actually normally I would record
my own shows as myself, but this is recording as a janitor.
I thought it best to answer the reason why I'm rejecting the show in a show because
actually we're short of shows, so please submit one.
So when you upload to Hacker Public Radio, if you go to the About page you'll be linked
to the stuff you need to know page and on there one of the things that you agree to is
that you're agreeing to license your show as CC by essay.
Now what is that?
I'll give you the blurb here first and then we'll go into more detail.
All our shows are now released under Creative Commons, attribution share like 4.0 International
license.
So the abbreviation you'll see sometimes for that is ccby-sa space 4.0, carrying on, which
means that while you continue to retain the copyright for your show, you are allowing
us and everybody else to use it provided we give you attribution and we release it under
the same license and there's a link to that license which brings you to this page which
is the Creative Commons page.
For those of you who don't know, Creative Commons is a way to, while you continue to own
the copyright of your material, it allows the person downloading your material to know
under what terms they're getting your work and you can select from various different selections
and more free, more free to use to certain restrictions.
So the one that has been chosen by the HBIR community is ccby-sa, which is a nice mix of sort
of like a gpl like license.
So the exact deed says as follows, this is from the Creative Commons website, you are free
to share and that means copy and redistribute the material in any medium or format for any
purpose even commercially, adapt to remix, transform, and build upon the material for any
purpose even commercially.
The licenseer cannot revoke these freedoms as long as you follow the license terms.
So the license terms are as follows, attribution you must give appropriate credit, provide a
link to the license and indicate if the changes were made.
You may do so in a reasonable manner but not in a way to suggest that the licenseer endorses
you or your use, the other restriction is share-like.
If you mix, transform, or build upon this material, you must reduce views, your contributions
under the same licenses the original and there are no additional restrictions.
You may not apply legal terms or technological measures that legally restrict others from
doing anything the license permits, notices.
You do not have to comply with the licenses for elements of materials in the public domain
or where your use is permitted by acceptable exceptions or limitations, no warranties.
So given the license may not give you all of the permissions necessary for your intended
use, for example, other rights such as private publics, city, privacy, or more lights may
be limited on how you use the material.
Okay, so that's pretty much the blah, blah, blah.
The bit that we're interested in is that you're free to copy, redistribute, the material
and more importantly, your ability to adapt it, which means remix, transform, and build
upon the material for any purpose, even commercially, any purpose, even commercially, okay.
So that brings us back to the question of open AI and they have terms of use and their
document describes a section tree, three content, your content, just to know what terminology
we're talking about here.
So your content, you may provide input service, input and receive output generated and returned
by the service based on the input.
So input and output are collectively content.
As between the parties and to the extent permissible by law, you own all inputs.
Now, subject to your compliance with these terms, open AI hereby assigns you all the rights,
titles and interests in and to output.
That means you can use the content for any purpose, including commercial purposes such
as sales or publication, if you comply with the terms.
Open AI may use content to provide and maintain the service, comply with applicable laws,
and enforce our policies.
You are responsible for content, including ensuring that you do not follow violets, any applicable
laws or terms.
So reading that, you think everything's hunky-dory, we can use a franny, we can use it for
any purpose, including commercial purposes, such as sale or publication, but the problem
is if you comply with these terms is in there, meaning you have to comply with all the
items on the page and linked to that page.
So then we go to the same page under usage requirements, section C says restrictions.
You may not want, use the service in any way that infringes, misappropriates or violates
any person's human rights, okay?
That violates create commons, but I'm not going to go into it.
Two, you may not reverse assemble, reverse compile, decompile, translate or otherwise attempt
to discover the source code or underlying components, models, algorithms and systems
of the service, except to the extent such restrictions are country to the applicable law.
Okay, we're hacker public radio, but I'm also not going to go into that one.
And number three, use the output of the service to develop models that compete with open AI.
Also not going to go into that one, but you see here that there are restrictions on
the service, and that puts it directly at odds with what is said here in the creative
commons license that you are built upon the materials for any purpose, even commercially,
commercially, sorry, share, you can copy, redistribute the material in any medium or format
for any purpose.
So the creative commons is saying that you can do one thing, the license that you receive
from chat GPT says there are restrictions.
So therefore in my eyes, making the call as janitor, there are incompatibilities with
the licenses, therefore anything produced by chat GPT is not covered, cannot be re-licensed
as creative commons.
That is my take in us.
Now I always tend to be more conservative on this.
This is where we as a community can decide, and we decide on the mail list.
So if you want to chime in on this, feel free to do so.
But as it goes now, this would fall under the same sort of rule where we're volunteers,
the janitors, and we do not want to get into any legal issue with regard to that.
However, you can still use the chat GPT stuff in my opinion.
This is of course my opinion taken off my janitor hat.
I would imagine that if you are using chat GPT and you do a show about it and you say,
okay, this is the output that I was given, and part phrasing is like this.
So we had the same discussion earlier on about how to cover new shows, some guy in the
internet, pulls that question earlier on.
So I think we will follow the same sort of guidelines there, treated as copyrighted
third party.
You may refer to it, but you may not use it directly.
That's what I think at the moment.
So therefore I pushing this over to the HVR council on the mailing list.
If you're not on the mailing list, feel free to join us.
That's what we're here for.
And also send in some shows.
Why don't you?
It's great.
Look, your CV could be hugely improved by active podcaster in the technology sector simply
by submitting a show.
Alright, that's it.
June and tomorrow for another exciting episode of Hacker Public Radio.
You have been listening to Hacker Public Radio, and Hacker Public Radio does work.
Today's show was contributed by a HVR listener like yourself, if you ever thought of recording
a podcast, and click on our contribute link to find out how easy it really is.
Hosting for HVR has been kindly provided by an onsthost.com, the internet archive and
our sings.net.
On the Sadois status, today's show is released under Creative Commons, Attribution 4.0 International
License.