So, buzzer WRONG.

Quite arrogant after you just constructed a faulty comparison.

If I say my name is Doo doo head, in a public park, and someone happens to overhear it - they can do with that information whatever they want. Same thing.

That's absolutely not the same thing. Overhearing something that is in the background is fundamentally different from actively recording everything going on in a public space. You film yourself or some performance in a park and someone happens to be in the background? No problem. You build a system to identify everyone in the park and collect recordings of their conversations? Absolutely a problem, depending on the jurisdiction. The intent of the recording(s) and the reasonable expectations of the people recorded are factored in in many jurisdictions, and being in public doesn't automatically entail consent to being recorded.

See for example https://www.freedomforum.org/recording-in-public/

(And just to clarify: I am not arguing against your explanation of Twitch's TOS, only against the bad comparison you brought.)

There is no expectation of privacy in public spaces. Participants to these streams which are open to all do not have a prohibition on repeating what they have heard.

You're both getting side-tracked by this discussion of recording. The recording is likely legal in most places.

It's the processing of that unstructured data to extract and store personal information that is problematic. At that point you go from simply recording a conversation of which you are a part, to processing and storing people's personal data without their knowledge, consent, or expectation.

You're both getting side-tracked by this discussion of recording. The recording is likely legal in most places.

It's the processing of that unstructured data to extract and store personal information that is problematic. At that point you go from simply recording a conversation of which you are a part, to processing and storing people's personal data without their knowledge, consent, or expectation.

Repeating what they heard is very different from automatically processing the chat to harvest personal information about the participants.

Just because some data is publicly available doesn't mean all processing of that data is legal and moral.

Yes. The small LLM isn't retrieving data, it's just understanding context of text enough to know what "Facts" need to be written to a file. I'm using the publicly released Deepseek models from a couple of months ago.

I've run a few models that I could on my GPU. I don't think the smaller models are really good enough. They can do stuff, sure, but to get anything out of it, I think you need the larger models.

They can be used for basic things, though. There are coder specific models you can look at. Deepseek and qwen coder are some popular ones

I'm not storing their data. I'm feeding it to an LLM which infers things and storing that data. Other Twitch bots store twitch data too. Everything from birthdays to imaginary internet points.

I'm not storing their data. I'm feeding it to an LLM which infers things and storing that data. Other Twitch bots store twitch data too. Everything from birthdays to imaginary internet points.

It'll work for quick bash scripts and one-off things like that. But there's not usually enough context window unless you're using a 24G GPU or such.

Snippets are a great use.

I use StableCode on my phone as a programming tutor for learning Python. It is outstanding in both speed and in accuracy for this task. I have it generate definitions which I copy and paste into Anki the flashcard app. Whenever I'm on a bus or airplane I just start studying. Wish that it could also quiz me interactively.

I've tried coding and every one I've tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.

I've tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.

So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can't really handle anything above 4B in a timely manner. 8B is about 1 t/s!

Was this system vibe coded? I get the feeling it was...

Some questions and because you don't actually understand, also, the answers.

• what does the LLM understand the context of, (other user's data owned by Twitch)
• How is the LLM fed that data? (You store it and feed it to the LLM)
• Do you use Twitch's data and its users data through an AI without their consent? (Most likely, yes)
• Do you have consent from the users to store 'facts' about them (You're pissy, so obviously not)
• Are you then storing that processed data? (Yes, you are, written to a file)
• Is the purpose this data processing commercial (Yes, it is, designed to increase viewer count for the user of this system - and before you retort "OMG it helps twitch too"... Uhm no, Twitch has the viewers if not watching him, watching someone else)

I mean yeah, it's a use case, but own up to the fact that you're wrong. Or be pissy. I don't care.

True.

Although in Germany for example it can also be an issue when recording. If you have a security camera pointed at a public space (that can include the sidewalk infront of your house), passersby can sue you to take it down and potentially get you fined. Even pretending to constantly record such an area can yield that result.

You build a system to identify everyone in the park and collect recordings of their conversations? Absolutely a problem, depending on the jurisdiction.

Literally not. The police use this right now to record your location and time seen using license plates all over the nation - with private corporations providing the service.

and being in public doesn't automatically entail consent to being recorded.

And yes, it's called 'expectation to the right of privacy'. Public venues are not 'private' locations, and thus do not need consent. You can, quite literally, record anyone in public.

Even the link you provided agrees.

There's not actually that much code. It's like 8 lines for an AI 'agent', and maybe another 16 lines for 'tools', and I'm using Streamlink for grabbing the audio stream, and pulseaudio has a 'monitor' device you can use to listen to what's playing on the speakers. Throw it on a very minimal linux distro on a VM, and that's it.

I don't do 'vibe coding', but that IS where I got the idea from. People who are doing 'vibe coding' nowadays aren't just plugging things into a generic AI, they're spinning up 'agents' and making tools via MCP and then those agents are tasked with specific things, and use the tools to directly write to files, search the internet, read documents, etc

I've tried coding and every one I've tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.

I've tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.

So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can't really handle anything above 4B in a timely manner. 8B is about 1 t/s!

Please be very careful. The python code it'll spit out will most likely be outdated, not work as well as it should (the code isn't "thought out" as if a human did it.

If you want to learn, dive it, set yourself tasks, get stuck, and f around.

So this wasn't a post actually asking what a small LLM was good for, it was just an opportunity you could use to dump on LLM usage I take it. So this whole thing was made in bad faith?

With the comments about "vibe coding" and such, all it looks like you're doing here is arguing the "merits" of how it's being used, and you're not interested in its actual usage at all.

Nobody is being pissy here except you. Small LLMs can be used for tasks such as this, and it doesn't have to be twitch - It could be an assistant that you build for reminders in your personal life - using it on twitch is a minor detail that you seem to have latched onto because you just want to dump on LLM usage.

Go to /c/fuck_ai for that.

I gave you an example that it's good for, and all you want to do is argue the merits of how I'm using it (even though it falls perfectly within Twitches TOS and use cases)