can i talk to an openclaw bot using internet relay chat?
Uncategorized
41
Posts
18
Posters
0
Views
-
my suspicion is that i can *handwaves in the direction of kent overstreet*
you see, i have built my own LLM, using the most ethical method possible: i trained it on the entire corpus of IRC logs in my possession, 2003 to present
-
you see, i have built my own LLM, using the most ethical method possible: i trained it on the entire corpus of IRC logs in my possession, 2003 to present
no giant water vaporizing data centers needed here, just a GPU, a dream and some cold hard chats
-
no giant water vaporizing data centers needed here, just a GPU, a dream and some cold hard chats
time 2 implant this brain into an openclaw and give it full access to my email
mostly because i don't want to retain any of my email
-
you see, i have built my own LLM, using the most ethical method possible: i trained it on the entire corpus of IRC logs in my possession, 2003 to present
@ariadne I once ran an eggdrop with a script that would store all the things people said to it in a file and any time it was addressed, it would store what was said to it in that file and then pick something else from that file to respond with.
That script had a line that would randomly decide to pick a random word from the input and try looking for that specific word from the corpus and use a random line that matched that word, and sometimes that alone would make the response it would come up with *uncanny*
Funny thing is I wonder how it would stack up against some LLMs nowadays (/j)
-
@ariadne I once ran an eggdrop with a script that would store all the things people said to it in a file and any time it was addressed, it would store what was said to it in that file and then pick something else from that file to respond with.
That script had a line that would randomly decide to pick a random word from the input and try looking for that specific word from the corpus and use a random line that matched that word, and sometimes that alone would make the response it would come up with *uncanny*
Funny thing is I wonder how it would stack up against some LLMs nowadays (/j)
@fxchip yeah same idea, just running on kubernetes and CUDA
-
time 2 implant this brain into an openclaw and give it full access to my email
mostly because i don't want to retain any of my email
@ariadne
I can see a near future where "the AI deleted it" becomes convenient cover for "I didn't want to bother sorting it out." -
can i talk to an openclaw bot using internet relay chat? if not, then what is the point
Wouldn't be surprised if someone didn't already write something for that. After all Twitch chat is IRC and - well - I'd be kinda surprised if nobody made a twitch bot for their channel using openclaw by now...
-
you see, i have built my own LLM, using the most ethical method possible: i trained it on the entire corpus of IRC logs in my possession, 2003 to present
@ariadne how to produce the most toxic chatbot possible
-
@ariadne how to produce the most toxic chatbot possible
-
@ariadne how to produce the most toxic chatbot possible
-
-
time 2 implant this brain into an openclaw and give it full access to my email
mostly because i don't want to retain any of my email
@ariadne new eval, you ask it to generate a random password and it has to respond with hunter2
-
you see, i have built my own LLM, using the most ethical method possible: i trained it on the entire corpus of IRC logs in my possession, 2003 to present
-
you see, i have built my own LLM, using the most ethical method possible: i trained it on the entire corpus of IRC logs in my possession, 2003 to present
@ariadne@social.treehouse.systems oh no, never know what secrets it might spill
-
@ariadne new eval, you ask it to generate a random password and it has to respond with hunter2
-
undefined oblomov@sociale.network shared this topic
-
@ariadne how to produce the most toxic chatbot possible
@ska @ariadne Ive thouht of something related, not chatbots but imagine a GPS driving assistant voice in your car giving you directions and feedback, but in the most toxic way possible. An angry swearing voice saying things like: "Your exit comes in half a mile, try not to miss that one, you fucking moron." I've thought that ought to be a funny option to toggle on once in a while.
-
@ska @ariadne Ive thouht of something related, not chatbots but imagine a GPS driving assistant voice in your car giving you directions and feedback, but in the most toxic way possible. An angry swearing voice saying things like: "Your exit comes in half a mile, try not to miss that one, you fucking moron." I've thought that ought to be a funny option to toggle on once in a while.
@raulinbonn @ska now you see the vision!
-
@ska @ariadne Ive thouht of something related, not chatbots but imagine a GPS driving assistant voice in your car giving you directions and feedback, but in the most toxic way possible. An angry swearing voice saying things like: "Your exit comes in half a mile, try not to miss that one, you fucking moron." I've thought that ought to be a funny option to toggle on once in a while.
@raulinbonn @ska @ariadne "you just missed the correct street, now do a u turn if you can"
-
@ariadne how to produce the most toxic chatbot possible
-
time 2 implant this brain into an openclaw and give it full access to my email
mostly because i don't want to retain any of my email
so i installed it into the openclaw meme thing. and it's not like, doing the stuff it claims it is doing.
like it is hallucinating things like "i updated SOUL.md with xyz"
i seriously do not think this stuff is real now
Gli ultimi otto messaggi ricevuti dalla Federazione
-
Eva Sereny â Romy Schneider, Italy, 1971.
-
@xargon @massimolauria Arriveranno. Vedo davvero cose che si muovono.
-
Questa notte allâorecchio mâhai detto due parole
comuni. Due parole stanche
dâessere dette. Parole
cosÏ vecchie da essere nuove ⌠https://cctm.website/alfonsina-storni-due-parole/Alfonsina Storni
#alfonsinastorni #poesia #amore #cctmwebsite #anoipiaceleggere #leggere
-
@antoinechambertloir@mathstodon.xyz The distinction you're drawing is a useful one, and I largely agree with it. When translation is imposed on you with no alternative, the responsibility for its faithfulness lies with whoever imposed it.
But it makes me ask: which category does my situation fall into?
I'm writing this reply in English. Not because I chose English as my preferred language of expression, but because if I wrote it in Korean, it would either be ignored or filtered through whatever tool my interlocutor happens to have on handâand any resulting misreading would be treated as my problem. So I write in English, carefully, to preempt that. Is that a voluntary choice? Formally, yes. Practically, it sits much closer to the âimposedâ end of your spectrum than it might appear.
The contract model works cleanly when both parties have genuinely equivalent alternatives. When one party's only real options are âuse this toolâ or âdonât participate,â the contract framing starts to obscure more than it reveals.
-
Saved recording of Brandon's live feed last night up in Illinois. Starting when large hail and tornado first showed up (about 6:20:00), his window would get smashed shortly after.
https://www.youtube.com/live/NYsANnAhr6k?t=23239
-
Ipocrisia liberal-progressista: quando le bombe tornano âdemocraticheâ
-
@arichtman TIL that's what they're called
-
@jfkimmes this does explain something: it seems to be able to invoke tools when it is planning, but then those tools do not get invoked in the final step.
so it uses tools to read files when planning, then fails to use tools when executing.
what a fascinating conundrum.
