can i talk to an openclaw bot using internet relay chat?
-
i wonder if the problem is that the model i trained is too shit to do anything other than really bad ERP
@ariadne yes. For 3B and lower you need targets. You could try hooking it up to my Akh-Medu experiment as there I only need a. Small LLM that does Natural Language https://akh-medu.dev But I think the NLU is still quite broken or hooked up in the wrong way. But A Kluge system like that should use muuuu h less power than a pure LLM
-
i wonder if the problem is that the model i trained is too shit to do anything other than really bad ERP
@ariadne Also for tool calling you need targeted fine tuning best with the exact samples for the tools
-
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
@ariadne oh yes, i saw a 'verification' step that was just 'echo' this week on some fedi post.
-
i wonder if the problem is that the model i trained is too shit to do anything other than really bad ERP
ok, i incorporated the feedback of some of the ML researchers who follow me, and dropped the openclaw-as-IRC-bot idea. it just isn't feasible.
instead, i've written a very simple vector database in Elixir, and a very simple IRC client in Elixir.
it can remember things about people in the vector database, those factoids are spliced into the system prompt.
the last 10 messages are also spliced into the system prompt
and then the new message is the user-supplied prompt.
no sliding context window.
-
ok, i incorporated the feedback of some of the ML researchers who follow me, and dropped the openclaw-as-IRC-bot idea. it just isn't feasible.
instead, i've written a very simple vector database in Elixir, and a very simple IRC client in Elixir.
it can remember things about people in the vector database, those factoids are spliced into the system prompt.
the last 10 messages are also spliced into the system prompt
and then the new message is the user-supplied prompt.
no sliding context window.
@ariadne very appropriate now the elixir community seems to be all over vibe coding
-
and you tell me people legitimately are using this software.
how?
is it really magically better when you hook up claude?
@ariadne yes, OpenClaw is kinda useless if you use it with anything other than Opus 4.5 or 4.6
-
@ariadne very appropriate now the elixir community seems to be all over vibe coding
@dysfun oh i didn't vibe code any of that. elixir is fucking easy
-
@dysfun oh i didn't vibe code any of that. elixir is fucking easy
@ariadne i know, but it feels appropriate
-
@ariadne yes, OpenClaw is kinda useless if you use it with anything other than Opus 4.5 or 4.6
@mathieucomandon alas i am too frugal to try it
-
ok, i incorporated the feedback of some of the ML researchers who follow me, and dropped the openclaw-as-IRC-bot idea. it just isn't feasible.
instead, i've written a very simple vector database in Elixir, and a very simple IRC client in Elixir.
it can remember things about people in the vector database, those factoids are spliced into the system prompt.
the last 10 messages are also spliced into the system prompt
and then the new message is the user-supplied prompt.
no sliding context window.
i need to tweak the system prompt though because it keeps trying to link me to GNAA shock sites and/or engage in horrendous ERP
-
@mathieucomandon alas i am too frugal to try it
@ariadne understandable. I tried it with Sonnet once and it started eating tokens like crazy while outputting poor results.
As for local models, I tried some Qwen variant and the output was pure nonsense!
Currently working with Qwen in a different context and making it do consistent things is a struggle -
i need to tweak the system prompt though because it keeps trying to link me to GNAA shock sites and/or engage in horrendous ERP
@ariadne how many of these shock sites did i used to host?
-
@ariadne how many of these shock sites did i used to host?
@dysfun idk what hosting provider did you run
-
i need to tweak the system prompt though because it keeps trying to link me to GNAA shock sites and/or engage in horrendous ERP
@ariadne well that was ENTIRELY predictable
-
i need to tweak the system prompt though because it keeps trying to link me to GNAA shock sites and/or engage in horrendous ERP
I have Enterprise Role-Playing at work.
-
@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." -
i need to tweak the system prompt though because it keeps trying to link me to GNAA shock sites and/or engage in horrendous ERP
@ariadne Ahh so there *is* someone that LLMs will put out of work?
-
@ariadne well that was ENTIRELY predictable
@meph you could say it was text produced by a prediction model
