Blurry Moon
@sun@shitposter.world
I used to be the Moon on a different planet.
Posts
Latest notes
No posts yet.
@meeper local models just still suck so bad at keeping a coherent conversation
@meeper I was messing around with this for a 2d pokemon mud
@i @vii right now what I mashed up is:
1. extract mention urls from html via a.mention css selector
2. pass the plain text into something that converts english numbers to regular numeric values.
3. regex match and extract the numeric values
4. convert the html to plain text using a few special conversion rules
5. pass that plain text into the llm that has its output constrained to a grammar that forces json in the form of commands for my bot
6. double check and replace values if needed
7. ignore messages that can't be construed as a tip
I am modifying this so it can detect multiple tips in a note and ignores text and mentions unrelated to the tips
1. extract mention urls from html via a.mention css selector
2. pass the plain text into something that converts english numbers to regular numeric values.
3. regex match and extract the numeric values
4. convert the html to plain text using a few special conversion rules
5. pass that plain text into the llm that has its output constrained to a grammar that forces json in the form of commands for my bot
6. double check and replace values if needed
7. ignore messages that can't be construed as a tip
I am modifying this so it can detect multiple tips in a note and ignores text and mentions unrelated to the tips
@Mitsu Lord I try
@Mitsu she has repeatedly attempted to make me watch things with gay romance in it already yes. And I do it 
the first cryptocurrency for gen alpha. no coin cap
@Mitsu is it called puck me in the glass
@vii since I can extract mentions and amounts directly from the post I almost don't even need the LLM, basically I am using it to give me a fuzzy confirmation that it's actually a tip command and not just something that accidentally has those values
@vic openclaw is very bad for security
@vii I bookmarked your post to learn more, thanks
@vii this won't work if for example I ask the bot to do some kind of fanct calculation
@vii simpler in most cases, I extract certain values from the text before llm processing. I use this to create a whitelist of values. Then I feed the text into a model using ollama that constrains the output to a json command, ensuring it has the right values
I have been reading up on how you make LLM-mediated chatbots that do things like TIPPING CRYPTOCURRENCY not hallucinate important values. It's not actually that hard.
@anemone remind me again if this is local model or forwarding to a service
@anemone you added in ocr?