4 hours ago
4 hours ago
3 hours ago
3 hours ago
(5 hours ago)KamCode Wrote: You are not allowed to view links. Register or Login to view.hi my pleasure do not mind the computer generation, i am trying to make this very clear in the group that i am using AI to run (my code and output a answer) it is not hallucinating i understand enough about actual ai architecture to know what i am doing i do not blindly trust a chatbot LLM i use custom designed model weights for various tasks aswell as FM, the code is available on github for ppl who are comfortable using python
Yes, this is the problem. We prohibit theories with any LLM assistance. You aren't the first to claim that you wouldn't be fooled by AI hallucinations. We had someone recently who insisted he was a "computer engineer" and knew how to stop his chatbot from hallucinating. And yet the paper he presented was riddled with hallucinations that anyone who had studied the Voynich manuscript would catch. Not once did he ask what the hallucinations were that we'd found ...because he was using the LLM to reply, and of course it doesn't care. He/it kept insisting everything was fine and that we should just "run the code".
(5 hours ago)KamCode Wrote: You are not allowed to view links. Register or Login to view.The dictionary: Fair challenge. The entries starting with "a, aa, aaa, aaaa, aaaah" look like junk but they're mostly not — "aaabharana" is ābharaṇa (ornament), "aaachaarya"
is ācārya (teacher), "aaadharana" is ādhāraṇa (support). The triple-a is a romanization artifact: "aa" represents long ā, so a word starting with ā + another a-initial
syllable becomes "aaa." There are about 269 entries starting with "aaa" out of 1,470,278 total — less than 0.02%. The first handful ("a, aa, aaa, aaaa, aaaaaaaa, aaaah") are
genuine noise — 32 entries total of repeated single characters in the entire file.
So you don't blindly trust a chatbot ... but you faithfully copy-pasted its answer here as a response?
I was leaving this to see how it goes but this is just too much LLM. You're using it to design tests, run your code, to generate your output, to write some of your responses here. If you want to post a theory about Sinhala, you will need to do so without any LLM involvement, which from what you say here likely means starting from scratch.
Moving this to The Slop Bucket and locking.