← Back to context Comment by redox99 7 hours ago Character level LLMs are used for detecting insults and toxic chat in video games and the like. 5 comments redox99 Reply viraptor 1 hour ago Yes, for small messages and relatively small scope dictionary, character level will work. But that's very different from what's tested here. minimaxir 7 hours ago Can you give an example of a video game explicitly using character-level LLMs? There were prototypes of char-rnns back in the day for chat moderation but it has significant compute overhead. jazzyjackson 6 hours ago I figure an LLM would be way better at classifying insults than regexing against a bad word list. Why would character level be desirable? vanviegen 4 hours ago I'd imagine for simplicity - just skip the tokenizer and feed bytes. duskwuff 2 hours ago Might a character-level LLM be better at recognizing poorly spelled (or deliberately misspelled) profanity?
viraptor 1 hour ago Yes, for small messages and relatively small scope dictionary, character level will work. But that's very different from what's tested here.
minimaxir 7 hours ago Can you give an example of a video game explicitly using character-level LLMs? There were prototypes of char-rnns back in the day for chat moderation but it has significant compute overhead.
jazzyjackson 6 hours ago I figure an LLM would be way better at classifying insults than regexing against a bad word list. Why would character level be desirable? vanviegen 4 hours ago I'd imagine for simplicity - just skip the tokenizer and feed bytes. duskwuff 2 hours ago Might a character-level LLM be better at recognizing poorly spelled (or deliberately misspelled) profanity?
duskwuff 2 hours ago Might a character-level LLM be better at recognizing poorly spelled (or deliberately misspelled) profanity?
Yes, for small messages and relatively small scope dictionary, character level will work. But that's very different from what's tested here.
Can you give an example of a video game explicitly using character-level LLMs? There were prototypes of char-rnns back in the day for chat moderation but it has significant compute overhead.
I figure an LLM would be way better at classifying insults than regexing against a bad word list. Why would character level be desirable?
I'd imagine for simplicity - just skip the tokenizer and feed bytes.
Might a character-level LLM be better at recognizing poorly spelled (or deliberately misspelled) profanity?