News for hackers. Stuff that matters.
Re:Show HN: A fast OSS voice assistant by 101008 on Monday July 08, 2024 @01:36PM (#40907438)
What's the model behind it? I asked a simple question (that others LLM got it right without a problem) and this answered somethign completely wrong (and curious, since I don't know where the hallucination came from)
Re:Show HN: A fast OSS voice assistant by vaasuu on Monday July 08, 2024 @01:56PM (#40907619)
Looks like it's using llama3-8b-8192 as the LLM [1], which is a relatively small model, so hallucination is quite likely.

[1]: https://github.com/ai-ng/swift/blob/7d1f993b095abc4a51cf9c70...