News for hackers. Stuff that matters.
Re:Show HN: Building an app to l earn languages with short s... by bavarianbob on Tuesday October 10, 2023 @12:31PM (#37834277)
Really great food for thought here, I'm going to have linger on it some more. I don't know enough about LLMs to know how to counteract hallucinations, but I wonder if you could construct an LLM against a vetted corpus (much like Anthropic does with Claude) in which it solves for the problem of generating robotic speech patterns. I do agree with you a lot on the "sound" problem because I don't think I'd advise a non-native English speaker to blindly trust ChatGPT as a learning mechanism based on my experience of using it.

So, in conclusion, I'm curious to learn whether this is a solvable problem or if LLMs are inherently not the right tool to use.

Re:Show HN: Building an app to l earn languages with short s... by yorwba on Tuesday October 10, 2023 @01:44PM (#37835120)
Once you have a vetted corpus large enough to train an LLM on, I don't think there's any need to generate even more text with the LLM, since you can use the corpus directly.
Re:Show HN: Building an app to l earn languages with short s... by wahnfrieden on Tuesday October 10, 2023 @01:53PM (#37835231)
yes llm can be deployed simply to search for material, to synthesize it, cite it, etc instead of being used to generate more similar material