News for hackers. Stuff that matters.
Re:Ask HN: Strategies to Reduce AI Hallucinations? by constantinum on Thursday July 25, 2024 @10:23PM (#41075341)
One strategy(not directly related to ChatGPT) is to use two models, one for extraction/generation and the other "challenger" to verify the extracted answer. Refer: https://docs.unstract.com/editions/cloud_edition#llmchalleng...
Re:Ask HN: Strategies to Reduce AI Hallucinations? by bosco_mcnasty on Friday July 26, 2024 @01:40AM (#41076055)
could the generator and challenger be cross trained against each other, so as to actually both get better? like a generative-challenger network (GCN) or something like this?
Re:Ask HN: Strategies to Reduce AI Hallucinations? by langcss on Monday July 29, 2024 @03:24AM (#41098526)
I think this is how RLHF actually works. https://huyenchip.com/2023/05/02/rlhf.html#3_1_reward_model
Re:Ask HN: Strategies to Reduce AI Hallucinations? by trte9343r4 on Monday July 29, 2024 @02:38AM (#41098372)
I use the same strategy. More like an interview. Many AI related tricks can be automated.