What do you use as “ground truth”? The page says “independent sources”, and I’m sure there’s too many to list, but my question is how are they vetted as being truthful and how are two sources with opposite viewpoints reconciled?
Show HN: Bullshit Detector – agent skills that fact-check videos and articles
21–30 of 80 posts
Re: Show HN: Bullshit Detector – agent skills that fact-check videos and articles
#22Re: Show HN: Bullshit Detector – agent skills that fact-check videos and articles
#23Re: Show HN: Bullshit Detector – agent skills that fact-check videos and articles
#24Hmm, smells AI generated. Why should an LLM (this is from a SKILL.md) care about $LINES?
Re: Show HN: Bullshit Detector – agent skills that fact-check videos and articles
#25What do you use as “ground truth”? The page says “independent sources”, and I’m sure there’s too many to list, but my question is how are they vetted as being truthful and how are two sources with opposite viewpoints reconciled?
There is no whitelist source. It can't rate sources for truthfulness. When sources conflicts - skill drops verdict to misleading or unverifiable and both are linked. Can't pick a winner at the moment. That's probably the weakest part and still a judgement call for a model.
Re: Show HN: Bullshit Detector – agent skills that fact-check videos and articles
#26What do you use as “ground truth”? The page says “independent sources”, and I’m sure there’s too many to list, but my question is how are they vetted as being truthful and how are two sources with opposite viewpoints reconciled?
Something I've found surprisingly effective is telling ChatGPT to "use credible sources" - you can then watch its thinking trace and see it do things like ruling out random blogs, considering media publications with a good reputation for fact checking, and double-checking information that seems unlikely.
Re: Show HN: Bullshit Detector – agent skills that fact-check videos and articles
#27Apparently the "AI-generated bullshit" detection is already part of LLMs.
Re: Show HN: Bullshit Detector – agent skills that fact-check videos and articles
#28What do you use as “ground truth”? The page says “independent sources”, and I’m sure there’s too many to list, but my question is how are they vetted as being truthful and how are two sources with opposite viewpoints reconciled?
Something I've found surprisingly effective is telling ChatGPT to "use credible sources" - you can then watch its thinking trace and see it do things like ruling out random blogs, considering media publications with a good reputation for fact checking, and double-checking information that seems unlikely.