points by mdp2021 1 day ago | 0 comments
> to go to for ... anti-hallucination stuff
In theory maybe, in some tentative hope that the RAG would patch the hallucination problem - but the LLM showed such a low effective equivalent IQ that its usage was always incredibly frustrating. (It could have improved recently - I am not sure. Some tests have indicated it as especially dumb even not long ago.)
[–] qlte 1 day ago
I still remember an HN post back when Perplexity was still the current hotness where the top comment about whatever AI news was analyzing MSFT stock with price history and key milestones, and cited Perplexity as their source. With some meta commentary about how easy research is now that tools like Perplexity are available.
Literally every cited number was flat out wrong. Some people replied to point out the mistakes but as I recall no one called out the Perplexity elephant in the room specifically.
I'll have to find it again, it was such an absurdly ironic scenario it felt like performance art or something.
[–] 5555watch 1 day ago
[–] mdp2021 1 day ago
You would go to it, but results showed much more work was needed - also in RAG. Which became a general focus in the community, for the many problem it may solve and the many it could help fixing. Some found better formulas for RAG, others swamped. Perplexity made it a flag, but in a factual large company. And the problem with "fake sources and citations" is still there, while mitigated in the full complex systems - hallucination is still a benchmarked effect in LLM ANNs, and blunders from excessive trust are still recorded.