News for hackers. Stuff that matters.
Re:Microsoft's AI Bing also generated factual errors at launch by brookst on Tuesday February 14, 2023 @08:51PM (#34799039)
How is Bing Chat citing sources with links not a plan to address the hallucination problem?

It’s not a perfect mitigation, but surely it’s at least one step above “no plan”.

Re:Microsoft's AI Bing also generated factual errors at launch by PaulDavisThe1st on Tuesday February 14, 2023 @10:57PM (#34799925)
First of all, the "citing sources" needs to be out-of-band from the regular response, since we've already seen that these systems are entirely comfortable inventing ficticious sources.

Second, if I give you a wonderfully written paragraph or two about the history of the British Parliament, and 3 links that supposedly back me up, how likely are you to check the links? Because that's what is actually going to happen. The LM will not "cite" a source, it will provide one out-of-band and your motivation to read it will need to be high, which is unlikely given the apparent quality of the LM's own answer.

Re:Microsoft's AI Bing also generated factual errors at launch by brookst on Wednesday February 15, 2023 @07:58AM (#34803207)
You seem to be talking about chatgpt, not bing chat. Bing chat literally uses the search engine queries and links to those sources. I have seen its summaries include mistakes, but I have never seen it invent sources (I’ve tried maybe 500 chat queries).

It’s ironic that you’re very confidently presenting erroneous information here. I’d really recommend trying the actual product, or at least looking at the demos. It has some problems. It does not have the same problems that chatgpt does, because it does not rely solely on LLM baked-in data.