News for hackers. Stuff that matters.
Re:Study: ChatGPT Outperforms Physicians in Quality, Empathe... by hammyhavoc on Saturday April 29, 2023 @05:33PM (#35757428)
Yup, and it hallucinates plenty with dev too, even over basic stuff like an NGINX config.

Given that it hallucinates in particular over measurements/specs/stats, I'd be extremely sceptical of taking a recipe from it, whether that's generated and original or coming from a known source.

Baking requires very specific measurements, the slightest mistake and it won't turn out well in most cases. Again, why go via an LLM and not a search engine to the actual source? It makes zero sense, especially if it only returns text and you can't see what the recipe produces if it's an existing thing.

Re:Study: ChatGPT Outperforms Physicians in Quality, Empathe... by Kamq on Saturday April 29, 2023 @06:13PM (#35757774)
> Again, why go via an LLM and not a search engine to the actual source?

I believe the argument presented (possibly in a separate thread) was that search engines have degraded to the point where what they show you is worse than LLM output.

Re:Study: ChatGPT Outperforms Physicians in Quality, Empathe... by Dylan16807 on Saturday April 29, 2023 @07:28PM (#35758311)
There's no such thing as "the actual source" for how to make a type of food.