Current LLMs often produce much, much worse results than manually searching.

If you need to search the internet on a topic that is full of unknown unknowns for you, they're a pretty decent way to get a lay of the land, but beyond that, off to Kagi (or Google) you go.

Even worse is that the results are inconsistent. I can ask Gemini five times at what temperature I should take a waterfowl out of the oven, and get five different answers, 10°C apart.

You cannot trust answers from an LLM.

> I can ask Gemini five times at what temperature I should take a waterfowl out of the oven, and get five different answers, 10°C apart.

Are you sure? Both Gemini and ChatGPT gave me consistent answers 3 times in a row, even if the two versions are slightly different.

Their answers are inline with this version:

https://blog.thermoworks.com/duck_roast/

I created an account just to point out that this is simply not true. I just tried it! The answers were consistent across all 5 samples with both "Fast" mode and Pro (which I think is really important to mention if you're going to post comments like this - I was thinking maybe it would be inconsistent with the Flash model)

It obviously takes discipline, but using something like Perplexity as an aggregator typically gets me better results, because I can click through to the sources.

It's not a perfect solution because you need the discipline/intuition to do that, and not blindly trust the summary.

Did you actually ask the model this question or are you fully strawmanning?