My AI Adoption Journey

I only go with resources where the text is actual documentation of their testing and/or the steps they've made, or other important details (e.g. SeriousEats, Whats Cooking America / America's Test Kitchen, AmazingRibs, Maangchi for Korean, vegrecipesofindia, Modernist series, etc) or look for someone with some credibility (e.g. Kenji Lopez, other chef on YouTube). In this case the text or surrounding content is valuable and should not be skipped. A plain recipe with no other details is generally only something an amateur would trust.

If you need a recipe, you don't know how to make it by definition, so you need more information to verify that the recipe is done soundly. There is also no reason to assume / trust that the LLMs summary / condensation of various recipes is good, because cooking isn't something where you can semantically condense or even mathematically combine various recipes together to get one good one. It just doesn't work like that, there is just one secret recipe that produces the best dish, and LLMs don't know how to judge quality of recipes, mostly.

I've never had an LLM produce something better or more trustworthy than any of those sites I mentioned, and have had it just make shit up when dealing with anything complicated (i.e. when trying to find the optimal ratio of starch to flour for Korean fried chicken, it just confidently claimed 50/50 is best, when this is obviously total trash to anyone who has done this).

The only time I've ever found LLMs useful for cooking is when I need to cook something obscure that only has information in a foreign language (e.g. icefish / noodlefish), or when I need to use it for search about something involving chemistry or technique (it once quickly found me a paper proving that baking soda can indeed be used to tenderize squid - but only after I prompted it further to get sources and go beyond its training data, because it first hallucinated some bullshit about baking soda only working on collagen or something, which is just not true at all).

So I would still never trust or use the quantities it gives me for any kind of cooking / dish without checking or having the sources, instead I would rely on my own knowledge and intuitions. This makes LLMs useless for recipes in about 99% of cases.

I'd already abandoned it for generating code, for all the reasons everyone knows, that don't need to be rehashed.

I was still in the camp of "It's a better google" and can save me time with research.

The issue it, at this point in my career (30+ years) the questions I have are a bit more nuanced and complex. They aren't things like "how do I make a form with React".

I'm working on developing a very high performance peer server that will need to scale up to hundreds of thousands to a million concurrent web socket connections to work as a signaling server for WebRTC connection negotiation.

I wanted to start as simple as possible, so peerjs is attractive. I asked the AI if peerjs peer-server would work with NodeJS's cluster server. It enthusiastically told me it would work just fine and was, in fact, designed for that.

I took a look at the source code, and it looked to me like that was dead wrong. The AI kept arguing with me before finally admitting it was completely wrong. A total waste of time.

Same results asking it how to remove Sophos from a Mac.

Same with legal questions about HOA laws, it just totally hallucinates things thay don't exist.

My wife and I used to use it to try to settle disagreements (i.e a better google) but amusingly we've both reached a place where we distrust anything it says so much, we're back to sending each other web articles :-)

I'm still pretty excited about the potential use of AI in elementary education, maybe through high school in some cases, but for my personal use, I've been reaching for it less and less.

AI written code is often much easier to read/review than some of my coworkers'