I worked in a medium data center and there was no noise outside, no noise from the office in the same building, no noise outside the airlock, very loud inside.
Maybe huge datacenters are very different somehow?
Surface level is where you can find the most day to day value. Just today I've used it to get advice about putting up a treehouse, rough price ranges and differences between fridges, common fridge widths, adding second accounts to microG, command flags to identify slow tests, poe support for my wifi router, differences in laser measurement devices, french translation, medication storage, different types of olive, and drafting 3 emails in another language. All of this would have taken me way longer without these tools, I'm confident it gave good results because I know that the information exists and is common.
It regurgitates info in a way that is very specific to what and how you requested it. If you ask it a question already having an estimate of how accurate its answers will be, you can get a lot of value from it.
I think this really underpins the difference between the people that say AI is useless and those that say it's enhanced many aspects of their day to day lives.
...and my comment clearly isnt talking about that, but at the suggestion that its useless to write code with an LLM because you'll end up rewriting 50% of it.
If everyone has an opinion different to mine, I dont instantly change my opinion, but I do try and investigate the source of the difference, to find out what I'm missing or what they are missing.
The polarisation between people that find LLMs useful or not is very similar to the polarisation between people that find automated testing useful or not, and I have a suspicion they have the same underlying cause.
I keep seeing this argument over and over again, and I have to wonder, at what point do you accept that maybe LLM's are useful? Like how many people need to say that they find it makes them more productive before you'll shift your perspective?
you can tell them what to do though right? I think a lot of variance between people that say LLMs are useless and people that say they are useful is people that learn what they are good and bad at and can predict the quality of the output based on their input.
Like, I might ask an LLM on its opinion on the best way to break something down, to see if it 'thinks' of anything i havent, and then ask it to implement that. I wouldn't ask it to do the whole thing from scratch with no input on how to structure things.
I think this comes down to how you first learnt to learn. If I write notes in nodepad i dont remember them as well as if i write them by hand, but I think that's just a byproduct of years of school, and other people have learnt their own ways and are just as effective.
it has been years since I read the book, but I'm surprised that there's so much hatred for it here. From memory it seemed like fairly harmless things like give things good names, try to make the code readable, dont comment what the code does but why, use consistent formatting, avoid duplication.
Other than people going overboard with empty classes and inheritance Ive not really seen a problem of people breaking down functions too far.
It's been a long time since I've read the book but I took it to be less 'cut the function at X lines' and more 'long functions tend to be doing too many things at a time'. I think if you're able to give a good name to some sub section of a function, it's a good sign that it can be extracted out. At that point, you shouldnt need to look at the functions implementation unless its the specific function that you want to modify, because its name and arguments should be enough to know what it does and that you don't need to touch it.
Are we talking about the same thing and you'd still find that hard to understand?
Most people aren't building Formula 1 cars. Buildings are a better analogy: they are designed to be maintained. You can replace a door handle without replacing the door or the wall, you can turn off the power to different sections to do repairs. Dangerous or complex parts are labelled, moved into their own rooms or cupboards, and locked.
I've spoken to several people who've said things like 'id never thought of using chatgpt for that'. I dont think the autocomplete is at all an attempt to guess what you're trying to ask, but to broaden your considerations of what you could potentially ask it (to convert more of your every day googling/questioning over to chatgpt).
Its the other way around. It's about giving people the attention they need exactly because they dont keep in touch any more, so they have a reason to come back to the platform.
There was a link here a few weeks ago about UK energy that said that only about 30% of the cost of energy is the cost to produce, the rest is the infrastructure and the costs to pay some suppliers to stay online in case they are needed.
That many posts from friends would represent months worth of my friends posts. For most people facebook doesnt show friends posts because no one posts anymore.
I think maybe this is where the polarisation of those who find chatGPT useful and those who don't comes from. In this context, the number of r's in strawberry is not a fact: its a calculation. I would expect AI to be able to spell a common word 100% of the time, but not to be able to count letters. I don't think in the summary of human knowledge that has been digitised there are that many people saying 'how many r's are there in strawberry', and if they are I think that the common reply would be '2', since the context is based on the second r. (people confuse strawbery and strawberry, not strrawberry and strawberry).
Your apples question is the same, its not knowledge, it's a calculation, it's intelligence. The only time you're going to get intelligence from AI at the moment is to ask a question that a significantly large number of people have already answered.
They do lie in a predictable way: if you ask them for a widely available fact you have a very high probability of getting the correct answer, if you ask them for something novel you have a very high probabilty of getting something made up.
If I'm trying to use some tool that just got released or just got a big update, I wont use AI, if I want to check the syntax of a for loop in a language I don't know I will. Whenever you ask it a question you should have an idea in your mind of how likely you are to get a good answer back.
If I had a senior member of the team that was incredibly knowledgeable but occasionally lied, but in a predictable way, I would still find that valuable. Talking to people is a very quick and easy way to get information about a specific subject in a specific context, so I could ask them targetted questions that are easy to verify, the worst thing that happens is I 'waste' a conversation with them.