The worst part about this to me is if someone routes a response through AI, I have no idea what they, personally, are trying to tell me that they may have included specifically in their prompt, what is hallucination, and what is something in-between.
It makes it hard to pick apart hallucinations from the miscommunications and disagreements. Picking apart every single point and treating it with the same tact you have to treat human output with, while still accounting for the fact that it could be a hallucination, takes an extremely skewed amount of effort compared to the effort of sending someone AI output. The worst part is, it's probably going to be pasted right back into the LLM chat box.
It's astonishingly bad form to send someone AI output, and this is only one of the reasons.
It's not an acceptable tradeoff to allow AI code in without reviewing the code currently, if not when it comes to code structure (which will introduce long term maintenance issues if it creates endless spaghetti code regardless of if AI is contributing or not), then at least when it comes to security.
Even with git-prime reducing the address space by a few orders of magnitude, there's still (effectively) zero chance for collision. The difference between 10^-29 and 10^-27 isn't that great in practice.
Actually there are π(N) ~ N / ln(N) primes less than N per the Prime Number Theorem, so π(2 ^ 160) ~ 2 ^ 153.2 - this only drops 7 bits. So that does increase the odds of collision but much less than what I expected!
I view current LLMs as new kinds of search engines. Ones where you have to re-verify their responses, but on the other hand can answer long and vague queries.
I really don't see the harm in using them this way that can't also be said about traditional search engines. Search engines already use algorithms, it's just swapping out the algorithm and interface. Search engines can bias our understanding of anything as much as any LLM, assuming you attempt to actually verify information you get from an LLM.
I'm of the opinion that if you think LLMs are bad without exception, you should either question how we use technology at all or question this idea that they are impossible to use responsibly. However I do acknowledge that people criticize LLMs while justifying their usage, and I could just be doing the same thing.
Exactly. Using them to actually “generate content” is a sure fire way to turn your brain into garbage, along with whatever you “produce” - but they do seem to have fulfilled Google’s dream of making the Star Trek computer reality.
I only reached the 100s back in the day. What amazed me was that it seemed like every problem had a paper solution, when it would take any computer algorithm thousands or millions of computations to solve the same problem.
I played around with some of the easier problems, my favorite was a couple times when starting with the obvious brute force solution in code and then refactoring and simplifying it iteratively ended up getting me the paper solution.
Keywords should definitely be highlighted. It's part of the structure of the code. Being highlighted makes it very quick to distinguish between keywords and variables and helps readability by making them easier to skim over and jump to. Maybe they could be the same color as punctuation, if number of colors is a problem.
I also like minimal themes (and light mode!) but keywords are precicesly the thing I want highlighted. The "Visual Studio(Light)" theme in VSCode gets it pretty close to what I want but still has some inconsitencies that bug me but I haven't bothered making my own to fix them yet. It primarily just highlights keywords, comments, strings.
But then you can have something like public async Task<byte[]> SomeMethod(DateTime date, int someNumber) and int is highlighted but DateTime isn't...
Sounds lovely, I'd love to hear what it's like when the number of living cells on screen controls the length of the note so it's not just a constant rhythm, even though it is hypnotizing.
>The discipline required to use AI tools responsibly is surprisingly difficult to maintain
I don't find that this requires discipline. AI code simply requires code review the same as anything else. I don't feel the need to let AI code in unchecked in the same way I don't feel the need to go to my pull request page one day and gleefully hit approve and merge on all of them without checking anything.
Prime numbers are a pattern; take the natural numbers - starting after 2, exclude every number that isn't 2, starting after 3, exclude every number that isn't 3, etc.
It repeats like this predictably. Even though it changes, the way in which it changes is also predictable. Their repetition and predictability make prime numbers a pattern.
Out of the fundamental pattern of prime numbers, higher-level patterns also appear, and studying these patterns is a whole branch of math. You can find all kinds of visualizations of these patterns, including ones linked in this thread.
It's not that you're seeing a pattern that's not there, it's that you're seeing a pattern that gradually becomes infinitely complex.
It makes it hard to pick apart hallucinations from the miscommunications and disagreements. Picking apart every single point and treating it with the same tact you have to treat human output with, while still accounting for the fact that it could be a hallucination, takes an extremely skewed amount of effort compared to the effort of sending someone AI output. The worst part is, it's probably going to be pasted right back into the LLM chat box.
It's astonishingly bad form to send someone AI output, and this is only one of the reasons.
reply