gnus_migrate

@gnus_migrate@programming.dev

• ⁨Comment⁩ on ⁨Why I use the D programming language for scripting⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  DMD is the reference implementation as far as I know, so I don’t think they have the same issue that C and C++ have with regards to needing to have a standard that pleases everyone. I agree that it has an issue positioning itself relative to other languages, but to me D is the “boring” language. It has most of what you need, there is very little that is surprising in it.

• ⁨Comment⁩ on ⁨The Fall of Stack Overflow⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Yeah but will people still care about contributing that information if they’re not going to be compensated for it in any way? Like people get something out of contributing to stack overflow, even if it’s just recognition. This is gone with ChatGPT.

• ⁨Comment⁩ on ⁨The Fall of Stack Overflow⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  I can think of four aspects needed to emulate human response: basic knowledge on various topics, logical reasoning, contextual memory, and ability to communicate; and ChatGPT seems to possess all four to a certain degree.

  LLM’s cannot reason, nor can they communicate. They can give the illusion of doing so, and that’s if they have enough data in the domain you’re prompting them with. Try to go into topics that aren’t as popular on the internet, the illusion breaks down pretty quickly. This isn’t “we’re not there yet”, it’s a fundamental limitation of the technology. LLM’s are designed to mimick the style of a human response, they don’t have any logical capabilities.

  Regardless of what you think is or isn’t intelligent, for programming help you just need something to go through tons of text and present the information most likely to help you, maybe modify it a little to fit your context. That doesn’t sound too far fetched considering what we have today and how much information are available on the internet.

  You’re the one who brought up general intelligence not me, but to respond to your point: The problem is that people had an incentive to contribute that text, and it wasn’t necessarily monetary. Whether it was for internet points or just building a reputation, people got something in return for their time. With LLM’s, that incentive is gone, because no matter what they contribute it’s going to be fed to a model that won’t attribute those contributions back to them.

  Today LLM’s are impressive because they use information that was contributed by millions of people. The more people rely on ChatGPT, the less information will be available to train it on, and the less impressive these models are going to be over time.

• ⁨Comment⁩ on ⁨The Fall of Stack Overflow⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Hey, if people are going to go back to reading manuals like we’re in the 1980’s again is it such a bad thing? /s

  It’s insane how a single tool managed to completely destroy the value collectively created by people in over a decade.

• ⁨Comment⁩ on ⁨The Fall of Stack Overflow⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  We’re not able to properly define general intelligence, let alone build something that qualifies as intelligent.

• ⁨Comment⁩ on ⁨Unit testing isn't enough. You need static typing too.⁩ ⁨⁨1⁩ ⁨year⁩ ago⁩:

  Also being able to prove the relationship between different parts of the code enables a lot of productivity tooling like IDEs. Simple things like renaming a class or a struct become chores at best in a statically typed language, whereas in dynamic languages there is an element of risk in refactorings like that.