Ask HN: How are you using GPT to be productive?

Post by f6v » Sat, Mar 25, 2023, 4:42 PM UTC

throwthrowuknow wrote: post #459

roflyear wrote: post #356

Earlier quoted context omitted.

Don't make stuff up. There is no indication that will happen.

GPT-4 has a model capable of using around 50 pages of written text worth of tokens (32,000) not sure exactly how many lines of code that translates to but it’s a lot. GPT-3 can use 4k so that’s a huge increase, the next version could be even larger and there are other ML techniques that allow for massive context lengths. Copilot already does a good job of refactoring code and knows enough about your code base to use…

Post by fooker » Sat, Mar 25, 2023, 4:43 PM UTC

macNchz wrote: post #501

fooker wrote: post #471

Earlier quoted context omitted.

You have no idea if the alternative code you would have written would have been idiomatic or had some critical flaw. We have 50+ years of software engineering wisdom to deal with these issues. Testing, Fuzzing, version control, code reviews, the whole gauntlet.

I mean... I certainly know which languages I can write idiomatic code in and which I cannot. I can't know that my code will be free of critical flaws, but I do understand the common sources of flaws and techniques to avoid them, and I'm quite confident I can build small features like this that simply aren't vulnerable to SQL injection, on the first try and without requiring fuzzers or code review: https://infosec.exc…

Post by precompute » Sat, Mar 25, 2023, 4:45 PM UTC

wussboy wrote: post #521

VoodooJuJu wrote: post #330

Useful things: - As a thesaurus - What's the name of that "thing" that does "something" - kind of like fuzzy matching - A starting point for writing particular functions. For example, I wanted a certain string-manipulation function written in C, and it gave me a decent skeleton. However they're almost always very inefficient, so I have to optimize them. Things I've tried, that others seem to be blown away by, that I…

This is the kind of response that truly leaves me underwhelmed with Chat GPT. A thesaurus? A different kind of search engine? No thanks. I think Chat GPT would be useful to raise an almost infinite number of accusations against your enemies on social media, muddying the water with a deluge of garbage and poisoning every conceivable well with unlimited zeal. Are your societal purposes remotely at odds with my own? I'l…

Post by wussboy » Sat, Mar 25, 2023, 4:48 PM UTC

precompute wrote: post #526

wussboy wrote: post #521

Earlier quoted context omitted.

This is the kind of response that truly leaves me underwhelmed with Chat GPT. A thesaurus? A different kind of search engine? No thanks. I think Chat GPT would be useful to raise an almost infinite number of accusations against your enemies on social media, muddying the water with a deluge of garbage and poisoning every conceivable well with unlimited zeal. Are your societal purposes remotely at odds with my own? I'l…

That sort of stuff only works until the other side hasn't wised up to your act. Judging by how popular LLMs are going to be, "trust" on the internet will be non-existent.

Post by precompute » Sat, Mar 25, 2023, 4:50 PM UTC

grumple wrote: post #449

kkwteh wrote: post #378

Earlier quoted context omitted.

The top google search always comes with a lot of ads and other crap that you have to filter through. Also the response might not be exactly what your looking for (you might not have the same materials.) For instance you can ask chatgpt to create a practice plan that doesn’t require cones, or is focused on a certain set of skills, etc.

Just wait until sponsors start paying to have ChatGPT incept ideas into your mind. "Crucial next step is to buy some Rogaine", but significantly less obvious. Or other less obvious but highly impactful behavior modification like the algorithms used by TikTok/Instagram that push you in a certain direction or reinforce existing beliefs.