Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Command line functions around OpenAI

kadekillary.work

Post reply on HN
Print view View original

231–240 of 316 posts

Re: Command line functions around OpenAI

#231

Post by swader999 »

karmakaze wrote: post #170
austin-cheney wrote: post #43

Earlier quoted context omitted.

Define “efficient at writing code”. I find that for many people this means something primitive and absurd like typing faster or remembering things better. Being efficient in the perspective of writing new automation so you don’t have to do the same manual things again can easily make someone a 10x (or greater) engineer. This typically means writing your own tools and not hoping some third party package or framework w…

The other thing is making better choices of what to make, how to make it, and most importantly things not to do. That can often save 9x from most anything.

Yeah, being able to negotiate with the PM to still solve the problem in a easier way than initially proposed is probably where I've had the most impact over the years.

Re: Command line functions around OpenAI

#232

Post by Madmallard »

AdityaSanthosh wrote: post #192
Madmallard wrote: post #19

High level engineers solve the right problems quickly and put everything together in a resilient fashion. GPT4 may help them do that more quickly but they probably already will use copilot and templates and past project material and various generators for anything tedious. 10x engineering comes from someone who is trying to "be a better developer" actively for many years. Most people who just use the tools to create…

I'm interested about the macros automation. Could you point me to any resource?

These were things like keybinds and shortcuts within his editor (which 10 years ago this was Eclipse at Amazon). There were other scripts he had but I do not really recall at this point what they were doing. If you google macros for software engineers you can probably find some useful stuff.

Re: Command line functions around OpenAI

#233

Post by daveslash »

l33t233372 wrote: post #224
daveslash wrote: post #163

Earlier quoted context omitted.

RE>> Anyone can write a loop or an if statement. I had an intern a few years ago -- recent college grad in CompSci. I tried my best to lightly mentor him. One day I was talking about the diff between a compiled language and scripting, mentioned REPL. To demonstrate REPL, I opened up both the windows CMD prompt and the Chrome Developer tools. I mentioned that with a REPL like the Chrome Tools, it's trivial to do FizzB…

Too many students are being pushed through computer science courses, especially at smaller schools. How did this person pass a technical interview?

They didn't. I was one of two technical interviewers. We both recommended on passing [not hiring]. It was only a seasonal internship, so we weren't super grilling, but we still recommended a pass. We were overruled by the hiring manager who mentored this person outside of of the office.

Re: Command line functions around OpenAI

#234

Post by soiler »

novaRom wrote: post #180
brundolf wrote: post #161

Earlier quoted context omitted.

I think code-generation is a red herring. I'm more interested in things like: - Explanation/research ("how does this work?") - Code analysis ("tell me if you think you see any bugs, refactoring suggestions, etc in this sprawling legacy codebase") Things that feed into the developer's thought process instead of crudely trying to execute on what it wants

Unfortunately, LLMs are still prone to make facts up, and very persuasively. In fact, most of non-trivial topics I tried have required double-/triple- checking, so it's sometimes not really productive to use chatGPT. You are correct that I made an error in my previous response. I apologize for the confusion I may have caused in my previous response I appreciate you bringing this to my attention. I apologize, thank yo…

I asked it to explain how to use a certain Vue feature the other day which wasn't working as I hoped. It explained incorrectly, and when I drilled down, it started using React syntax disguised with Vue keywords. I definitely could have tried harder to get it to figure out what was going on, but it kept repeating its mistakes even when I pointed them out explicitly.

Re: Command line functions around OpenAI

#235

Post by enraged_camel »

nkingsy wrote: post #181
roenxi wrote: post #10

Being efficient at writing code can barely make someone a 5x engineer. A team of people who write code effectively is easy to do. Hyperproductivity in software is all about deciding what problems to tackle. Richard Hipp isn't worried about chipotle restaurant orders in golang, he's worried about how to store data reliably. That isn't a coding puzzle that ChatGTP is likely to help with. Either ChatGTP can do the whole…

I briefly worked with a software engineer who was making about a million dollars a year. I mentioned that an approach would be a lot of work. His response: “It’s just typing. Typey typey type (makes fingers on keyboard gesture).” Absolute lightbulb moment for me. To become a senior engineer is to realize that the code writing part is inconsequential as long as there are no technical unknowns in the work. It’s freed m…

>> We aren’t paid to write working code. We are paid to grow harmonious systems. Working code is table stakes.

With all due respect, you may have learned the wrong lesson — or missed some important context — and the above is a false dichotomy. Working code isn't just table stakes; it is virtually impossible to "grow harmonious systems" if you don't have solid working code, because without solid working code you cannot grow the system reliably.

The other thing to note is that just because someone makes a lot of money doesn't necessarily mean that they are good at their job, or that they are a good team player, or that the way they operate and the context they operate in applies to you. I know consultants who pull in a million or more every year, and you know how they do it? They write absolute shit software that, while fulfilling the contract requirements, ends up hamstringing the client down the line. Sometimes prioritizing short-term gains might be acceptable or even necessary (e.g. the auditor asks you to compile data from a bunch of sources and you need to do it fast), but for projects with longer life spans one should definitely not blindly "typey typey type".

Re: Command line functions around OpenAI

#236

Post by pixelbath »

Zetice wrote: post #185

Ok, dumb question, but does the API skip over the whole, "Thanks for asking that question, here's what I found:" stuff I keep seeing in ChatGPT when I ask it to generate non-text responses? Even when I ask it the "generate a 10 row csv containing sample chipotle restaurant order data with headers" prompt, I get "Sure, here's an example CSV file with 10 rows of sample Chipotle restaurant order data, including headers:…

Yes, echoing the input prompt is a feature of the API, which most people don't turn on by default, likely because it eats more output tokens: https://platform.openai.com/docs/api-reference/completions/c...

Re: Command line functions around OpenAI

#237

Post by l33t233372 »

daveslash wrote: post #233
l33t233372 wrote: post #224

Earlier quoted context omitted.

Too many students are being pushed through computer science courses, especially at smaller schools. How did this person pass a technical interview?

They didn't. I was one of two technical interviewers. We both recommended on passing [not hiring]. It was only a seasonal internship, so we weren't super grilling, but we still recommended a pass. We were overruled by the hiring manager who mentored this person outside of of the office.

> We both recommended on passing. It was only a seasonal internship, so we weren't super grilling, but we still recommended a pass

I’m confused. Are you using “pass” as in “pass on the candidate”(fail) instead of “pass” as it is used in the context of an exam?

Re: Command line functions around OpenAI

#238

Post by javajosh »

nkingsy wrote: post #181
roenxi wrote: post #10

Being efficient at writing code can barely make someone a 5x engineer. A team of people who write code effectively is easy to do. Hyperproductivity in software is all about deciding what problems to tackle. Richard Hipp isn't worried about chipotle restaurant orders in golang, he's worried about how to store data reliably. That isn't a coding puzzle that ChatGTP is likely to help with. Either ChatGTP can do the whole…

I briefly worked with a software engineer who was making about a million dollars a year. I mentioned that an approach would be a lot of work. His response: “It’s just typing. Typey typey type (makes fingers on keyboard gesture).” Absolute lightbulb moment for me. To become a senior engineer is to realize that the code writing part is inconsequential as long as there are no technical unknowns in the work. It’s freed m…

Oh yeah I know somebody who makes 2 million and disagrees. And he's twice as correct as your guy.

Re: Command line functions around OpenAI

#239

Post by fastball »

noncoml wrote: post #202

Am I the only one that doesn’t get it? I tried GPT and it’s unable to write anything but the most simple code from simple requirements. As a tiny bit of complexity and it’s lost. Are people at work dealing with tiny code bases with well defined requirements?

I don't know what kinda code-bases you work on, but I think there are many more potential factors which determine how useful GPT might be besides "tiny and well-defined". I won't try to enumerate them here, but as an example if you are working in a much more / entirely functional way, you can think of your entire code-base as tiny and well-defined, even if it is composed of 1000s of functions. Can think similarly if the arch is microservices.

Re: Command line functions around OpenAI

#240

Post by daveslash »

l33t233372 wrote: post #237
daveslash wrote: post #233

Earlier quoted context omitted.

They didn't. I was one of two technical interviewers. We both recommended on passing [not hiring]. It was only a seasonal internship, so we weren't super grilling, but we still recommended a pass. We were overruled by the hiring manager who mentored this person outside of of the office.

> We both recommended on passing. It was only a seasonal internship, so we weren't super grilling, but we still recommended a pass I’m confused. Are you using “pass” as in “pass on the candidate”(fail) instead of “pass” as it is used in the context of an exam?

Pass, as in "pass on the candidate (fail)". Apologies for the confusion. I've edited my comment for clarity. Thank you.
Post reply on HN