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

191–200 of 316 posts

Re: Command line functions around OpenAI

#191

Post by haliskerbas »

mattgreenrocks wrote: post #183
nkingsy wrote: post #181

Earlier quoted context omitted.

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…

I have to ask: how do you work as an eng who pulls in $1m/yr?

High level IC at big tech can get you around that neighborhood

Re: Command line functions around OpenAI

#192

Post by AdityaSanthosh »

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?

Re: Command line functions around OpenAI

#193

Post by notjoemama »

I tried chatpt and asked a few questions about doing something specific in a Rails project. It was so specific that I had already found the sources online that were avaiable. It summarized the sources into directly actionable steps. At first I thought that was odd and unhelpful, but perhaps I expected too much. So then I tried giving it a prompt about setting up the devise ruby gem in a new rails project. That's one of those tasks that it helps to be familiar woth once and you can promptly forget; you'll rarely return to authentication in the lifetime of an app after its done and secure. It again presented me with the exact actionable steps for setup. I reviewed the gem's GitHub readme and found the response to be correct.

As far as I can tell, chatgpt performs the action of finding and simplifying the information needed to take the next step forward, with caveats for a lack of understanding unless asked and the potential to be inaccurate or wrong. But that's all it does at the moment. No better than asking the "devise expert" on my team how to setup devise from memory. Kinda cool experience, but I doubt it's a titanic shift because it doesn't have the depth of sematic meaning you and I do.

Re: Command line functions around OpenAI

#194

Post by throwthrowuknow »

globalise83 wrote: post #82
krsdcbl wrote: post #7

Earlier quoted context omitted.

Plain and simple: Feed the code it produced back into it and ask it to modify the sections needing maintenance or changes, or just tell it the issues you're having and ask it to explain/debug them.

Be careful! I have been experimenting with just this approach and ChatGPT 4 often forgets important parts of the code when generating the new files. If you ask ChatGPT to break down every change into step-by-step changes with code examples, it does a really great job and you can check every change yourself before implementing it.

A good prompt is key. If pasting code make sure to run it through the tokenizer first to make sure it’s not too long. Be very descriptive about what you want it to do. If it goes off the rails just hit the stop button and then edit your prompt with the little edit button at the top right and try again, this saves on context length and it saves the previous prompt and response so you can switch between them and compare.

Re: Command line functions around OpenAI

#195

Post by beebeepka »

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've only been using it for a few days and already find this post amusing. Almost hit a "come on, man, just get it" moment.

Incredible technology, though. Feels like whoever decides not to use it will be at huge disadvantage real soon

Re: Command line functions around OpenAI

#196

Post by throwthrowuknow »

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:…

Add: I only want the CSV, don’t describe what you are doing.

Re: Command line functions around OpenAI

#197

Post by shagie »

edgyquant wrote: post #104
uncletaco wrote: post #35

At what point did we stop making fun of that 10x engineer thread and started taking it seriously? Who forgot that 10x was a silly little thing that made zero sense in the real world?

Maybe the 10x engineer isn’t true, but I’ve worked at companies where I was on a team and my output was equal to the rest of the team combined. So if there isn’t such a thing it must mean that there are 1/10X engineers and they’re prevalent.

This might also be a bit of Price's Law in play (not saying that you aren't a 10x developer)...

https://dariusforoux.com/prices-law/

> Price’s law says that 50% of the work is done by the square root of the total number of people who participate in the work.

Price's square root law: Empirical validity and relation to Lotka's law https://www.sciencedirect.com/science/article/abs/pii/030645... (behind various paywalls)

If you're on a team of 10 people, 3 of those people will be doing about half the work. And then 7 are doing the other half. If there are 10 work units, the 3 are doing 5/3 of a work unit each and the 7 are doing 5/7 of a work unit each for a ratio of 2.3x

---

Yes, 1/10th developers are common - especially in larger teams. And there are also -1/2 developers too where someone will spend half their time just cleaning up after the -1/2 developer.

And just with the nature of teams, larger teams are going to have a significant fraction of the team doing very little work (note: this applies to consultancy teams too and if you get a team of 20 people to work on the project, you really should just get a team of 4 and stay on top of them as it will be less work to manage).

Re: Command line functions around OpenAI

#198

Post by hyperthesis »

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…

Iteration speed helps.

That said, the real work is insight away from the keyboard.

I think your "what problems to tackle" is overlapping management or business strategy - though yes, it absolutely is the greatest multiplier.

Re: Command line functions around OpenAI

#199

Post by jeanloolz »

esperent wrote: post #6

> First off, you’ll need an OpenAI API key. You can get this by going here and signing up. Note that you'll also need to be from a Western country, or at least have access to both a phone number from one and a VPN. And if you want a plus subscription, you'll also need a US credit card - not stated anywhere but I've been totally unable to sign up for plus with either Irish or Belgium cards, it just immediately flashes…

Signed up and subscribe with spanish card without any issues.

Re: Command line functions around OpenAI

#200

Post by jacobr1 »

surgical_fire wrote: post #178
angarg12 wrote: post #151

Earlier quoted context omitted.

I discussed my experience using ChatGPT in HN before and I was accused of being skeptical. But it isn't true at all, I think LLMs are a wonderful tool that will change software development. However I'm not worried about losing my job. As you say, I find the act of writing code is hardly the bottleneck to my productivity. One of the best case scenarios, LLMs become the ultimate high level language. In that case, Softw…

> As you say, I find the act of writing code is hardly the bottleneck to my productivity. When people claim ChatGPT can replace software engineers because it can sort of code is always puzzling to me. 20 years into this career, and writing code is only a minor part of my day-to-day activities. A part I do enjoy doing, but still minor part nonetheless. > What if you design an organization so that coding is the bottlen…

What amazes me when I talk to people that work in "non-tech" companies is how common boilerplate work is actually out there. Man-millennia of effort to move data from one system to another, or generate a report, or trigger something. The first AI MuleSoft or similar platform is going to kill it.
Post reply on HN