Live data from Hacker News

Command line functions around OpenAI

kadekillary.work

81–90 of 316 posts

Re: Command line functions around OpenAI

#81
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…

Oddly, I am most productive when I have time to be slow. I make 10x better decisions about what to do, how to do it, and in many cases why NOT to do it.

This isn’t very conducive to corporate work though. It’s about timelines and features promised to customers.

I find I’m 10x more productive in the long term on projects I’m a sole developer on or when working with a small knit team. And I don’t measure that in lines of code or number of features.

I wonder if ChatGPT can help there.

Re: Command line functions around OpenAI

#82
post #7

What the articles like this miss is that we understand pretty well how ChatGPT writes code. But what about maintenance, and particularly debugging? How would it make these tasks. And we know that these things take much much more time than writing code.

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.

Re: Command line functions around OpenAI

#83
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…

Good points. I feel obligated to tell you that it is spelled, ChatGPT not ChatGTP.

Apologies, it is very common for an LMM to make this kind of mitsakes.

Re: Command line functions around OpenAI

#84
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…

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…

I agree with the compounding impact of self-automation.

Also, some people just keep growing their creative outlook. They are not afraid to try solving bigger & bigger problems.

I worked with an engineer (individual contributor) at a company with a lot of related software products.

Time and again, he would hibernate then come out with a new well developed tool or product that either impacted the entire product line or started a new product line.

Once the value of what he had done was obvious, and his clever design had stabilized in a form understandable to others, he would hand it off to a team of great developers to polish, release, update etc.

10x impact would be an understatement.

If we measure impact, it is easier to see where 1x, 5x, 10x, or 100x can be achievable and verifiable.

Also x/2, x/10 or (and I have seen it) -x. One team leader, -5x at least, until they were removed.

Re: Command line functions around OpenAI

#85
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…

> But it won't make any old engineer a rival to the big names in software engineering. This stood out, so I looked it up, and it seems Richard Hipp is 61 years old. I guess it is more about the "any" than the "old". Or maybe old engineers are engineers doing it the "old way" (pre-chatgpt)?

"any old x" is an idiom that references "any random" or "any", indicating x being interchangeable or not special in any way. It has nothing to do with age.

Re: Command line functions around OpenAI

#86
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 mean saying that using ChatGPT will make you one of the most elite coders in the world is a pretty high bar no? I have been skeptical about all this, but decided to play with using ChatGPT for coding a task I had. It wasn't perfect, either in workflow or in final results but what was clear was that not adopting it will very quickly make you lag behind your peers. I think the additive bonus is especially high for se…

Can’t believe you were downvoted. Nuance and its appreciation are becoming rare.

Re: Command line functions around OpenAI

#87

Earlier quoted context omitted.

Writing code quickly may not help the mythical 10x engineer, but it might help a 1x engineer become a 5x engineer. In relative terms, the unaided 10x engineer is now only a 2x engineer as his peers are now vastly more productive. That's huge.

The GP is undermining their own point by even mentioning “5x, opening the door to think about this in linear terms. But the concept of a “10x engineer” was never about how fast they produce code, and the multiplier was never a fixed number. The point was that some engineers can choose the right problems and solve them in a way which the majority would never achieve even with unlimited time. As an example, if you took…

Maybe in 2030 the AI will be able to respond to that situation appropriately, like it won't just layer more sticky plasters on top with each additional requirement and make a mess but will re-evaluate the entire history of instructions and rearchitect/refactor the code completely if necessary?

And all this with documentation explaining what it did, and optimising the code for human readability, so that even with huge reworks you can still get the gist in a time measured in hours rather than it taking, what, weeks to do manually?

Re: Command line functions around OpenAI

#88

Earlier quoted context omitted.

... if churning out boilerplate is your definition of "productive".

If churning out boilerplate is what your employers sees as product, does it really matter? Coding udeals are valuable in a vacuum but most companies want those PRs merged, technical debt be damned.

If this is the case they need to up their abstraction game.

Re: Command line functions around OpenAI

#89
post #81
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…

Oddly, I am most productive when I have time to be slow. I make 10x better decisions about what to do, how to do it, and in many cases why NOT to do it. This isn’t very conducive to corporate work though. It’s about timelines and features promised to customers. I find I’m 10x more productive in the long term on projects I’m a sole developer on or when working with a small knit team. And I don’t measure that in lines…

> This isn’t very conducive to corporate work though. It’s about timelines and features promised to customers. [...] I wonder if ChatGPT can help there.

Obviously not, it will just make expected windows shorter and shorter.

"This would take a C developer a month, but you use Java so 2 weeks should suffice"

"This would take a Java developer two weeks, but you use Python so a week should suffice"

"This would take a Python developer a week, but you use ChatGPT so I'll expect it sometime tomorrow."

Re: Command line functions around OpenAI

#90
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…

I don't have a US credit card and a plus subscription I haven't had any issues.

FWIW I am using a UK debit card. It's hard to believe they would have reason to block cards from Belgium or Ireland.

Post reply on HN