It's often that little edge piece of script that kills productivity. Something you need but off your beaten track that takes a few hours or days to figure out. That's ai coding will shine.
Command line functions around OpenAI
251–260 of 316 posts
Re: Command line functions around OpenAI
#252Earlier 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…
>> 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 canno…
Table stakes is a poker term meaning you can’t even play the game without it. There’s no dichotomy here.
I’d go further and say that in big tech, well factored well tested code is table stakes and the ability to produce it quickly is assumed. Junior engineers have to prove that to get their first promotion.
If that’s all they show, it will be their last promotion, and that’s perfectly fine too.
Re: Command line functions around OpenAI
#253Wow. 210+ comments and maaybe 10 of those actually talk about the article! (yes, I've read them all because I can't believe almost everyone missed the point) The point of the article is actually neat: a small shell (Fish) script to send query to ChatGPT or DALL-E and get response back in the terminal. As a terminal user myself, this is really nice! (I rewrote it for myself in bash which I use, but used the curl comma…
> everyone's just philosophising about the title
It's so easy to bait with a #x in a title, and especially when defining in terms of engineer (also an elusive term at times).
Re: Command line functions around OpenAI
#254I 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…
I often find myself delving into vendor code that is public methods but not necessarily advertised in their documentation.
I'm working on trying to figure out lang chain to basically feed it all my vendor and node module code and their respective docs, so basically hallucinating goes way down and the info is as fresh as my cron job to rebuild the langchain embeddings.
I'm doing this for laravel, filamentphp, livewire, alpinejs, vuejs, nextjs, react, svelte, typescript, and PHP docs as well, mostly just the docs... I'll probably work on limiting the info to the most important things or just docs for some of the things...
I'm then planning on having gpt agents specifically tuned to write unit tests another to write code, another to review the code another to run and validate the tests, another to model data and create migrations, etc ...
naked chatGPT can do a lot, adding custom embeddings changes it into a master of x topic and levels it up 10 fold.
Re: Command line functions around OpenAI
#255Not mentioned in post this but occured to me by reading: I think I will start changing my functional prompts to require a JSON format in responses so that various aspects of the response don't need to be manually parsed, and requests can be more reliably piped to subsequent requests.
> Not mentioned in post this but occured to me by reading:
> I think I will start changing my functional prompts to require a JSON format in responses so that various aspects of the response don't need to be manually parsed, and requests can be more reliably piped to subsequent requests.
that adds more characters though so maybe hits token limits faster, I was thinking about how to have better contexts then found out about langchain and creating a sort of long term memory using vector databases. still trying to figure this out, but once I do, I think it'll be amazing what I can do with it.
Re: Command line functions around OpenAI
#256Earlier quoted context omitted.
a good programmer is almost certainly a fast typer of course a fast typer does necessarily make a good programmer
Yes and no. Most of my stuff is automated, auto completion and micro code gen. My thinking is the bottleneck, never typing speed. Measured it last summer a few times trying to beat my daughter and I think it was about 60wpm. For coding if I know what I'm doing its probably 30wpm in my editor.
Yeah, these days, IDEs like JetBrains are powerful enough that you can pull off significant chunks of refactors with a few right clicks (any sort of renaming, moving of methods, or deletion of code)
Typing will get you places faster, but some of the most productive tools we have don’t rely on it at all.
Re: Command line functions around OpenAI
#257Earlier quoted context omitted.
What does IC mean? Doesn't seem to be very googleable
IC means integrated circuit.
Ichabod Crane
Re: Command line functions around OpenAI
#258Earlier 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…
> they will just be average or much worse when their motivation is destroyed Ouch
That's true, and I'd lean on the "much worse" side. When you join a project that has very minimal tooling and almost no automation, you're facing a dilemma: should I focus on improving the tooling while delaying features or should I deliver features while making future improvements ever harder to make?
The problem with this is that neither is good for your mental health. Unless you're joining that project with a specific goal of improving its development process, don't bother. Run away. Fast.
Especially if there are already other devs that are militantly against your take on dev process improvements. The level of emotional distress is hard to fully appreciate without experiencing a situation like this. Suggesting the simplest and most obvious things becomes a brutal fight that you're guaranteed to lose. Living without them makes you miserable in its own right. You're trapped between a rock and a hard place with no way out.
If out of various kinds of psychotherapy you pick the one based on an experience of living in a Nazi concentration camp as the most applicable - it's time to run. Really. Don't look back.
Re: Command line functions around OpenAI
#259Earlier quoted context omitted.
>> 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 canno…
Table stakes is a poker term meaning you can’t even play the game without it. There’s no dichotomy here. I’d go further and say that in big tech, well factored well tested code is table stakes and the ability to produce it quickly is assumed. Junior engineers have to prove that to get their first promotion. If that’s all they show, it will be their last promotion, and that’s perfectly fine too.
I think this is very accurate to my experience in big tech. As a person who's only gotten that "first promotion" so far, I'd be interested to hear your summaries of what attributes / skills are looked for at successive levels: e.g. what engineers need to prove to get promoted to Senior, Staff, Senior Staff, etc.
Re: Command line functions around OpenAI
#260Earlier quoted context omitted.
I have to ask: how do you work as an eng who pulls in $1m/yr?
(throwaway I guess) I make over $1m as a SWE. “Senior Staff” or “Level 7” role at a big tech company everyone knows. I mostly write code! I am way faster than most others here, and I have encouraged and mentored the people on my team to be similarly efficient. I also help decide technical direction but it’s far from the “architecture astronaut” stereotype that writes no code. It’s an infra team so no significant infl…
Is that TC or salary?