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

Did GitHub Copilot increase my productivity?

trace.yshui.dev

Post reply on HN
Print view View original

201–210 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#201

Post by thaumasiotes »

ToValueFunfetti wrote: post #94
tymscar wrote: post #88

Earlier quoted context omitted.

You are clearly not a dimwit, and you don’t only have way more experience than most people here, you also have some amazing projects under your belt. However I can’t help but notice that the vast majority of blogposts, talks, tweets, and basically everything else you do now is around LLMs. Do you not think that’s indicative of this being “hyped” and “shiny tools”?

If hype just means people are excited about it and talking about it, it should be a positive signal about the merit of the thing. I think people get the wrong idea by measuring P(X is good | people are excited about X) and finding it to be low. But P(X is good | people are not excited about X) is vastly lower, and 'hype' as here used is not really discrediting.

> I think people get the wrong idea by measuring P(X is good | people are excited about X) and finding it to be low. But P(X is good | people are not excited about X) is vastly lower

Only if you're including things that don't exist. If you restrict yourself to things that people might conceivably talk about, that probability is actually very high, for the simple reason that bad things are exciting specifically because they are bad.

Here are some boring things:

- bread

- sunlight

- air

- water

- parents

Note that starvation, darkness, suffocation, dehydration, and being orphaned are all much more exciting than their opposites.

Re: Did GitHub Copilot increase my productivity?

#202

Post by what-the-grump »

erhaetherth wrote: post #105
rm_-rf_slash wrote: post #40

Earlier quoted context omitted.

Yeah the copilot doesn’t need to be integrated into every keystroke, just able to analyze the context and kickstart the code. Getting up to speed with new libraries is so much easier with AI instead of the bad old days of trial-and-error-and-marked-as-duplicate

I especially like when I'm looking for a particular method on a class I've never used before and it just makes one up for me as though it exists.

It’s adding features that should have existed for you! It can also make up the documentation for the method while you are at it.

Re: Did GitHub Copilot increase my productivity?

#203

Post by YurgenJurgensen »

CaptainFever wrote: post #157
YurgenJurgensen wrote: post #153

Earlier quoted context omitted.

Then why not show me? Why is getting AI 'art' advocates to actually post something they think is good and explain why so hard? Where are these talented imaginative people and what are they doing?

Air Head by shy kids https://www.youtube.com/watch?v=G4wJ4WeJrz4 You also don't see the everyday people using it to generate pictures about their own experiences and lives, using it to populate their DnD worlds, their personal unpublishable fanfics, etc.

...and explain why you think it's good.

This part is important since I'm still yet to see evidence that the AI artist is capable of thinking more deeply than "(full_body:1.2) , best quality, (8k, RAW photo, best quality, masterpiece:1.2) , (realistic, photo-realistic:1.4) , ultra-detailed, (Kpop idol) , perfect detail, looking at the viewer, makeup, pretty South Korean lady wearing a bathing suit, wet skin, light reflections, angelic cute face, half body shot, short brownish black hair".

Re: Did GitHub Copilot increase my productivity?

#204

Post by couchand »

lozenge wrote: post #137
noduerme wrote: post #112

Earlier quoted context omitted.

adding an off the shelf ORM layer creates so much more opacity and tech debt than writing queries I don't understand why anyone would willingly put one into their stack. Sure, they're neat although I don't even know if they save time. There's something very satisfying about well-crafted queries. And is it ever really well crafted if you can't tweak them to improve their their execution plan? I've never had a client o…

ORM is not for writing analytics queries. It's for your CRUD operations. Something like Django Admin would be impossible without an ORM. You create tables for your business logic and customer support or whoever can just browse and populate them.

Wouldn't standard ANSI SQL's information_schema be sufficient to build such an interface? I'm struggling to see how an ORM is necessary.

Re: Did GitHub Copilot increase my productivity?

#205

Post by mhh__ »

YurgenJurgensen wrote: post #111
mhh__ wrote: post #11

Earlier quoted context omitted.

> spam The first 100 lines of any project is spam (usually 0 entropy), so AI is a nice win.

If the entropy is 0, you didn't need an LLM. If it's the same every time you can just copy and paste those 100 lines from GitHub or StackOverflow.

Why bother copying and pasting though, that's my whole point.

Google is terrible in comparison, just let it write the code for you.

Re: Did GitHub Copilot increase my productivity?

#206

Post by couchand »

blksv wrote: post #147
kaba0 wrote: post #124

Earlier quoted context omitted.

How do you map rows to objects? How do you insert into/update rows in your databases? These are the basic problems ORMs solve splendidly. They are for OLTP workloads, and have deliberate escape hatches to SQL (or some abstraction over it, like JPQL in java-land). I just fail to see what else would you do, besides implementing a bug-ridden, half-ORM yourself.

Rows are tuples, not objects, and treated as such throughout the code. Only the needed data is selected in the form most appropriate to the task at hand, constructed in a hand-written sql query, maybe even taylored to the DB/task specifics. Inserts/updates are also specific to the task, appropriately grouped, and also performed using plain sql. Data pipelines are directly visible in the code, all DB accesses are expl…

This. The right way to structure database access is a result type per tuple, not an object type per table.

Re: Did GitHub Copilot increase my productivity?

#207

Post by couchand »

klauserc wrote: post #148

I find GitHub Copilot close to useless for production code. The worst, most obscure bugs I've had to debug in the last year were all in Copilot-written code. It _looks_ plausible, but it makes extremely subtle mistakes. Occasionally, you have repetitive sections of code where it can copy&adapt lines from the context, but that's about it. It's a different story for test code. Test code is often formulaic and "standard…

Test code is code. It's as much of a burden as every other piece of code you are troubled with, so you must make it count. If you're finding it repetitive and formulaic, take that opportunity to identify the next refactoring.

Just churning out more near copies is not a good answer.

Re: Did GitHub Copilot increase my productivity?

#208

Post by mellosouls »

I really wish writers of and commenters on these articles (especially those less impressed) would clarify the version they have used and whether they have experimented significantly with state of the art.

Overwhelmingly in my experience of reading these back-and-forths, they are referring to 3.5 at best (as in this article).

Yes, of course I accept there are users of the paid version (4+) and class competitors like Opus that don't find they help their productivity but unfortunately any comments referring to significantly less capable engines than those - without at least clarifying that - risk just adding noise to the conversation.

Re: Did GitHub Copilot increase my productivity?

#209

Post by whywhywhywhy »

marcus_holmes wrote: post #87

Years ago, over a decade ago now, I was a .Net developer. Microsoft introduced Entity Framework, their new way of handling data in .Net applications. Promises made, promises believed, we all used it. I was especially glad of Lazy Loading, where I didn't have to load data from the database into my memory structures; the system would do that automatically. I could write my code as if all my memory structures were popul…

I feel pre November “dev day” 90% of the time I could trust GPT4 output to just work but post downgrades the increased amount of times I’ve copy and pasted then seen the error and realized there’s unfinished placeholder stuff, straight up parts not done or previous code removed that was important.

Just means I now spend a lot of time rewriting it which I could have just done in the first place but now I’ve wasted time asking GPT too.

Post reply on HN