Live data from Hacker News

Did GitHub Copilot increase my productivity?

trace.yshui.dev

31–40 of 326 posts

Re: Did GitHub Copilot increase my productivity?

#31

Earlier quoted context omitted.

I’d love to know the specifics on the ppl hiring the consultants and the work output. In my experience you need someone with experience to chain together any genAI output, as well as validate that it’s even correct. It’s not like it magically does everything for you.

Correct, but that was also the point; all these ‘consultants’ are senior programmers. Nothing is magically done; they use the ai to do the work they were mostly doing before with more people/themselves without ai; now they just focus more on business side. Higher pay and harder to replace (for now). My company does the same but in a niche; our specific tooling is easier to automate (which we did/are still doing) and…

> he saw his EU clients cancelling all his contracts because his people could be replaced by openai

But this is what I want to know. They thought they could replace the ppl in the first place.

Re: Did GitHub Copilot increase my productivity?

#35
post #29

GitHub touts a 55% improvement in coding speed based on a study conducted in-house that tested the participants’ ability to paste a pre-written prompt and then check the output: https://github.blog/2022-09-07-research-quantifying-github-c... The effectiveness of a Copilot-like tool trialed at FB showed that 8% of code contributed by participants was sourced from suggestions, but the latter study made no promise about…

This last sentence is the most important. You can describe your dB schema in words and get laravel migration, models, controllers and if you wanted policies, form requests etc all near perfect. You can get a V1 in 10-20 minutes then go about handling all the actual logic

Re: Did GitHub Copilot increase my productivity?

#36

Local maxima go BRRRRRRR AI will get there eventually, but this current paradigm seems increasingly only useful for spam and shitty clip art. Even so, everyone is throwing absurd amounts of investment capital at it in the hopes that something useful will happen. It's a pretty clear depiction of the investor class being so detached from the technical reality of what they're investing in that they just sit around light…

Yeah; its concerning how depressingly similar Sam's recent language is to, say, SBF's in his prime. Waxing poetically with faux-intellectualism about the sheer addressable market his business will capture (all of humanity) (and funded by the government) [1]. You can just listen to key players in the space, how their language has changed over the past year, and recognize that we're probably very near a local maxima / plateau / AI winter.

Reality is: AI is startlingly expensive. Stupid, stupid expensive. Microsoft is building "Stargate", their $100B AI-focused supercomputer [2]. The money to build that isn't coming from selling AI services. Its coming from their old, boring, tried and true businesses; Windows, Office, Azure, and M365. Xbox is dying before our eyes. Their tried and true businesses make great money but aren't growing. Its up to AI to prove to investors that their P/E multiple is justified.

[1] https://twitter.com/tsarnick/status/1789107043825262706

[2] https://www.tomsguide.com/ai/meet-stargate-the-dollar100-bil...

Re: Did GitHub Copilot increase my productivity?

#37
post #16
post #8

Earlier quoted context omitted.

I've been finding this stuff genuinely useful for two years now, across Copilot and ChatGPT and Claude 3 Opus and similar tools. Either I'm a dimwit, easily conned by hype and shiny tools to the point that I can imagine benefits for two years that simply aren't there... or there's something to them.

I don’t think you’re a dimwit but I read your post[1] with an example and I am curious to whether you feel you’re losing something by telling the LLM it’s wrong and to try again, rather than going through the exploratory/iterative learning process yourself. For example, would you have known to ask about GeoJSON if you had not come across and learned about it pre-LLM? More succinctly: do you feel you’re learning more…

Absolutely I could have learned more from that particular project if I'd spent more time with it rather than getting the LLM to do the work... but that's why I like it as an example: since it was effectively a distraction (a "side quest") the alternative wasn't learning more, it was not doing it at all (and learning nothing).

I'm able to get really great results out of LLMs because I have 20+ years of experience helping me know what questions to ask of them.

I do feel like my rate of learning has increased though, because I'm much more likely to try out a completely new technology when I know an LLM can flatten the learning curve for me a bit.

Re: Did GitHub Copilot increase my productivity?

#38
post #16

Earlier quoted context omitted.

I don’t think you’re a dimwit but I read your post[1] with an example and I am curious to whether you feel you’re losing something by telling the LLM it’s wrong and to try again, rather than going through the exploratory/iterative learning process yourself. For example, would you have known to ask about GeoJSON if you had not come across and learned about it pre-LLM? More succinctly: do you feel you’re learning more…

You seem to be writing from a lost world when people enjoyed coding because they enjoyed learning new things with every project. I think that's sadly something only enjoyed at work by a very small minority these days.

I very much aim to learn something new with every project. The thing I like most about working with LLMs is that they let me take on MORE projects!

Re: Did GitHub Copilot increase my productivity?

#40
post #29

GitHub touts a 55% improvement in coding speed based on a study conducted in-house that tested the participants’ ability to paste a pre-written prompt and then check the output: https://github.blog/2022-09-07-research-quantifying-github-c... The effectiveness of a Copilot-like tool trialed at FB showed that 8% of code contributed by participants was sourced from suggestions, but the latter study made no promise about…

This last sentence is the most important. You can describe your dB schema in words and get laravel migration, models, controllers and if you wanted policies, form requests etc all near perfect. You can get a V1 in 10-20 minutes then go about handling all the actual logic

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
Post reply on HN