Looks useful. But when you consider just how little time a senior developer actually spends developing, less so. If it could attend meetings on your behalf, or raise tickets for other teams to do stuff...
I honestly don't understand how copilot is helpful aside from filling in function signatures or keys in structs. For anything that is not boillerplate and takes the least amount of thought, it is just in the way. They really need to adjust the temperature on it or just have it not suggest things when it doesn't know.
I have never used it. I don't like to be too much influenced. Something that spit out code while you are writing is an influencer. I use Chat GPT style AI and review all the code before pasting it.
Can copilot understand and work on a legacy large spaghetti complex code base with various quality written by numerous come-and-go and offshore 900+ developers over the last 13 years ? it is easy to write code for green field projects from scratch . my 123yo neighbor can do that single-handedly
Im not using copilot yet, but Im using ChatGPT 4.0 while working on large corporate codebase developed by around 20 people. And my experience is that it is useful mostly on those tasks: 1) Question answering - our project has documentation online and public, so ChatGPT knows it and whenever I want to know how the part of the system works from user perspective, I can easily ask. For documentations that ChatGPT does not know, I can use RAG (chatgpt 4.0 with file attachement). 2) Refactoring - it can refactor parts of your code based on your instructions 3) Suggestions - good only for using some simple functions you dont remember how they are named and called. 4) Refactoring according to new frameworks - I was using it to change our components from react class to react functional and 4.0 did 70% of work on its own! 5) Code generation of repetetive code from templates - imagine you have some basic info like data from the server, you have several examples how the form can look like and LLM can generate rest of the code. Of course this can be achieved by metaprogramming like reflection and dynamic forms. But many times, forms have additional nuances that are more easily handled when its written staticaly by having real components here rather then dynamic ones from metadata. LLM can help you generate. 6) Code generation of tests - like previous step, this can be used as tool for generating e2e tests, because they are usualy sequential code. Basicaly any task that has the form of language translation can be done faster with LLMs - which testing is - take the form and translate it to tests - semantics is very similar, syntaxe is different. And the generation can be driven by instructions and examples. Copilot is basicaly ChatGPT 4.0 (althrough Codex is different model, they both perform well in programming), but Copilot has better integration with IDE. So the above points are valid also for copilot.
Its not going to pass. This "hype" is revolutionary. What will pass is coders of the past who do it all by hand. For example how the CNC took over hand machining. Every machinist said the same thing you just said. Now, good luck finding a machinist the same way you would when CNCs first came out. It may not be up to speed right now, it may make mistakes. But that will get better, and the job of a coder will turn into a job of prompting. Prompting and being able to CLEARLY explain what your looking to achieve is gonna be of high regards. Good luck 🤞🏾
Comprehensive talk on GitHub Copilot. Thanks!
This video deserves way more views. Sharing it with all my friends!
Looks useful. But when you consider just how little time a senior developer actually spends developing, less so. If it could attend meetings on your behalf, or raise tickets for other teams to do stuff...
That's not gonna change much. Whatever the copilot simplifies, will simply become what developers do. Just another abstraction like many before.
I love ❤️ the last reflection about being great engineers 👏🏻👏🏻👏🏻👏🏻
I honestly don't understand how copilot is helpful aside from filling in function signatures or keys in structs. For anything that is not boillerplate and takes the least amount of thought, it is just in the way. They really need to adjust the temperature on it or just have it not suggest things when it doesn't know.
Completely agree. Got the same experience. I have the impression that it has gotten worse in recent months
@@omidjung115yep it sucks
I have never used it. I don't like to be too much influenced. Something that spit out code while you are writing is an influencer.
I use Chat GPT style AI and review all the code before pasting it.
Can copilot understand and work on a legacy large spaghetti complex code base with various quality written by numerous come-and-go and offshore 900+ developers over the last 13 years ? it is easy to write code for green field projects from scratch . my 123yo neighbor can do that single-handedly
yes, if the codebase can fit into the model's context window
@@TheDanielLivingstoncontext window myass
@@tomjones8293please, tell us how you really feel...
Im not using copilot yet, but Im using ChatGPT 4.0 while working on large corporate codebase developed by around 20 people. And my experience is that it is useful mostly on those tasks:
1) Question answering - our project has documentation online and public, so ChatGPT knows it and whenever I want to know how the part of the system works from user perspective, I can easily ask. For documentations that ChatGPT does not know, I can use RAG (chatgpt 4.0 with file attachement).
2) Refactoring - it can refactor parts of your code based on your instructions
3) Suggestions - good only for using some simple functions you dont remember how they are named and called.
4) Refactoring according to new frameworks - I was using it to change our components from react class to react functional and 4.0 did 70% of work on its own!
5) Code generation of repetetive code from templates - imagine you have some basic info like data from the server, you have several examples how the form can look like and LLM can generate rest of the code. Of course this can be achieved by metaprogramming like reflection and dynamic forms. But many times, forms have additional nuances that are more easily handled when its written staticaly by having real components here rather then dynamic ones from metadata. LLM can help you generate.
6) Code generation of tests - like previous step, this can be used as tool for generating e2e tests, because they are usualy sequential code.
Basicaly any task that has the form of language translation can be done faster with LLMs - which testing is - take the form and translate it to tests - semantics is very similar, syntaxe is different. And the generation can be driven by instructions and examples.
Copilot is basicaly ChatGPT 4.0 (althrough Codex is different model, they both perform well in programming), but Copilot has better integration with IDE. So the above points are valid also for copilot.
blah blah blah, excited for this phase of hype to pass; anybody that has spent more than an hour with these things shares my opinion.
Its not going to pass. This "hype" is revolutionary. What will pass is coders of the past who do it all by hand. For example how the CNC took over hand machining. Every machinist said the same thing you just said. Now, good luck finding a machinist the same way you would when CNCs first came out.
It may not be up to speed right now, it may make mistakes. But that will get better, and the job of a coder will turn into a job of prompting. Prompting and being able to CLEARLY explain what your looking to achieve is gonna be of high regards. Good luck 🤞🏾
AI Hype is too much,
Marketing gimmick used by Tech Industry to grab Cash
Can't wait for all the buggy saas products written by cheap developers who don't properly review generated code.
Bit sales-y pitch.
yup too surface-level
Copilot is years behind the dotnet standard. Almost useless.
Explain.
@@DannyCookTheProgrammer Easy, these LLMs are usually trained on a couple years old data and not updated.
You are all making idiots of yourself
I can’t wait for these AI grifters to move onto something else and leave us alone.
But, does IT know cobol ? :)
Are there any cobol repos on GH?
plenty and sourceforge has GnuCOBOL, free, open source, and runs on Linux/Windows/Mac @@CripplingDuality