|TLDR Explains Code Like I Am Five
|Written by Nikos Vaggalis
|Monday, 05 December 2022
TLDR is a plugin for the popular JetBrains IDEs that explains what a piece of code does in natural English. It's a big productivity boon for developers.
TLDR, although based on OpenAI's Codex, the model that's also powering GitHub Copilot, does not intend to help you write code or automate anything. Instead it attempts to decipher what a piece of code does by producing a narrative in natural English, saving hours when trying to read and comprehend it.
As programmers, one skill that must be mastered is reading code. This is manifested in a variety of ways:
Code generation is nothing new to the world of programmers; it was there even before the advent of Windows Forms or Macromedia Dreamweaver; drag and drop your GUI elements on a visual plane and get the code generated, ready to be deployed in production.
The other way around, generating specifications from code is already a thing too; check Swagger for instance which generates OpenAPI definitions from existing (Java) APIs code.
The next step in the evolution ladder subvened by the recent achievements of AI is assisted coding. Intelligent code completion, documentation and code searching across multiple sources, auto completing incomplete code and revealing syntax errors as you go.
And then, there's Github Copilot. Based on OpenAI's Codex, an AI system that is a descendant of GPT-3, was trained on massive amounts of data that contain both natural language and billions of lines of source code from publicly available sources.
Copilot is a game changer as it can interpret natural, albeit simple, language, to write fully blown working code on the userâ€™s behalf. That is unlike other code completion tools which suggest one-liners, Copilot generates entire functions. Copilot can:
This last feature is still in an experimental stage and available only as a VS Code extension for the time being.
If you are a Jetbrains fan, there's TLDR, a plugin compatible with the Jetbrains range of IDEs, based on the same model as Copilot and the same explaining code abilities. Saying that, it would be very interesting for someone to produce a side by side comparison of both of those tools, to check which has the best outcomes when applied on the same piece of code.
One test I run on TLDR was with Intellij Community edition and Java. Having seen the demos (on PHP) and trying it myself on some Core Java snippets I can say that the results were pretty good. Then I decide to explore its wider potential. Would it also be applicable to code dependent on third party library imports or frameworks?
So I applied it on an under-development Vaadin/Spring Boot based app. I first analyzed a short Vaadin snippet of creating a Login View:
This is what it gave me back:
You can't possibly read this so here's a transcription:
Then I thought that it would be interesting to try it on Spring security configurations which are notoriously hard to get right and decipher their meaning.
(For the curious, I disable the csrf protection of Spring Security as Vaadin handles it internally.)
This is the transcription of the result:
One observation though... I don't know what "(more on that later)" or "- see below" refer to.
I can say, that it was spot on! Very very impressive indeed... next time I stumble upon on such a security configuration one-liner, I know where to turn to. However I couldn't try it on more snippets because the free version is limited and allows you just two attempts per day. I will have to wait for tomorrow to run another two, perhaps on a more elaborate piece of code, or what about a complex regular expression?
The deal here is that reading code is much more difficult to do than writing it and an assistant like this is going to prove valuable in reducing the time you need to comprehend it.
One concern that I have regarding both Copilot and TLDR, is that of privacy, since they both expose an API which is called upon with your code as the payload. The AI to interpret your code lives on their servers after all. I haven't gone through their privacy policies and I'm pretty sure that there aren't any malevolent spying clauses but one who wants to use their products in production should first check.
At the end of the day, the question is, what does the future hold for programmers? Are we doomed as a profession? Will AI take our jobs too?
OpenAI's ambitions in the long term do not stop at Copilot or TLDR; they want users to employ natural language to control APIs. This would be immensely beneficial in for example querying databases the same way we do with search engines like Google;type a sentence in your mother language to query a database instead of writing SQL. This will not only help data professionals in creating reports and dash boards faster but it will also make it feasible for non technical users to get access to the source data.
The story of coders' jobs being obliterated is not new. It has been told many timeds before even before the advent of AI. The villains were the low code and the no code tools;they would make coders redundant.
But the difference lies between the terms coder vs software engineer. Coding might be threatened but engineering software is not. Engineering software means understanding and refining requirements, translating business logic, thinking architecturally,
Instead I suggest looking at these as tools that will increase productivity just like the Windows Forms GUI generator did.
High level languages like Python or Java make programming easier and more accessible to more developers, than when there was with just C. These tools aim to do the same. High level languages did not reduce jobs, they increased them.
In conclusion, the key here to realize is that an AI can't cope with the reasoning and wide range of skills required in engineering software. But it can undoubtedly be a useful aid.
For the time being enjoy TLDR.
|Last Updated ( Friday, 01 September 2023 )