“We envision a system where the programmer writes a few of lines of code, hits a button and the rest of the code appears. And not only that, the rest of the code should work seamlessly with the code that’s already been written.”<p>I'm skeptical...<p>'Writing computer programs could become as easy as searching the Internet. A Rice University-led team of software experts has launched an $11 million effort to create a sophisticated tool called PLINY that will both “autocomplete” and “autocorrect” code for programmers, much like the software that completes search queries and corrects spelling on today’s Web browsers and smartphones.'<p>Interested, but very, very skeptical...
From this article, I have absolutely no idea what this software will actually do.<p>Can anyone enlighten me as to what they are actually trying to do, from the perspective of an actual software developer?<p>Or did they just successfully string together the correct sequence of buzz words to unlock the grant money?
As usual, the future is already here, just unevenly distributed.<p><a href="https://github.com/capitaomorte/yasnippet" rel="nofollow">https://github.com/capitaomorte/yasnippet</a><p>I do wonder if you gave $11M to João Távora what the end result would be. Probably pretty cool.
I half-remember they tried to do a subset of this with some LISP/SCHEME, but it didn't pan out too well.<p><a href="http://en.wikipedia.org/wiki/DWIM" rel="nofollow">http://en.wikipedia.org/wiki/DWIM</a>
It's a great idea. But, what code base is this autocomplete going to run off of?<p>If they are thinking of sourcing the internet itself, there had better be some kind of omniscient, all powerful proofreader in place, because there are a lot of people that submit a lot of code that is HORRIBLY insecure, inaccurate, prone to breakage or just plain spaghetti.<p>I'd hate to be working on a missile guidance system, only to press <tab> to complete a code block and end up getting some Intel Pentium FDIV instructions.
The announcement itself is pretty sparse on the proposed approach, but given the research interests of Swarat Chaudhuri [1] and Moshe Vardi [2], I would guess they will attempt to combine recent advancements in program synthesis, program verification, and code mining.<p>Program synthesis: There has been a lot of interest in the formal methods community to automatically generate programs (for small instances) with the target specification coming from input-output examples (e.g., Excel Flash Fill [3]), program templates or holes (called Sketches [4]), reactive models of adversarial environments, formal invariants etc. Also the solution techniques used vary considerably: from game theoretic solving, SAT solvers, model checkers, to version-space algebras and others. The community has not yet fixated on a specification language, or a solving technology. The industrial nature of the tools being leveraged (e.g., model checkers and SAT solvers from the hardware community) gives hope for promising developments. A Berkeley course [5] covers a good spectrum of the current developments.<p>If I were to guess, maybe the Rice researchers are approaching the code completion/correction problem as mining for fragments of large codebases that are incomplete/incorrect and applying program synthesis to fill those fragments. Of course that would mean that they would also need to mine the specification requirements for those fragments. All of this is easier said than done, and it would be an ambitious project. Swarat has also done some really cool work on "probabilistic reasoning for programs" and "verification of probabilistic programs", so that might be part of it too. (Of course, I may be completely off-base! After all, we are commenting on a non-technical funding announcement here.)<p>[1] Swarat's publications: <a href="http://www.cs.rice.edu/~sc40/pubs/" rel="nofollow">http://www.cs.rice.edu/~sc40/pubs/</a><p>[2] Moshe's publications: <a href="http://www.cs.rice.edu/~vardi/papers/index.html" rel="nofollow">http://www.cs.rice.edu/~vardi/papers/index.html</a><p>[3] Excel's FlashFill from Sumit Gulwani, researcher@MSR: <a href="http://research.microsoft.com/en-us/um/people/sumitg/flashfill.html" rel="nofollow">http://research.microsoft.com/en-us/um/people/sumitg/flashfi...</a><p>[4] The Sketch program synthesizer: <a href="https://bitbucket.org/gatoatigrado/sketch-frontend/wiki/Home" rel="nofollow">https://bitbucket.org/gatoatigrado/sketch-frontend/wiki/Home</a><p>[5] Ras Bodik/Emina Torlak: Berkeley course material on Program Synthesis: <a href="http://www.cs.berkeley.edu/~bodik/cs294fa12" rel="nofollow">http://www.cs.berkeley.edu/~bodik/cs294fa12</a>
Posted just a bit later on HN: <a href="http://codesnippet.research.microsoft.com/" rel="nofollow">http://codesnippet.research.microsoft.com/</a>
"PLINY is part of DARPA’s Mining and Understanding Software Enclaves (MUSE) program, an initiative that seeks to gather hundreds of billions of lines of publicly available open-source computer code and to mine that code to create a searchable database of properties, behaviors and vulnerabilities."<p>I feel that the reason DARPA is willing to fund this is because of that last part: "vulnerabilities".
Autocomplete + the Internet already erodes many programmers skills to the point where they can barely write code without help. I can't imagine what this kind of tool would do.<p>Not that there is anything wrong with autocomplete. I certainly use it, but I've seen a lot of programmers that barely understand the code they are writing.