Robots Are After Your Job: Exploring Generative AI for C++ - Andrei Alexandrescu

Robots Are After Your Job: Exploring Generative AI for C++ - Andrei Alexandrescu - CppCon 2023

Рет қаралды 32,100

4 ай бұрын

cppcon.org/
CppCon 2023 Early Access: cppcon.org/early-access
Access All 2023 Session Videos Ahead of Their Official Release To KZfaq. At least 30 days exclusive access through the Early Access system. Videos will be released to the CppCon channel on a schedule of one video per business day, with initial releases starting in November.
---
Robots Are After Your Job: Exploring Generative AI for C++ - Andrei Alexandrescu - CppCon 2023
github.com/CppCon/CppCon2023
Almost a year since the launch of ChatGPT - considered by many as the first truly compelling code generator that translates free-form human language into code - the C++ community continues to grapple with the implications. Reactions range from indifference or skepticism to genuine concern about the future of human programmers.
Although some advanced C++ techniques are already accessible to tools like ChatGPT, certain fundamental aspects remain outside the reach of current and possibly next-generation generative AI tools. This disparity raises pivotal questions: Which parts of the intricate C++ ecosystem can we confidently delegate to generative AI? What uniquely human skills must we retain and refine?
We'll probe the potential and limits of contemporary AI, taking a novel look at the age-old binary search algorithm. Although this algorithm has long been held up as a paragon of efficiency, we challenge that notion. What would ChatGPT have to say about it, and how might it partner with us to refine this cornerstone of algorithmic logic? The conversation opens a window into a future where developers become the "one percenters" of programming-focusing solely on the most cerebral and high-level challenges, while AI takes care of the everyday tasks. Join us to explore this fascinating paradigm shift and reflect on what it means for your own work in and with C++.
---
Andrei Alexandrescu
Andrei Alexandrescu is a Principal Research Scientist at NVIDIA. He wrote three best-selling books on programming (Modern C++ Design, C++ Coding Standards, and The D Programming Language) and numerous articles and papers on wide-ranging topics from programming to language design to Machine Learning to Natural Language Processing to fundamental algorithms. Andrei holds a PhD in Computer Science from the University of Washington and a BSc in Electrical Engineering from University "Politehnica" Bucharest. He is the Vice President of the D Language Foundation.
__
Videos Filmed & Edited by Bash Films: www.BashFilms.com
KZfaq Channel Managed by Digital Medium Ltd events.digital-medium.co.uk
---
Registration for CppCon: cppcon.org/registration/
#cppcon #ai #cpp #cppprogramming

Пікірлер: 42

@tomkirbygreen 8 ай бұрын

Oh you know this is going to be good :-) Andrei brings the wake-up call!

@christopherhayden8442 7 ай бұрын

I had the pleasure of picking Andrei's brain for many hours over several days at a conference in Boston several years ago. Fantastic engineer and fantastic person. His talks never disappoint. Thank you, Andrei! I was a little surprised to hear that using a larger left bias for the upper bound portion of the improved equal range algorithm didn't have a benefit. Maybe I need to take a closer look at the implementation and think about the problem a little longer.

@SvenAlmgren 4 ай бұрын

Andrei for President! Best speaker ever :)

@ferinzz 4 ай бұрын

This is awesome. This is why I enjoy watching these talks and seeing people continuous question the standards of their own library. showing how these llms can improve your day to day to make the menial tasks easier is a great message to share.

@ark.1424 4 ай бұрын

That is a great talk and awesome research!

@CoreDump07 4 ай бұрын

21:20 very well explained, chat gpt and its brothers it not gonna rob us of our jobs, it helps us get better and faster and do more interesting stuff.

@yoniyash2839 2 ай бұрын

Great stuff Andrei! I wonder if we'll see these improvement in the STD

@yogthemuskrat 8 ай бұрын

Ok, the REAL question is - did Andrei jam with that band?

@andralex 7 ай бұрын

Did! Will post the video shortly.

@andralex 7 ай бұрын

And here's me drumming a cover of Sonny Boy Williamson's "Keep Your Hands Out Of My Pocket"! kzfaq.info/get/bejne/eKeiaL1zmr3bhpc.html

@selvakumarjawahar 8 ай бұрын

sold!! I paid my tax now

@Codenoia 3 ай бұрын

It also would be very interesting a talk about using C++ for implementing ChatGPT-like AI... are they using Python for AI nowadays? Why not C++?

@kuhluhOG Ай бұрын

1:08:25 I think that good judgement derives from good intuition, which in turn derives from good skill, which in turn comes from lots of experience. Obviously, a person may not necessarily get stuff from right to level, but that's a different topic. So, no, I wouldn't say that AI levels the playing field in terms of skill.

@ManpreetSingh-og4fy 4 ай бұрын

I got this guy's book Modern C++ design a decade back and came to know how little C++ I knew

@mashton72 3 ай бұрын

It's on my bookshelf. One of the few programming books I read cover to cover. Genuinely creative, but compilers back then.....ugh....the compile errors were painful

@user-rq9rl1hs4j 3 ай бұрын

Me too😅😅😅

@Bolpat 4 ай бұрын

1:17:20 Creativity and Judgement also translate quite well between languages, but Skill not so much.

@joopie99aa 7 ай бұрын

For equal_range, expanding upon the idea that you're likely to have a small number of equal items (in relative terms), wouldn't it be faster to do an exponential search for the upper bound, instead of a center left binary search? With the center left upper bound binary search, you still start by considering the entire remaining range, but bias towards shrinking it quickly. With an exponential search you start by considering the minimal range and exponentially grow it up to the entire remaining range if necessary. So the runtime of the second part of the algorithm will depend only on the length of the equal range, not on the total length of the list. For large lists in the expected case where the equal range is small by comparison this should provide a significant speed up. Even better, unlike in traditional exponential search, in this case you can 'drag the lower bound (on the upper bound) with you' as you exponentially grow the upper bound. EDIT: ah, I see this was asked in the questions in the end.

@Bolpat 4 ай бұрын

1:25:00 I put the code on slide 36 in GodBolt and with GCC and Clang on O3, there are no mul instructions using int* and std::less. I don’t really understand the assembly, but it contains zero multiplication and zero division instructions.

@mashton72 3 ай бұрын

If AI does all my boiler plate coding, bring it on

@ivanp_personal 4 ай бұрын

When will we have those algorithms in the namespace std? Did Andrey submit them for standardization? All the best should be part of the standard.

@10e999 Ай бұрын

So where's the drum? :)

@muxecoid 15 күн бұрын

Having links to actual prompts used to generate code while iterating would be super helpful. Especially together with discussion of what were the bugs in generated code.

@eyedl 3 ай бұрын

hilarious XD

@Bolpat 4 ай бұрын

1:21:00 the -torae isn’t Latin. It looks like Latin to the uninformed, but it’s not proper. The vocative of nouns ending in _-ore_ is _-ore,_ i.e. the same.

@dmvjjvmd 25 күн бұрын

Well, 3rd declension noun vocatives are identical to the nominative, yes. I'm assuming he went with "programmator" on the analogy of "doctor" (programmatore is Italian), and since he is addressing programmers, it's plural, making the proper form "programmatores" (-es being the 3rd decl. ending nom./voc. pl.). All that said, his name looks Romanian, so perhaps he was riffing off of how Romanian morphology evolved out of Latin. I don't know anything about it.

@joseoncrack 3 ай бұрын

Robots are after nothing. That's the ruling 1% that are after your job.

@TheEternalVortex42 Ай бұрын

21:20 this formula doesn't seem correct, you are summing a bunch of integers but then you get a rational number as a value? Even trying n = 2 you get 23/10 which doesn't seem to match what we should get. I think the correct formula is 3 n lg n - 2 n + 2. BTW this shouldn't really take very long even by hand since you just need to know how to sum a geometric series?

@vasiliypupkin6311 7 ай бұрын

Было бы круто видеть такие видео для ру сегмента😢

@AntonTimofeev1988 4 ай бұрын

в каком смысле ру сегмента? с переводом?

@ark.1424 4 ай бұрын

no way, you need to learn international language which is English to watch a great things like that, but😊

@ark.1424 4 ай бұрын

No, thanks! the translated version would say stalin created C++ 😂

@vincentlextrait3092 4 ай бұрын

On average a developer writes 4 lines of code per day. Inserting these faster is not really a thing...

@thesquee1838 4 ай бұрын

Is this a real statistic?

@PikeBot 4 ай бұрын

Exactly. Because you can't trust GPT-generated code, you have to check it. You've transformed a code writing task (the easiest part of your job, unless you're doing something truly unusual, in which case GPT won't have any models to work off of) into a code reading task (much harder, and what most of your work already is).

@Lisekplhehe 4 ай бұрын

Writes or contributes?

@rutabega306 4 ай бұрын

Really?

@MantasXVIII Ай бұрын

@@PikeBotit takes me 1 second to check what Claude Opus gives me, but it would take me 30+ seconds to write. If you use it like an assistant, not like a replacement of yourself, it is an amazing tool.

@tcioaca 4 ай бұрын

Unpopular opinion: not a great talk, sorry (not great doesn't mean it was terrible, though!). Why? It was not balanced (pun not really intended). Instead of choosing such an example and actually insisting so much on that specific problem, for quite a long time threw me off. If the problem requires so much attention to be understood, just to build the motivation of your speech, I am sorry, but this is not a balanced speech, not by the common rules of how most speeches are typically structured. Now, I would have been curious how ChatGPT would have structured the speech, once Andrei had the idea for what the motivation is. Like a meta-production in a certain sense.

@GreenJalapenjo 3 ай бұрын

I'm just over half-way in, but so far I have pretty much the opposite impression: it's an interesting talk about algorithms with some kinda unnecessary stuff about ChatGPT thrown in.

@PROMuffy 3 ай бұрын

I saw this as a handpicked concrete example demonstrating which aspects of programming AI is currently geared toward and which aspects it has yet to fulfil. The bullet points at the end of the talk summarise these. The talk was as much about how the problem was solved as the solution. Understanding what tools an expert uses and how they use them can give valuable insights into how they work, and then you can consider how that differs from the way you work.

@tcioaca 2 ай бұрын

Still, I personally do not think that this is a balanced speech. Maybe he chose the wrong kind of problem. But the structure itself could have been optimized. In the end, is it a speech about the intricacies of a specific algorithm or about what ChatGPT can do for the more common mortal developer!? Why not give examples of more mundane, but not trivial tasks and show when an LLM can help and when it cannot. Sorry, but if for half an hour you expose a complex problem to have to introduce some techniques where ChatGPT can be helpful.. you lost me. Call me stupid, if you will, I stand by my feedback this time.