GitHub Copilot CRUSHES Leetcode Interview Questions! 😳
Channel:DevOps Directive · Length:9:20 · Published:2021-07-04 · Views:266472
Summary
A DevOps YouTuber tests GitHub Copilot on a range of Leetcode problems and finds it solves most immediately, with a few needing tweaks and some far off. He concludes it would outperform him in a FAANG-style interview.
Why HN recommends it
Cited as evidence that AI can solve interview-style algorithm puzzles, in threads questioning the value of Leetcode.
Software practice, open source & careers · LLMs & generative AI
Subtitles (excerpt)
github copilot the ai code completion tool from github that may or may not be here to take our jobs hey team sid here with devops directive where it's my job to help you level up your devops and cloud infrastructure skills if that sounds interesting to you subscribe so you don't miss out on future content last week on june 29th github announced a new product called copilot which they describe as an ai pair programmer that helps you write better code i've heard a few people express concern with varying degrees of seriousness that this technology will displace human developers however in order to take our jobs co-pilot would first need to pass the dreaded technical interview process today i'm going to put co-pilot up against a variety of interview questions from leak code and see how it fares at the end we'll evaluate how it did and decide whether or not we need to start upskilling into a different career path without further ado let's get into it i've got vs code up here on the left with copilot installed and then i also have the elite code problems on the right let me just sort by difficulty or filter on difficulty so we can get an easy problem to start and let's get one that i haven't done yet and let's try square
On Hacker News
> But if there wasn't any art to these problems, then after 400+ problems wouldn't you have figured out the robotic algorithm to solve them? [VIDEO] — usrbinbash, 2022-01
It's a question of whether copilot can be "creative". I'm mit sure, but it did manage to solve some of the harder leetcode questions here [VIDEO] and I'm curious how it will fare on the later advent of code problems. — thomasahle, 2021-12
i actually like it that copilot is better than me at solving interview questions. [VIDEO] I for one welcome our robot overlords. i wonder if they could retrain the model on BSD or MIT licensed code only; How much of the open source code is licensed as GPL vs more permissive licenses, does anyone know? Interesting that they want to charge for the use of co-pilot, I guess that we will see this busi… — MichaelMoser123, 2021-07
Related videos
- 🚀 TDD, Where Did It All Go Wrong (Ian Cooper) · DevTernity Conference · 1:03:55
- Bret Victor The Future of Programming · Joey Reid · 32:55
- Transformers, the tech behind LLMs | Deep Learning Chapter 5 · 3Blue1Brown · 27:14
- "Uncle" Bob Martin - "The Future of Programming" · Paul Stringer's Mobile Tech · 1:18:21
- Deep Dive into LLMs like ChatGPT · Andrej Karpathy · 3:31:23
- Tim Ewald - Clojure: Programming with Hand Tools · ClojureTV · 58:39
- Using Python to Code by Voice · Next Day Video · 28:17
- Transforming Code into Beautiful, Idiomatic Python · Next Day Video · 48:51
- Agile is Dead • Pragmatic Dave Thomas • GOTO 2015 · GOTO Conferences · 40:39
- Let's build GPT: from scratch, in code, spelled out. · Andrej Karpathy · 1:56:20
- A Hackers' Guide to Language Models · Jeremy Howard · 1:31:13
- Plover: Thought to Text at 240 WPM · Next Day Video · 34:21
- "The Economics of Programming Languages" by Evan Czaplicki (Strange Loop 2023) · Strange Loop Conference · 43:57
- "The Mess We're In" by Joe Armstrong · Strange Loop Conference · 45:50
- Principles of Technology Leadership | Bryan Cantrill | Monktoberfest 2017 · RedMonk Tech Events · 51:22
- A Talk Near the Future of Python (a.k.a., Dave live-codes a WebAssembly Interpreter) · David Beazley · 1:01:45