meta_pixel
Tapesearch Logo
Log in
Programming Throwdown

Squashing bugs using AI and Machine Learning

Programming Throwdown

Patrick Wheeler and Jason Gauci

Objective C, Java, Programming Throwdown, Education, News, Programming Languages, How To, Tech News, C, Python

4.6604 Ratings

🗓️ 18 February 2020

⏱️ 63 minutes

🧾️ Download transcript

Summary

The best part of hosting Programming Throwdown is reading emails from people who listened to this show before they had any coding experience and went on to land jobs in tech. Thanks so much for inspiring us with your stories. My second favorite part of hosting the show is hearing about so many awesome programming tools and resources, often when they are just starting out. DeepCode is one of these amazing resources. DeepCode is a static analysis tool that looks at your code and, using AI trained on all code in github (!!!), finds common mistakes and offers suggestions on how to resolve. I am a heavy user of static analysis tools, and yet DeepCode was still able to find real issues in one of my python projects above and beyond pylint and mypy. Best of all, it's completely free to use for open source projects! Give it a shot and let us know what you think! Show notes: https://www.programmingthrowdown.com/2020/02/episode-99-squashing-bugs-using-ai-and.html

Transcript

Click on a timestamp to play from that location

0:00.0

Programming Throwdown, Episode 99, squashing bugs using AI and machine learning with Boris Paskolov. Take it away, Jason.

0:23.9

Hey, everybody. This is a really, really fascinating topic. I think there's been a lot of interest

0:30.4

around using AI to sort of help developers. We've all had apps, even like super popular apps, like the Uber and the Google app and other apps where they have bugs and they crash and things like that.

0:44.9

So even the people who are the best at this have tons of issues.

0:49.9

And so it's becoming a really interesting area.

0:52.4

And we're so fortunate we have Boris Puskalov of the CEO and co-founder of DeepCode to kind

0:58.4

of sit down and roundtable how we can make software better.

1:02.7

So Boris, why don't you kind of start off by telling us like a little bit about your background.

1:09.0

What was the idea or the inception of DeepCode and kind of

1:13.1

highlight that I was doing right now?

1:15.5

Sounds good. So welcome everyone. Thank you for having me.

1:20.8

So my name is Boris Pascliffe. I was originally born in Bulgaria and I did did my bachelor's at Mastering Computer Science in Boston,

1:30.3

and then worked with a number of different companies as a developer.

1:35.3

Later on in my life, I did an executive MBA, so I started moving into project management, program management,

1:41.3

and many different things in that space.

1:43.3

And yeah, and I'm still working in technology, but I'm coding less and less, as you can imagine.

1:49.0

So about DeepCote, obviously, the idea is that it started in 2016, and it's a spin-off from

1:56.0

ETH Zurich, which is the number one tech university in Europe.

2:00.0

I usually call it the MIT of Europe

2:02.1

when I make fun with the guys. Nice. But yeah, the idea is that my other co-founder's professor

2:10.0

Dr. Martin Vetchef and Dr. Vessel and Ritesh, so they spent about 12 years together researching

2:17.3

the topic of learning from big code, so they spent about 12 years together researching the topic of learning

...

Please login to see the full transcript.

Disclaimer: The podcast and artwork embedded on this page are from Patrick Wheeler and Jason Gauci, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of Patrick Wheeler and Jason Gauci and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.

Copyright © Tapesearch 2025.