Dota 2, every mention

7 scenes (2017) · ← back to Dota 2

tap a year for its mentions
00811522017201820192020202120222023202420252026episodesmentions
0122017201820192020202120222023202420252026episodes it came up in
007.511522017201820192020202120222023202420252026episodesmentions per episode

every year 2017 anyone Greg Brockman 8Diana Hu 6Bob McGrew 4Szymon Sidor 3François Chollet 3Miles Brundage 2Max Junestrand 2Craig Cannon 2

Verbatim, from the transcripts: the passages where Dota 2 comes up

loading…

Building Dota Bots That Beat Pros - OpenAI's Greg Brockman, Szymon Sidor, and Sam Altman · Y Combinator Nov 8, 2017 · 12 mentions

  • ▶ 4:55 Szymon Sidor Um, I can tell you a bit about, uh, our project, which is, um, essentially developing large scale reinforcement learning for, uh, DOTA two, uh, and their majority of the work is actually engineering 2 times in the scene
  • ▶ 8:38 Greg Brockman And so looking down the list, Dota actually, uh, was the first one 4 times in the scene
  • ▶ 13:30 Greg Brockman And in the end, we had something that looked just like a typical OpenAI gym environment, and so all you have to do is you say, gym.make this, you know, Dota environment ID, and suddenly you're playing Dota, and that your Python code just… 2 times in the scene
  • ▶ 24:11 Greg Brockman We're, we're not very good at Dota.
  • ▶ 27:30 Craig Cannon In Dota?
  • ▶ 50:58 Szymon Sidor So, so, so specific list of things, ah, that, that we found very useful, at least in, in the Dota team, ah, is, ah, some knowledge of, ah, distributed systems, because, ah, we build a lot of those, and those are,
  • ▶ 59:00 Greg Brockman Sort of starter and a very good place to like, I think one thing that I really like about this Dota project and bringing it to all these pros is that we're all going to be interacting with super advanced AI systems in the future.
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.