StarCoder, every mention
13 scenes across 3 shows · ← back to StarCoder
tap a year for its mentions
Latent Space 19
the MAD Podcast 8
No Priors 1
every year every show Latent Space 19 the MAD Podcast 8 No Priors 1
Verbatim, from the transcripts: passages where StarCoder comes up on Latent Space, the MAD Podcast, No Priors
Amp: The Emperor Has No Clothes
- ▶ 27:15 Alessio Fanelli And I know Cody was using StarCoder for inline edits, at least that's what Bianca said publicly, so I'm not leaking anything.
⚡️ Beyond Transformers with Power Retention
- ▶ 15:35 Diego Bachman And this is basically showing this blue line here is a model called, uh, star coder 6 times in the scene
- ▶ 19:47 unnamed speaker Uh, these are both at 32 K context, and the only difference between these two is this is the star coder to baseline at 32 K, and this is the power coder.
- ▶ 23:32 Diego Bachman Maybe someone wants to do quen coder instead of star coder, or someone just wants to do a text model or a question answering model or an instruct tune model instead of a code model.
- ▶ 28:54 unnamed speaker This is the three billion parameter star coder
Better Data is All You Need — Ari Morcos, Datology
- ▶ 23:49 Ari Morcos I haven't done it, but the StarCoder paper has done it, and there have been a couple other papers that have all shown that.
AI at Roblox: Revolutionizing Game Creation | Morgan McGuire, Chief Scientist of Roblox
- ▶ 24:53 Morgan McGuire Or we've published, um, and we can get into this a little more later, um, uh, Starcoder, for example, with some of our research on this, how do you make software that programs?
- ▶ 33:15 Morgan McGuire Contributions in that space have been Starcoder and Starcoder II, which are large language models, and that there's a large collaboration with a lot of participants.
- ▶ 38:36 Matt Turck And StarCoder, you mentioned it, um, a couple of times. 6 times in the scene
The Four Wars of the AI Stack - Dec 2023 Recap
- ▶ 5:40 unnamed speaker You know, uh, there's StarCoder, there is CodeLlama, but like, it's not really, for how important code is, it doesn't seem like as big of a battlefront as just general function calling, reasoning, um, you know, these, these other kinds of…
No Priors Ep. 47 | With Sourcegraph CTO Beyang Liu
- ▶ 34:01 Beyang Liu The primary model that Cody uses for inline completions right now is, uh, StarCoder, uh, seven billion.
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
- ▶ 14:05 Alessio Fanelli Um, how do you think about, um, open source models, um, and kind of, like, private, because Copilot has their own private thing, and I think you guys use StarCoder, uh, if I remember right? 3 times in the scene
- ▶ 1:08:20 Beyang Liu Like, we run StarCoder, uh, on, on top of Fireworks, and that's made it so that we don't, just don't have to think about, uh, building up an inference stack, and so that's great for us, because it allows us to focus more on, uh, the, the… 4 times in the scene