Amp, every mention
34 scenes · ← back to Amp
tap a year for its mentions
every year anyone Quinn Slack 40Alessio Fanelli 23Thorsten Ball 14Shawn Wang 9Anjney Midha 5Steve Yegge 1Dax Reed 1
Verbatim, from the transcripts: the passages where Amp comes up
Orbs: Shifting Coding to Cloud — Quinn Slack, Amp Code
- ▶ 0:13 Quinn Slack We got the whole AMP team together in Munich and it's been awesome.
- ▶ 1:02 Shawn Wang Okay, so AMP, people have been introduced on this pod and everything, and people mostly have just seen you online. 6 times in the scene
- ▶ 6:39 Quinn Slack And on the AMP team, we are 20 people. 2 times in the scene
- ▶ 9:18 Quinn Slack So let's pull this one up and what it's doing here under the hood is actually, you know, probably number one complaint that people have about AMP is you gotta wait for the sandbox to, uh, spin up. 3 times in the scene
- ▶ 15:02 Quinn Slack I, okay, so here I'm in AMP and this, you can see phase one B two. 3 times in the scene
- ▶ 20:49 Quinn Slack What we've been finding is just, you know, using more ad hoc repositories that are hosted by AMP. 5 times in the scene
- ▶ 26:51 Quinn Slack We have now the AMP subscriptions, like AMP megawatt and gigawatt, and they give like super generous, uh, quotas for orbs. 6 times in the scene
- ▶ 31:57 Quinn Slack We do everything in AMP, which started out as a coding agent, but like you can't keep an agent in a box that has another label. 2 times in the scene
Why AI Labs With Unlimited GPUs Still Fail — Anjney Midha, AMP
- ▶ 1:16 Shawn Wang We're in Periodic Labs with Anjumita, CEO, uh, founder of Anthrox. 2 times in the scene
- ▶ 8:04 Anjney Midha And so we see the, the AMP grid 3 times in the scene
- ▶ 24:29 Anjney Midha So, so there's sort of two sides of the, of the same scaling bottleneck curve, but those two, you know, we formed AMP as a public benefit corporation.
- ▶ 38:14 Anjney Midha You know, one of the things we do with the AMP grid is we donate excess compute.
- ▶ 1:00:02 Shawn Wang Yeah, I mean, uh, you're, you're so inspirational, and, uh, yeah, there's more I want to dig into about how you've, like, set everything up, every single one of your investments, how AMP is going, but we're running out of time for that,…
Steve Yegge's Vibe Coding Manifesto: Why Claude Code Isn't It & What Comes After the IDE
- ▶ 0:04 unnamed speaker We are here live at AI Engineer Summit with Steve Yeggi, the legendary Steve Yeggi of Stevie's Tech Talks, Stevie's Platforms, Brands, and most recently, Sourcegraph and AMP.
- ▶ 23:28 Steve Yegge It's the, it's the whole, it's this idea that quad code and AMP and Codex,
Anthropic, Glean & OpenRouter: How AI Moats Are Built with Deedy Das of Menlo Ventures
- ▶ 1:01:51 Alessio Fanelli I'm sure that's AMP code free plan.
⚡ Inside Google Labs: Building The Gemini Coding Agent — Jed Borovik, Jules + AIE CODE Preview
- ▶ 26:25 unnamed speaker Yeah, I see the AMP folks,
Amp: The Emperor Has No Clothes
- ▶ 0:25 Alessio Fanelli And today, I guess, Kodi is a brand, uh, that has passed, and now you have AMP. 4 times in the scene
- ▶ 3:38 Quinn Slack First, it started with Copilot, and then, Cody, we were really good at Chatrag, and then Cursor and Windsurf showed that kind of IDE forks and partially agentic things could get better and better, and then, you know, the next generation,… 4 times in the scene
- ▶ 5:24 Alessio Fanelli Are there any numbers that you share about developers, like, you know, AMP usage overall? 4 times in the scene
- ▶ 8:36 Quinn Slack So there's a lot of things on AMP that we do, like no consistent pricing, no user model choice, no checking off all the boxes that security and compliance and legal want that, you know, takes nine months. 4 times in the scene
- ▶ 13:05 Alessio Fanelli So you have both a plugin for IDs, so I use some code and cursor, but I can also go into CLI and use some code. 4 times in the scene
- ▶ 18:19 Quinn Slack And we, about three weeks ago, we said, we think probably it's painful, but we will kill the VS code extension for AMP. 4 times in the scene
- ▶ 24:55 Thorsten Ball So I can give you the choice to use Gemini 2.5 in, in AMP, but without the system prompting you into it without, you know, what I call before, like going with the grain of the model, the models are trained in different ways. 3 times in the scene
- ▶ 30:23 Thorsten Ball Like we, when you use AMP, you're using a model from Anthropic, you're using a model from OpenAI and you're using a model from Google. 4 times in the scene
- ▶ 36:23 Thorsten Ball And, you know, just as an example, I think over the last three months, I would say we're, we're ahead of the curve, like using AMP internally, like we're ahead of like the mainstream agentic adoption, but like say a month or two,
- ▶ 37:20 Alessio Fanelli What are like the failure modes that you heard from customers where it's like, hey, we tried AMP and it just didn't work at doing X, Y, Z. 6 times in the scene
- ▶ 46:18 Thorsten Ball And what we encourage users to do, for example, in AMP is to start a lot of small threads and be really, you know, do context engineering and be really strict about what goes into context and what doesn't. 3 times in the scene
- ▶ 58:34 Quinn Slack Are building AMP for the people that do want to move. 3 times in the scene
- ▶ 1:06:34 Thorsten Ball For me, for example, we don't do any formal code reviews on the AMP team, but it doesn't mean that code isn't reviewed because we use, you know, AMP to write 80 to 90% of our code base. 3 times in the scene
- ▶ 1:10:46 Quinn Slack And we've had non coders, including one of our board members who built something with AMP that replaced, uh, like 250 K a year piece of software that he used for a lot of their internal, uh, fund tracking. 2 times in the scene
- ▶ 1:14:30 Alessio Fanelli It's like, obviously you're doing this with AMP in a way, right? 4 times in the scene
- ▶ 1:21:29 Quinn Slack Yeah, use AMP.