How we built Grok Bot in a month | Roman Ugarte (SpaceXAI)

Roman Ugarte · 1h 22m · youtube.com ↗

18 korrents from this recording

Roman Ugarte did not write this page.

Every claim below is a statement made in this recording, quoted word for word and linked to the second it was said, so you can hear it rather than take our word for it. The wording comes from the transcript published alongside the recording; the sentence above each quote is our reading of the claim, not their wording.

0:10:27 · watch on youtube.com↗

Our reading
An AI product that adds a tab for each new form factor is shipping its org chart, and users seem to be reacting negatively to it.

Their wordsinstead it's three different visions that all kind of share a screen and you can hop between but it is kind of a shipping your org chart style thing that I think users are reacting negatively to.
5 min later
0:14:58 · watch on youtube.com↗

Our reading
As models get smarter, users should no more need second-by-second updates from an AI agent than from a teammate.

Their wordsAnd the reason for that is we think as these models get smarter, the same way that your teammate, you know, you wouldn't ask for second by- second updates of exactly all the buttons they're pressing and websites they're going to, I think it's too much to ask your bots to do that, too.
6 min later
0:20:38 · watch on youtube.com↗

Our reading
Much of what people want from AI is not menus and features but something they can hand a meaningful task to and have it done.

Their wordsa lot of what people want from AI is not this thing with lots of drop- down menus and bells and whistles, but just a thing that you describe a task, a task that's meaningful to you and it goes and it does it
8 min later
0:28:35 · watch on youtube.com↗

Our reading
Adding things to a product is not the goal and is not what makes it more useful to more people.

Their wordsLike adding things to the product is not the goal. That's not the thing that's going to push this this product forward and make it more useful to more people.
2 min later
0:30:38 · watch on youtube.com↗

Our reading
Users should never have to think about whether an AI agent's work runs locally or in the cloud.

Their wordsAnd the first is you should never have to think about local and cloud and where are these workflows running?
1 min later
0:32:04 · watch on youtube.com↗

Our reading
AI agents need their own computers, because people do not do their jobs through APIs but by clicking and typing on a computer.

Their wordsWe as humans don't do our jobs via MCPS and APIs. Like we use a computer and we click on pixels and we kind of type things in input boxes. And it's very important that your bot has those baseline capabilities as well.
3 min later
0:34:59 · watch on youtube.com↗

Our reading
Companies with sunk cost in an existing paradigm find it very painful to build the new thing from scratch.

Their wordsI think it's just been hard to act on if you're stuck in the existing paradigm and if you have a lot of kind of sunk cost in that existing paradigm, it's very painful to create a new thing from scratch.
5 min later
0:39:35 · watch on youtube.com↗

Our reading
People should have a team of AI bots that help them with their job and their life, and it should really feel like a team.

Their wordsyou should have a team of AI bots that help you with your job and help you with your life. And it should really feel like a team.
2 min later
0:41:23 · watch on youtube.com↗

Our reading
When an AI product decision is unclear, the answer usually comes from asking what you would want from a human teammate.

Their wordsyou just need to ask the question of what would you want from a human teammate and can we push AI to behave in a similar way
2 min later
0:43:42 · watch on youtube.com↗

Our reading
The power tools of the future will probably be mostly intent and steering from the human, with AI abstracting away all the knobs.

Their wordsI think power tools of the future will actually be very different from that. Uh where it is mostly just intent being expressed and good steering on the part of the human and these AI tools abstract away all of the knobs.
2 min later
0:45:20 · watch on youtube.com↗

Our reading
One product will probably be the best form factor for both work and personal AI assistants.

Their wordsAnd so my instinct is that I think one product will be the best form factor for both of those things.
8 min later
0:53:27 · watch on youtube.com↗

Our reading
The next shift in AI will probably be agents that are more proactive toward you than you are toward them.

Their wordswhere the agent or the bot should actually be more proactive to you than you reaching out to it. And I think that will be the next shift in AI.
3 min later
0:56:29 · watch on youtube.com↗

Our reading
AI for knowledge work will probably follow coding's adoption pattern, with many people first feeling the aha moment in a personal capacity.

Their wordsAnd I think for knowledge work, we're going to see a similar pattern of people really feeling the aha moment sometimes in a personal capacity.
6 min later
1:02:56 · watch on youtube.com↗

Our reading
An AI you have to supervise at 90 percent is not 90 percent task completion: you are still doing the thing.

Their wordsYou're not that's not 90% task completion. You're still doing the thing and it feels that way and it's it's weighing on you in the same way
3 min later
1:05:41 · watch on youtube.com↗

Our reading
What defines a startup is not headcount or funding round but a chaotic, disorganized scramble energy.

Their wordsif you define a startup by number of people or by like the funding round like none of those things really make any sense. The core thing that defines a startup is exactly what you're describing, which is this kind of scramble energy of things are kind of chaotic and kind of disorganized.
3 min later
1:08:48 · watch on youtube.com↗

Our reading
An AI product company that cannot completely reinvent itself every six months is going to lose.

Their wordsAnd if we as a company can't completely reinvent ourselves every six months, which recently it's felt even shorter than that of kind of complete like very significant reinventions of our priorities, the core product, what users feel, uh we're going to lose.
2 min later
1:10:34 · watch on youtube.com↗

Our reading
Product scaffolding built because models are not yet smart enough should be deleted as they improve, even when that upsets some users.

Their wordsthese scaffolding product overhang style things that get built in because the models have not yet gotten smart enough to just do it themselves. Those things will get moved away over time and we need to feel comfortable making kind of hard decisions that might upset a small set of users
4 min later
1:14:20 · watch on youtube.com↗

Our reading
Founders starting out today should be more grounded in making possible something that is not possible now.

Their wordsAnd so I would really encourage many founders or people starting out today to be more grounded in that perspective of how can I make something that is not possible now possible.