Design at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.
Read the talk
Design at the Speed of Adjectives
Paul Bakaus explains how Impeccable turns design vocabulary into contextual instructions for coding agents, while keeping people responsible for direction, iteration, and taste.
From a talk by Paul Bakaus
At a glance
Ideas worth remembering
A useful steering command connects an intention to specific operations and constraints. Bolder means hierarchy, scale, and decisive typography that respects the design system; harden addresses conditions such as device performance and responsiveness.
Context and iteration remain essential to Bakaus’s approach. Audience, emotional direction, references, and boundaries inform the choices that a plausible generated page may otherwise lack.
The appropriate level of control changes throughout the workflow. Contextual commands can help with crafting and iteration, while Bakaus still sees a need for human work in the final 5, 10, or perhaps 20 percent that moves a result from good to great.
Impeccable’s refusal of automatic mode follows its core design decision: help people steer agents and amplify their craft, while keeping direction and taste in human hands.
A small prompt, two different interpretations
Paul Bakaus opens with Impeccable, a design skill that works through an existing coding harness. Its purpose is to improve the agent’s design work and, potentially, help the person directing it become a better designer. The presentation concerns the approach behind the tool: how to give people useful control over generated design.
The demonstration starts from an intentionally basic website. Bakaus describes it as acceptable but bland, with at least some color. He asks the agent to make its workflow section bolder with Impeccable installed. He considers the result bolder, but immediately identifies a weakness: section numbers that he regards as a recurring generated-design tell. The skill can guide a transformation without eliminating every unwanted convention.
To address the possibility that the model alone would produce the same improvement, he presents a comparison using the same project and the same prompt without Impeccable. He invites the audience to judge the difference. This is an illustrative comparison, rather than a quantified evaluation: his account establishes what he changed between the examples, but the spoken description does not establish their comparative visual quality independently. It introduces the central question of the talk—what an adjective, or a verb, actually tells an agent to do.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Finding control between pixels and delegation
Bakaus places the tool in a changing relationship between design and engineering. He sees designers moving into code and engineers moving into design, with more people becoming design engineers. Users tell him that Impeccable supplies a shared design language. In his view, the conventional sequence of product definition, design, critique, handoff, and engineering implementation is beginning to collapse in both small and large companies.
He describes two extremes in the actual work. Direct manipulation means changing margins, padding, and other properties in tools such as Figma, where the person operates on the design or final output. At the other extreme, a person simply asks an agent to design or build something. The first offers detailed control; the second delegates broad execution. Bakaus’s interest lies between them: choosing the level of control and the moment at which a person should enter the loop.
This makes tool choice a question of matching the operation to the job. Bakaus argues that, for most work, adjusting padding, margins, and spacing is too low a level of abstraction. A person may know the desired change in emphasis without needing to specify every spacing value. The opportunity is to express that intention at a higher level while retaining enough control to direct the result.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Generated design changes its defaults
Broad delegation has its own problem: recurring visual defaults. Bakaus contrasts older generated pages associated with purple gradients against what he now calls Claude beige, characterized by beige palettes, Instrument Serif, and italics. His observation is that the familiar tells keep moving. Recognizing one set of patterns does not mean the underlying tendency toward sameness has disappeared.
He does not consider that newer style inherently bad. The criticism is that many outputs adopt the same appearance. A design can be visually competent yet fail to distinguish the particular product it represents. Here, the concern is uniformity across generated work, rather than the quality of any individual font or palette.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Design needs decisions before execution
Bakaus’s first explicit position is that design cannot be completed in one shot. He presents this as his judgment about present capabilities, with uncertainty about whether it might ever become possible. Effective design needs context about the purpose, audience, and thing being built. It also needs iteration. Team members and users bring different opinions, and even someone working alone must develop the result through a process.
A missing design vocabulary makes that process frustrating, particularly when stakeholders cannot express what they want. Bakaus proposes questions that establish direction before asking for execution: what emotional territory should the design occupy, what should it never feel like, what references matter, and who is the audience? These questions supply both positive direction and boundaries. His analogy is a human design studio: even an excellent design director would need to understand the brief before going away to make the work.
Returning to a quickly generated page, he identifies the missing ingredient as deliberate decisions. In his assessment, the page may be competent, but it is empty because nobody chose what it should communicate. The limitation is substantive: producing a plausible arrangement of elements does not itself establish a purpose or a point of view.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Compressing design language into commands
Impeccable’s proposed control surface consists of adjectives and verbs: make something bolder or quieter, distill it, polish it, make it denser, or harden it. Bakaus defines distilling as simplification. Hardening concerns whether the design works across conditions, including poor performance on certain devices and missing responsiveness. The vocabulary therefore covers both visual direction and the practical behavior of the interface.
The motivation comes from his observation of designers and engineers attempting the same task with the same model and harness. He reports a stark difference in their outputs based on the language they use. Impeccable tries to compress that design language into a skill so that people can express intentions more effectively. The important capability is contextual interpretation: a steering word should resolve to what that change means for the project, rather than merely invoking the model’s general associations.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
What bolder should change
Bolder illustrates why the word alone is insufficient. Without a project-specific meaning, the agent can follow its own references, inventing colors or gradients. Impeccable instead directs boldness toward hierarchy, scale, and decisive typography. Those changes are intended to raise the user’s attention while respecting the existing design system. The command describes an effect to achieve and constrains the kinds of changes used to achieve it.
Bakaus describes a file loaded when the bolder instruction is invoked. It includes a challenge to imagine showing someone the result and telling them that AI made it bolder; if that attribution seems believable, the work has failed the challenge. He says the agent is instructed to apply this test to itself and sometimes reflects that its work was poor. This supplies a self-critique heuristic aimed at avoiding obvious generated styling, though it does not establish that the agent can reliably judge how another person will perceive the result.
The broader mechanism is to imbue a familiar word with a more specific meaning. The model already associates that word with many things; the skill translates it into the domain the person cares about. Bakaus also limits the claim. This level of control cannot solve every design problem, and the appropriate level changes during the work. He leaves room for exploratory work at the beginning and human finishing work at the end. In his judgment, AI still cannot replace people for the last 5, 10, or perhaps even 20 percent needed to move a design from good to great, although it can improve the work.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Placing commands along a messy workflow
After more than 20 years building tools, Bakaus says he begins by mapping the target user’s workflow. Design is nonlinear, involves different people, and passes through several kinds of work. He looks for points where a tool can help: initialization and shaping, crafting, iteration through adjectives and verbs, hardening and polishing, and finally bringing the result back into the design system while cleaning up technical and design debt. These are intervention points along a process, rather than a claim that every project follows a fixed sequence.
Overdrive shows a more playful intervention. Bakaus was unsure whether to ship this command, which tries to create something deliberately over the top and began partly as a joke. He reports that people loved it. His example is an event horizon shader that he had already built, then pushed further with overdrive. He explicitly says the example was not made in one shot. The command intensified existing work; it did not account for the whole process of creating it.
His decision process includes testing uncertain commands with the community and observing whether people find value or joy in them. But the underlying requirement remains explicit meaning. An adjective with nothing behind it is only a nicer prompt. Because the model has encountered many meanings for the same word, the instruction must explain which meaning applies to this work.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Why steering remains the person’s job
Bakaus closes with a firm product decision: Impeccable will have no automatic mode. He reports frequent requests for the tool to do all the work without the user choosing commands, and says he intends to close a pending pull request for that reason. Choosing the command is central to the tool’s purpose. It gives the person a way to steer toward a desired result; removing that choice would move it toward the one-shot design tool he does not intend to build.
His rationale rests on a distinction between amplifying taste and manufacturing it. He calls the former amplified craft: tools can sharpen a person’s taste and help express more of it. In his view, taste arises from context, culture, and accumulated experience. When everyone replicates the same thing, its distinctiveness becomes muddy. He acknowledges that this is a contested opinion and says his tools are not an attempt to solve taste itself.
He ends by identifying the aim as finding the right level of control for design, then thanks the audience and invites questions. The closing position preserves a role for both parties: the tool helps express and execute direction, while the person continues to choose where the design should go.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Read the complete timestamped transcript
- 0:01
[music]
- 0:12
Cool. Uh, let's get this going. Welcome
- 0:15
everyone. Thanks for coming. Um, my name
- 0:18
is Paul and, uh, I'm going to try to
- 0:21
save you from the midday slump. So,
- 0:24
let's, uh, let's see if we can do that.
- 0:26
Um, okay. So this talk, this cold open
- 0:29
of this talk will make a lot more sense
- 0:31
if you know uh what impeccable is. Uh
- 0:34
but if you don't know what it is, it's a
- 0:35
design, it's a design skill that turns
- 0:37
your coding harness into a better
- 0:39
designer and hopefully you into a better
- 0:40
designer. Um and you can try it out. It
- 0:43
works across all harnesses, cloth code,
- 0:45
github, copilot, cursor, codex, etc. Um,
- 0:50
and this talk is really about uh my
- 0:53
approach to how to building this tool as
- 0:56
opposed to the tool itself. Um, but
- 0:58
let's get started with a pretty typical
- 1:00
website. So, this is a intentionally
- 1:04
very basic website and I want to give
- 1:06
you that one as context to what I'm
- 1:08
going to show you next. So, you know,
- 1:10
it's it's a it's it's an okay website.
- 1:12
It's not great. It's pretty bland. Um
- 1:15
but it at least it has some color some
- 1:17
something. Um so now here is um the
- 1:22
command make it bolder make the workflow
- 1:25
section bolder with impeccable.
- 1:28
Um so this is with impeccable installed.
- 1:31
So now there are it's not perfect. There
- 1:35
are some problems with this. for
- 1:36
example, the um the section numbers that
- 1:39
you have there, that's a very typical AI
- 1:41
slop tail uh that uh that GPT loves to
- 1:44
do and I mean Claude actually loves to
- 1:46
do as well and
- 1:48
it sometimes creeps in. So I wouldn't
- 1:50
say this is perfect by any means but I
- 1:52
think it's I would say bolder than
- 1:54
before. Um
- 1:56
now a lot of people install impeccable
- 1:59
try it out uh and then they ask me well
- 2:02
I don't know like maybe it could be
- 2:03
placebo maybe the model is good enough
- 2:04
in itself right uh not sure if it
- 2:06
actually works well let's compare it to
- 2:10
this is exactly the same project GPD55
- 2:12
on extra high um same exact prompt
- 2:16
without impeccable
- 2:20
so there is a slight difference I would
- 2:22
say but you be the judge of
- 2:25
Um, so the before and after is pretty
- 2:28
different and I'm going to talk about
- 2:31
why that is and um and and what the
- 2:34
approach is.
- 2:36
So designing at the speed of adjectives
- 2:39
and um to get the elephant out of the
- 2:41
room, they are not just adjectives,
- 2:43
they're also verbs. Uh but some of them
- 2:46
are adjectives.
- 2:50
First off, the role of the engineer and
- 2:52
the design are blurring. Um, I've seen
- 2:54
more people become design engineers than
- 2:57
ever. Designers are moving into code,
- 2:59
engineers are moving into design and
- 3:01
vice versa. Some of the best comments I
- 3:03
get from people who walk up to me and
- 3:05
say like, well, impeccable gives me this
- 3:07
shared language of design that everybody
- 3:09
can communicate now in. But really,
- 3:12
these worlds are all colliding in my
- 3:14
opinion and the typical handoff is kind
- 3:17
of broken. like the the waterfall
- 3:19
process of I start with design, maybe I
- 3:22
start with like the what on the PM side,
- 3:24
then it goes into design and then
- 3:25
there's like this handoff and this
- 3:27
critique process and then ultimately the
- 3:29
engineer builds it. That thing is just
- 3:31
not real anymore. I don't know about
- 3:32
you, but um I think that's starting to
- 3:35
collapse very quickly in small and large
- 3:38
companies.
- 3:41
And when it comes to the actual work of
- 3:43
design,
- 3:45
I feel like there's right now kind of
- 3:46
like two worlds that you can play in.
- 3:48
Either it's direct manipulation sort of
- 3:51
like in the pixel space, right? So
- 3:53
you're in Figma and you're manipulating
- 3:55
margins, paddings, whatever it is. Um or
- 3:58
you're in web flow or you're in some
- 3:59
other tool where you directly
- 4:01
manipulating the final output uh or the
- 4:04
design. Now that's fine, but then you
- 4:07
feel like you're getting behind because
- 4:08
everybody else is like agentic and going
- 4:11
crazy with loops and loop maxing, right?
- 4:13
And now you're going on the other
- 4:14
extreme, which is simply telling your
- 4:16
agent, please design this for me or
- 4:18
please build this. But it feels like to
- 4:20
me at least there's this there's this
- 4:22
middle ground that we haven't explored
- 4:24
enough like what is the exact level of
- 4:26
control? How can we insert the human in
- 4:28
the loop at the exact right time?
- 4:32
Uh and so this this came to mind then
- 4:35
it's pretty popular tweet a while ago.
- 4:37
Um so centering a diff with opus. Yes.
- 4:42
Uh not a great use of opus. Uh but you
- 4:46
know it kind of speaks to that problem.
- 4:48
It's like okay well when do we use which
- 4:51
tool? When is which tool adequate to do
- 4:53
what job?
- 4:56
In my opinion right now for most work
- 5:00
the direct manipulation of padding,
- 5:02
margins, spacing and so on is actually
- 5:04
at a elevation that's too low.
- 5:08
And on the other hand um if you go fully
- 5:12
agentic you get web pages like this now
- 5:15
that you would you would get this in
- 5:16
like 2022 I would say. So everybody here
- 5:19
can point out the typical AI slot
- 5:20
patterns. Um but the purple gradients
- 5:23
were actually way beyond that. there are
- 5:25
no purple gradients anymore uh in most
- 5:27
frontier models. Um now we just get this
- 5:31
and it's kind of wears a different suit
- 5:32
as Claude would say. Um but uh but it
- 5:36
really is slop as well. It's just a
- 5:38
moving target. So now we have I call
- 5:40
this claude beige. We have these
- 5:42
instrument serif fonts. We have italics.
- 5:44
And it's not necessarily a bad design.
- 5:46
It's just everything that comes out of
- 5:48
claw design looks that way. And when
- 5:51
everything looks the same, you kind of
- 5:52
get algorithmic unilo as I call it. Uh
- 5:56
so also not great.
- 5:58
Now here's my first hot take of today's
- 6:01
session. You cannot oneshot design.
- 6:05
Um now many people want to and maybe
- 6:07
we'll get there eventually. I just don't
- 6:09
think it's possible at the current
- 6:11
moment. Uh maybe not ever. Um, I think
- 6:14
in order to build something that really
- 6:17
looks and feels great and is effective
- 6:19
design, you need to have something
- 6:22
that's context context rich which has
- 6:24
been informed by what you're trying to
- 6:26
do, what your audience is, what you're
- 6:28
trying to build. And also it will have
- 6:30
to be multi-shot. You will have to
- 6:32
iterate on your design. Uh, and you I
- 6:35
mean even if you're a soloreneur, but if
- 6:37
you're not a soloreneur, you might have
- 6:39
different people who have different
- 6:40
opinions. Users have opinions. I mean
- 6:42
design is messy. it's process and
- 6:45
wishing it away and just saying like
- 6:47
solve this problem for me agent will not
- 6:49
unfortunately solve your problem. Um
- 6:54
now the other problem is if you don't
- 6:56
know the language of design or if your
- 6:58
stakeholders don't know the language of
- 7:00
design gets really frustrating really
- 7:01
quickly too. So if you've ever designed
- 7:03
something um you kind of know like this
- 7:05
kind of experience um and then you know
- 7:08
the inner feeling builds up of like
- 7:11
and at some point you're like
- 7:15
uh
- 7:16
so really what you have to ask first is
- 7:18
what's the emotional territory? What
- 7:20
should this never feel like? What's
- 7:22
what's the reference? What's the
- 7:24
audience? These are all really important
- 7:26
questions to figure out. Like you can't
- 7:27
go to a human design studio even if it's
- 7:31
the best design studio in the world. You
- 7:33
go to design director and you say like
- 7:35
you know what I want to design for my
- 7:37
brand and a design dire not nods. It's
- 7:40
like got it and then walks away. That
- 7:43
doesn't make any sense. Like they
- 7:45
obviously have to figure out what it is
- 7:46
that you're trying to build and what
- 7:47
you're trying to get out of it.
- 7:50
Importantly on this example even sort of
- 7:52
like the 2026 version of AI slop you
- 7:55
know quickly vibe coded page nobody
- 7:58
decided anything here
- 8:01
like you just oneshotted this nobody
- 8:03
decided anything on this page this was
- 8:05
just I mean it's maybe competent but
- 8:08
completely empty
- 8:10
so my uh thesis that I make here and
- 8:15
what I've been trying to build over the
- 8:16
last couple months is a tool that gives
- 8:19
you just the amount of control needed to
- 8:22
steer your agent in the right direction
- 8:24
with adjectives and verbs.
- 8:26
And these are the types of words I'm
- 8:28
talking about. Talking about words like
- 8:30
make this bolder, make this quieter, uh
- 8:33
distill this. So basically
- 8:34
simplification, um polish this, um make
- 8:37
it denser or harden this. Um harden for
- 8:41
instance would mean uh make sure that
- 8:43
this design works across the board.
- 8:44
Maybe the performance is bad on certain
- 8:46
devices. Maybe it's not responsive. Um,
- 8:49
and so these are these are words
- 8:51
that we use in the world of design. And
- 8:55
I noticed when seeing two people attempt
- 8:57
the exact same task and one is an
- 8:59
engineer who's never really touched
- 9:00
design at all and the other one is a
- 9:02
designer um there's a stark difference
- 9:06
even when they use the same model and
- 9:07
same harness everything in the output
- 9:09
that they're getting based on the
- 9:10
language that they use. So, I've been
- 9:14
trying to put that language basically
- 9:17
compress it into a skill uh and into a
- 9:19
system to be able to express yourselves
- 9:21
better. And so, for example, you could
- 9:24
have like a baseline um over here, but
- 9:27
then you make it bolder and the agent
- 9:30
actually knows what bolder in your
- 9:31
context means. You make it quieter, it
- 9:33
knows what it means. You distill and it
- 9:36
knows what it means.
- 9:40
Um, but then bolder how what does bolder
- 9:44
mean in the context of your project?
- 9:45
That's a really important question
- 9:47
because as you could tell at the
- 9:48
beginning of the demo uh in the cold
- 9:51
open uh when you just ask GPT or claude
- 9:55
whatever make this bolder it doesn't
- 9:56
know anything about what you mean. Uh
- 9:58
now it has its own sense of reference of
- 10:01
like what boulder could mean but it will
- 10:03
do whatever it wants right it will
- 10:05
invent new colors it will invent new
- 10:07
gradients. it will I mean it doesn't
- 10:09
matter um what it actually means in
- 10:12
impeccable
- 10:14
not gradients not glass not neon but
- 10:17
actually hierarchy scale decisive type
- 10:20
so uh things that uh don't break your
- 10:23
design system and adequately raise the
- 10:27
attention that the user would put on it
- 10:31
uh and this is an actual sentence from
- 10:33
the the file that is loaded when you say
- 10:37
bolder impeccable um show someone your
- 10:39
work and say AI make this bolder made
- 10:42
this bolder if they believe you you
- 10:44
failed this is something that we
- 10:47
actually instruct the agent to do for
- 10:49
themselves and then the agent oftent
- 10:50
times reflects and like I don't know
- 10:54
think I did some bad work here
- 10:57
an adjective is a light wart and a light
- 11:01
wart such a German term and Matt Puk
- 11:05
actually talked about this recently uh
- 11:06
who also makes some really excellent
- 11:08
skills. And so this is uh stolen by one
- 11:10
of his tweets, but I really think uh um
- 11:14
it makes a lot of sense. Um these are
- 11:16
words that h that you basically imbue
- 11:19
with meaning that you infuse with
- 11:21
meaning and they mean something. They
- 11:23
already mean something to the model, but
- 11:24
then you translate this into the area
- 11:28
that you're interested in
- 11:30
and the right altitude really shifts.
- 11:34
Um, now I don't think you can solve any
- 11:38
problems at that altitude. That's super
- 11:40
important too. Uh, there is still room
- 11:42
for the very beginning. For instance, if
- 11:44
you just want exploratory work and you
- 11:46
just want to get something on the screen
- 11:47
or you just want the last amount of
- 11:50
polish. I don't think right now uh AI is
- 11:53
good enough to replace humans for the
- 11:55
last 5, 10, maybe even 20% of the work
- 11:57
to get it from good to great. Uh but it
- 12:02
does actually make it better. Now I've
- 12:05
built tools for more than 20 years. I
- 12:07
guess I'm dating myself here. Uh but
- 12:10
whenever I build a tool, I actually map
- 12:11
the workflow first. I think about what
- 12:14
is the actual workflow of the target
- 12:15
user that I'm trying to help. And the
- 12:18
workflow of design is not linear. It's
- 12:20
messy. Has many different stages. Uh
- 12:23
there are different people involved. And
- 12:25
so I kind of mapped every part of the
- 12:27
process and thought about well what are
- 12:29
the injection points along that route
- 12:32
and how can we help along that route.
- 12:35
And so you start with initialization
- 12:36
with the shaping process of design uh
- 12:39
you go over to uh crafting to iterating
- 12:42
uh with all these verbs and adjectives
- 12:44
and then to the actual harden and polish
- 12:46
phase and finally you kind of bring it
- 12:48
back to your design system. You do some
- 12:49
tech debt cleanup design deck cleanup.
- 12:53
Um, now here's one example of a command
- 12:56
that I wasn't actually sure about
- 12:57
shipping and it's called overdrive. Um,
- 13:01
I basically built this uh built this
- 13:03
command in Impeccable that uh tries to
- 13:06
create something completely over the top
- 13:08
and it was kind of like a a half of a
- 13:10
joke maybe. Um, but people absolutely
- 13:14
are rabbit about this about this thing.
- 13:15
Um, and they love it. Um, and so this is
- 13:18
just one example of I mean this is not
- 13:20
oneshotted. Uh this is a um sort of
- 13:22
realistic event horizon shader um that
- 13:25
I've built for my shader library radiant
- 13:27
shaders. But I did actually use the
- 13:29
overdrive command for this to uh
- 13:32
overdrive it even more uh and make it
- 13:34
more ridiculous. So sometimes I come up
- 13:36
with these uh commands I'm actually not
- 13:38
sure about and I test them with the
- 13:39
community and once it sticks uh I
- 13:42
realize okay well there are more people
- 13:44
who are getting joy out of this.
- 13:46
Um
- 13:49
oh here we go. Here we go. Okay. Um, an
- 13:52
adjective with nothing behind is just a
- 13:54
nicer prompt. So, you really have to
- 13:56
tell the agent what you mean by the word
- 13:59
that you're using. Uh, it it has so many
- 14:01
different meanings uh within its
- 14:04
training materials that you really have
- 14:05
to tell it. Um, now here's another
- 14:07
thing.
- 14:09
I've gotten so many requests
- 14:12
for an automatic way of using
- 14:13
Impeccable. So many. It's so
- 14:17
frustrating. Like so at least once a
- 14:19
week somebody tweets at me say like you
- 14:21
know what would be cool just let
- 14:22
impeccable do all the work by itself. I
- 14:24
don't have to decide on any command
- 14:25
anymore. That's not the point. The point
- 14:27
is to give you a way to steer what you
- 14:30
want to end up with. It's never going to
- 14:33
be a tool to oneshot design. That's not
- 14:35
the intent. And I'll never I mean
- 14:37
there's a pull request standing uh
- 14:39
standing out right now that I'm going to
- 14:40
close because of that.
- 14:43
There is no auto and there will be no
- 14:45
auto
- 14:47
in my opinion and uh this is a bit
- 14:49
awkward maybe for some of the next
- 14:51
speakers but I think taste cannot be
- 14:54
amplified uh sorry I think taste can be
- 14:56
amplified I think I call this amplified
- 14:58
craft uh and I think you can work with
- 15:01
tools to sharpen your taste and bring
- 15:04
out more of your taste I really do not
- 15:05
think it can be lab ground lab grown I
- 15:07
think it is uh taste by definition sort
- 15:11
of is uh contextual It's cultural. It's
- 15:15
scars. And once everybody replicates the
- 15:17
same thing, it starts to become really
- 15:20
muddy and we don't think of it as taste
- 15:23
anymore. That's my opinion. And I know
- 15:24
this is like a hotly contested topic.
- 15:26
Uh, but I'm not trying to solve taste
- 15:28
with my tools.
- 15:30
Um,
- 15:32
that's what I got. Uh, this was about
- 15:34
finding the right level of control for
- 15:36
design. Thank you very much. And, uh, I
- 15:38
think I have time for a few questions if
- 15:40
you have any. Thank you.
- 15:56
>> [music]