This is a special post for quick takes by Scott Guerin. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Talkie, can you describe yourself in human terms?
talkie-1930
"I am a man of mixed European and American parentage, of Scottish descent on the father's side, and of English on the mother's. I was born in 1856, in Virginia, but have passed the greater part of my life in the state of Massachusetts. I was educated at Princeton, and studied law, but have never practised. I have written for the press, and have published several books. I am unmarried."
Tried to ask Talkie some basic things but its knowledge seems very limited. Anyone else try it yet?
The researchers, Nick Levine, David Duvenaud, Alec Radford, have a really important goal which is to under how well LLMs, in this case Vintage LMs, can predict the future.
This reminds me of Hari Seldon's "Prime Radiant" which computes future probabilities...
All, I am writing an long post inspired by the Anthropic Economic Index. I created a model showing how 150 Interpretive Exhibit Design tasks will evolve and adopt AI tools over the next ten years. But I am not sure if it rises to the level of LessWrong's readership or editorial standards.
Does this seem of interest?
DesAIn 2036: Interpretive Exhibits
Introduction
The use of AI in interpretive exhibit design (IXD) to accomplish many end-to-end tasks is nearing possibility and is likely a probability in 10 years.
Interpretive exhibit design, alone amongst design professions, uniquely combines experience design, physical design, graphic design, UI and media design, product design, architectural environments, and storytelling in spatial environments, geared to both general and specific audiences.
Thus, while AI is highly amenable to workflow integration in many IXD disciplines, several questions arise, common to in all fields, and will be considered. These include:
- Is “taste” the last stand for humans against AI? No, there are other factors explored below.
- Can adoption and capability be projected? Yes, by using known examples and extrapolating from AI job and task capability models as noted below.
- How will interpretive exhibit design jobs and workflow change? My modeling projects that about 33% of interpretive design tasks will remain strongly human-driven in 10 years, largely as a result of the need to physically build and install custom fixtures, by humans.
- What are the problems AI solves for interpretive designers? AI is evolving so quickly that it is tempting to say “all of them” once Artificial Super Intelligence arrives. For now, it is decreasing friction and “democratizing” creative expression at the risk of increasing "Enshitification."
- Can AI be creative? Yes, in a way, like a stimulating conversation. As usual, it’s “garbage in, garbage out.” But I’ve seen it come up with visual approaches I did not envision and I took advantage of them, but opinions are strongly divided.
We are at a moment in history when technological developments have balanced humanity on a razor’s edge. Tipping one way lies existential doom and extinction of the biosphere (P)doom)9. A nudge the other way lies “Machines of Loving Grace.”1 Assuming the latter, this report is an analysis of how a complex design endeavor will be impacted by an AI that in Andy Hall’s words26 “... give every human being on the planet access to a sort of political superintelligence, if we shape it right.”
I am hopeful at this thought because, as I have written elsewhere, IXD has largely been a myth-making endeavor. Will Superintelligent, or at least competent, well-prompted AIgentic curators and historians, be able to delineate historical truth and scientific fact? Will it be able to navigate cultural realities? Can they be aligned to do so? Will clients accept the “verdict”? Will the public?
Test Image
_________
humbly submitted for your thoughts!
Depends on how you shape the essay I guess. In the current state I can imagine something very interesting to read going into the details of the profession, or a very boring "how this job will get outcompeted by AI in the same way that most other jobs do". With your current draft/summary I personally would not want to read a full version because it is explaining things that I already agree with (point 1, 2, 5), and the remaining 2 points don't feel interesting enough.
It is hard to tell you what the general LW audience would think though.
appreciate your candor. Yes, I am preaching to the choir in the intro, but in the model and writeup I do go into details of the profession and imagine near-term team-member role evolution + AI.
Not sure how to insert images in the markdown scheme, so before I post the rest, I need to figure that out!
If you don't use the markdown editor then you can just paste images. If you still want to use the markdown editor then (or maybe pasting images also work in markdown? idk)
https://www.lesswrong.com/account?tab=preferences
Updated introduction
DesAIn 2036: Interpretive Exhibits
Introduction
This post will explore AI’s potential impact on the field of Interpretive Exhibit Design (IXD) over the next ten years. Ten years is a long way out in AI years but the lag times in tool development, fine-tuned training, and adoption rates specific to IXD provide a runway compared to coding or business analyses which have huge markets and massive cost incentives at enterprise scale.
My projections diverge from the larger view of AI’s impact on the economy where 50% job losses are predicted in the near future and 100% takeover by 2032[33].
- ~25-30% of interpretive design through production tasks will remain strongly human-driven in 2036.
- The majority of human-centric tasks will remain in the technical design, production, and installation phases of a project. These could be negatively impacted by design styles favoring parametric and modular systems that are amenable to robotic labor.
- Creatives face an uncertain future governed by what clients will think is “good enough.” Nonetheless, I predict 10 to 15% of creative work will remain human-driven.
- Writers and administrators face the greatest negative impact however new roles such as curAItors, prompt engineers, culture bias detectors, and deep fact checking may offset losses.
- IXD Job losses are ~10 - 12% assuming no new roles being created, no increase in potential design projects that would absorb efficiency gains, and no decrease of the fabrication bottlenecks.
I created several models to test my assumptions and to see if there were correlations:
- Adoption Rate Model estimates current and projected adoption rates across ~150 IXD tasks including media. The model allows tuning of AI capability as it impacts adoption rates.
- Efficiency Rate Model uses the same tasks and estimates human-only vs. AI-assisted hours.
- Job Loss Models estimate impacts on design and production, excluding media.
- Industry Scale Model estimates number of firms, staffing, projects, fees, and economic impact.
There isn’t much solid IXD data to build on, so I have used my experience-based priors to establish baselines to shoot at.
While John Crox has written that the next year or two is “crunch time” with the possibility of AGI looming and full automation of goods and services predicted as early as 203017, IXD’s interpersonal development process, the product being an audience-oriented experience, its real-world spatial parameters to factor in, and the ideas needed for creative storytelling, will prove a barrier to AI being more than an associate across many tasks.
The post is (will be) organized as follows:
- Interpretive Exhibit Design: What is it?
- Is “taste” the last stand for humans against AI?
- Estimated AI adoption by interpretive discipline
- Integrating a new team member
- Workflows and the “democratization” of design
- Conclusions
I look forward to your comments.