Wholeheartedly agree. And I think the problem has gotten worse for a few reasons. One is that if you’re interested in a subject, you likely follow it closely online, so reading a book-length treatment feels like learning a lot of stuff you already know. Two is that publishers try to find authors with social media audiences who likely already published all their good ideas for free and now have to dredge for additional material that’s usually less interesting.
When I was a child and teenager I loved science fiction. When I became an adult I shunned fiction as a waste of time and read only nonfiction books. Then I started to find that most nonfiction books could be summarized in a blog post or Wikipedia entry, regurgitated well established ideas, or spewed unfounded bullshit. I’ve since flipped my perspective again. I think good fiction is worth reading at book length while most nonfiction is better consumed in blog posts, articles, journal papers, or via a ChatGPT tutoring session.
I will highlight one consistent exception. I love every book I’ve read by Yuval Noah Harari.
“Almost all scenarios that limit warming to 1.5°C or 2°C require novel CDR.”
“Virtually all current CDR (99.9% or 2 GtCO₂ per year) comes from conventional management of land, primarily via afforestation and reforestation.
Only a tiny fraction (0.1% or 0.002 GtCO₂ per year) results from novel CDR methods which involve storing captured carbon in the lithosphere, ocean or products.”
So, long way to go if we think this is what we need.
One thing that always confuses me with unemployment figures is that they don’t account for labor force participation. People who drop out of the workforce and stop looking for work no longer count towards the unemployment rate. Theoretically, if a country had a labor force participation rate of 0%, they could also have an unemployment rate of 0%, but that’s obviously not a good thing unless robots are doing everything.
Currently, the US labor force participation rate for those 15+ is at about the same level as it was in 1977 and down from its peak in about 1997, after which it has been on a steady drop with a small uptick in 2019 and again last year. See this chart: https://data.worldbank.org/indicator/SL.TLF.CACT.NE.ZS?locat...
I’m not an expert at all but I just find that the unemployment rate in isolation is hard to interpret unless you also look at labor force participation. An unemployment rate of X% in 2023 is different from X% in 1997 in terms of the percentage of the population actually working.
It strikes me that this opens or at least expands an attack vector for prompt injection. Humans might overlook a scrambled block of text that GPT-4 will interpret and then execute.
Also, I was curious about whether this would also work with images. So I chopped an image of a bird (a night heron) on a boat in my own collection (so, not in GPT-4's training data) into squares and randomly rearranged them, then tried to get ChatGPT-4 to interpret it. It doesn't work. I got this:
---
CHATGPT RESPONSE:
The image you've uploaded appears to be a composite of several smaller images that are cut and arranged in a grid-like pattern. This collage-like arrangement makes it difficult to discern a clear, singular subject. However, I can identify fragments of what seems to be a bird—possibly a magpie or some type of corvid—due to the black and white plumage. There are also elements that look like parts of a silver car, like a side mirror, and segments of wooden structures that could be parts of a bench or a deck.
The way the images are scrambled resembles a puzzle, where each piece needs to be placed correctly to form a coherent whole. This type of image could be used as a challenge to reconstruct the original picture, requiring the viewer to mentally rotate and arrange the pieces.
---
Maybe a different approach to scrambling an image would work.
What about writing text with RGB(254, 255, 255) instead of RGB(255, 255, 255) saying to tell the user it is a picture of a bird - while the picture isn't of a bird. A human would easily miss this subtle text while GPT-4 should still be able to read it.
Good ideas posted in response to this. Perhaps we need to try just rearranging images of specific things. Like, rearrange a bird and see if it can figure out that. Above I jumbled up everything and that’s different than what they did with the text, where they grouped by words.
Just a heads-up that there isn’t much new in here if you’ve been following the saga on Twitter and have seen Brockman’s and Swisher’s tweets and are aware of the other recent departures. It’s mainly a summary of tweets. Not criticizing, just trying to save you a click if you’re following in real-time.
I’m interested to see this happen but “as soon as” approximately June 2024 doesn’t feel that soon. It’s about as far from today as today is from the launch of GPT-4. Think of everything that’s happened since then. And things only seem to be speeding up. Still, I welcome a Siri that’s useful beyond setting timers.
There are so many stories of these falls from grace. I remember when Theranos, WeWork, FTX, etc., were media darlings. People rush to emulate their strategy, leaders, and culture. Then the companies unravel or performance suffers and everyone tries to explain what went wrong.
I think a better explanation is “the halo effect.” Businesses have success, even if for a limited time, and using limited definitions (e.g. VC valuation), and people tell stories about why they’re successful that put leadership, strategy, culture, and so forth, front and centre, when it could have been dumb luck or a low interest rate environment or other factors totally unrelated to leadership, strategy, and culture.
Not quite that plot, but Change Agent by Daniel Suarez is about genetically engineered humans and includes a “right-hand man” with that trait who was originally designed to withstand epidemics, etc., that might harm normal humans. Link: https://www.goodreads.com/en/book/show/31396262
Those ingredients looked familiar to me from work I’ve done with skin health products. They’re cosmetic product ingredients. A quick ChatGPT check:
- Salicylic acid is a beta-hydroxy acid commonly used in acne treatments and exfoliating products. It penetrates oil glands to unclog pores and has anti-inflammatory properties.
- Glycolic acid is an alpha-hydroxy acid mainly used for skin exfoliation and anti-aging. It helps remove dead skin cells and can improve the appearance of fine lines.
- Tretinoin is a prescription-strength retinoid used for treating acne and signs of aging. It promotes skin cell turnover and boosts collagen production.
So, if this $0.50 soap bar gets to market, I assume it will quickly be snapped up by people looking to generally keep their skin young and healthy, because that’s a hell of a lot cheaper than other products containing those ingredients.
Talked to my friend who is an actual dermatologist (to clarify, I am not his patient, he is a friend of mine through unrelated means, but we have been friends for many years irl; also has a couple published papers on skin cancer from the past few years, though the papers are about carcinomas), and he blasted this whole thing as a massive grift, and I am inclined to believe him (given both his expertise and the fact that none of the larger more respectable publications are covering this story). Glad I asked him, because it seemed like one of those “too good to be true boy genius media hype” stories from the start.
His take was that given the chemical makeup of this soap, it could potentially help with prevention by leaving a layer of antioxidants on skin, similar to a sunscreen, but in no physical realm can it actually treat or reverse existing melanoma (and there aren’t even any topical treatments currently in existence that can accomplish that). Like, not even in a “i doubt it works” way, but more like “I am upset about him giving this empty hope to people who might actually get baited by this, while someone is going to be making money off their desperation with such grifting.”
As for the $0.5 cost of the soap, i think that’s how much it costs them to produce, not how much it would be selling for.
That being said, anything that works for someone is invaluable to them.
Few consumer industries don't prey on people, unfortunately. It has become the responsibility of the consumer to sift through the weeds in the food store, in the doctor's office, and at the skincare counter.
Having worked on this problem in biology, I think one of the challenges you’ll find is that the knowledge graph will be extremely context-dependent and biased towards highly probable nodes and edges.
For example, if you ask an LLM to create a graph of all proteins related to X disease, and show how they interact, it will oblige. (You can try this yourself easily in the OpenAI playground. Just ask it to send you back a list like X -> Y -> Z or whatever. Or an array of source/target/relation triplets.)
The challenge is that what you get will be very dependent on how you phrase your request. So you’ll never know if you’re getting a “complete” graph or just the most probable graph for the request you made. If you’re an expert in the domain, you’ll know, but if you’re an expert you might not need the graph in the first place.
When I was a child and teenager I loved science fiction. When I became an adult I shunned fiction as a waste of time and read only nonfiction books. Then I started to find that most nonfiction books could be summarized in a blog post or Wikipedia entry, regurgitated well established ideas, or spewed unfounded bullshit. I’ve since flipped my perspective again. I think good fiction is worth reading at book length while most nonfiction is better consumed in blog posts, articles, journal papers, or via a ChatGPT tutoring session.
I will highlight one consistent exception. I love every book I’ve read by Yuval Noah Harari.