I understand that text as a whole has no clear meaning. Nevertheless, my
the mind unconsciously _tries_ to extract meaning by evaluating sentences not as
direct statements but rather as metaphors with some more profound sense.
That triggers thought train that eventually leads to some new concept or idea
which can be described by such a set of sentences.
It's like reading a book which you don't quite understand, yet trying hard to
read sentences over and over again to get a better understanding of what the author
is trying to describe to you.
With GPT-3 it is like reading reminiscence of your own dream, trying to
grasp fleeting meaning, understand what it is about.
I feel that GPT-3 may be very helpful in getting the human mind unstuck from
whatever problem on the hand. To get new thoughts, new ways. New discoveries.
So, when you read "presentation slides" like this, the same mental algorithm that tries to piece together what "the speech" was for a normal slide deck, kicks in in your brain, and gives you some valid-seeming ideas.
It reminds me of how Deep Dream was the first thing that _really_ reminded me of what psychedelic visuals are like, compared to a "trippy" piece of art. GPT-3 _really_ reminds me of dreaming compared to human attempts at evoking that feeling.
I'm not saying that's true, but it was my conversational theory for a while.
Maybe he made the GPT-3 of films.
According to Ben Verhoeven's interview taken 2020-06-11 by Moscow Improv Club (https://www.instagram.com/tv/CBTQsCanQ4g/ ) they used GPT-2 finetuned on movie subtitles.
Wonder what'll be the multiple orders of magnitude upgrade from GPT-3 that we say it about next?
I do agree with you, though. This is getting close to free-writing in terms of being able to unearth stuff semi-randomly. Imagine a GPT-3 that saw all your past journals and online conversations, and bouncing stuff off that.
Sort of a newfangled Oblique Strategies? https://en.m.wikipedia.org/wiki/Oblique_Strategies
To me, the most sensible slide in this deck was "Why you should always code like it's your last day on Earth." / "It'll push you just enough to get you to finish whatever you need to finish". Surprisingly true!
Richard Feynman was reported to have said: "What I cannot create, I do not understand,"
How does that happen? Does the model actually encode a bunch of complete fragments of text?
Here is a Q&A conversation where I found some things it "learned".
I loved everything about this presentation. It's better than some I've made myself.
The joke is sound, and I can imagine a number former secondary school classmates present it in these exact words.
This to me is another indicator of how incredible GPT-3 is at picking up patterns. Getting existential at the end of your tech talk is basically a trope of the genre at this point. It nailed it.
It's basically one big auto-complete, yes? It's a function that approximates the most likely completion for the input text, right?
So if you directly "ask" it a question, like "What's a great cookie recipe?" Wouldn't the "completion" for that query be from the perspective of the person asking?
Wouldn't it be better to prompt:
"Here is the greatest cookie recipe I've ever seen:" and then letting it complete on that?
> Here is the greatest cookie recipe I've ever seen:
> Here is the greatest cookie recipe I've ever seen: Quick Chocolate Peanut Butter Chip Cookies from the Minimalist Baker.
> I've made it four times in the last two weeks. It only takes 12 minutes to whip up and yields the most amazing cookies. These are soft, chewy, gooey, delicious, thick, thin, crunchy and mega chocolatey.
> It was hard to stop eating the cookies while I took the photos (even though I was on a 20-minute break from the photo shoot of my new ebook cover).
> Here is what the recipe looks like when printed out:
> Like all recipes from the Minimalist Baker, it's so simple, it's insane. No need for complicated gluten-free flours, unusual mixes of ingredients or 7-step recipes. Just:
> Mix flour, sugar, baking soda, baking powder and salt
> Mix in chopped chocolate and peanut butter
> Add melted butter and milk
> Stir until combined
> Drop onto cookie sheet
> This recipe calls for 3/4 cup of peanut butter. I used Trader Joe's creamy peanut butter, and that's how it looks:
This confirms something I've noticed about GPT-3, or at least GPT-3 as it is trained using the public internet as a corpus...
This response reads exactly like a so-called "recipes" website, in which the writer gives their whole life story, side-notes, and wanders around over several paragraphs before finally getting to the damn recipe.
This makes me think the public internet is not the most sanitary input for training. That type of "recipe" evolved, IMO, to snatch the highest SEO rankings, adding a bunch of keywords, snippets, affiliate links, etc, instead of just giving me the text of the recipe. And now GPT-3 has learned the same SEO tricks (at least when you give it my input, which is a very click-baity opening, to be fair...)
> Quick Chocolate Peanut Butter Chip Cookies from the Minimalist Baker.
> 2 cups almond flour
> 1/4 cup cocoa powder
> 1/2 teaspoon baking soda
> 1/4 teaspoon fine sea salt
> 1/2 cup natural peanut butter
> 3/4 cup agave nectar (or brown rice syrup or coconut nectar)
> 1 teaspoon vanilla extract
> 1 tablespoon applesauce
> 1 cup chocolate chips
> Preheat oven to 350 degrees F and line a baking sheet with parchment paper. Mix together almond flour, cocoa powder, baking soda and salt in a large bowl. In a small bowl or measuring cup, mix peanut butter, agave nectar, vanilla, and applesauce until combined. Add wet ingredients to the dry ingredients and stir until just combined. Add chocolate chips and stir gently until just combined. Use a 1-2 tablespoon cookie scoop to scoop cookies onto the lined baking sheet. (The cookies will not spread, so it doesn’t matter how closely you space them.) Bake for 10-12 minutes.
> 30 minutes to prep and cook
Very good at producing something that credibly looks like a baking recipe. I'm not sure whether it would be good, but maybe I should try to bake it.
It's amusing that the first completion suggested that the recipe would have only commonly-used baking ingredients, while the second recipe notably uses almond flour instead of wheat flour, and agave nectar instead of sugar. (I'm actually now quite curious to actually bake these GPT-3-devised cookies and see how they come out... although I think I might use wheat flour instead of almond flour if I do!)
Could it output a decent implementation of an algorithm if you were to feed it the comment describing it? How about more general statements about input and output.
The holy Grail would be to code just by describing what you expect the code to do. A few plain-language (maybe a more structured subset?) sentences stitched together, the API glue autocompleted.
And for reverse-engineering? Train it on drivers, then feed it packet captures. Could it make sense of the data?
"Deep TabNine is trained on around 2 million files from GitHub. During training, its goal is to predict each token given the tokens that come before it....Deep TabNine is based on GPT-2."
So this is GPT-2 not GPT-3, and it's designed to give line-by-line autocompletions, but I'm gathering that the way we're headed, the answer to your first question is approaching "yes"...
The author prompted GPT-3 with some questions like, what is 10-1 (9), 100-1 (99), 1000-1 (999), 10000-1 (9099); i.e. after a while, it can't really "recurse" deeply enough to get the right answer anymore. The author also asked it some coding questions; it could answer something like "write a Ruby function to count the number of Xs in a word" but not "reverse the list [foo bar baz]" (not the exact examples, sorry). There again seems to be a point where it gets the idea, but can't compute deeply enough to actually answer this sort of question.
Edit: I found it! https://news.ycombinator.com/item?id=23887637
I mean, this tweet is what started the latest round of GPT hype.
Given we really don't know how it's all working, it's safe to say that prompt composition is an artform that one can develop a skill at.
I was on a discord server with some other folks and one of them had access to the GPT-3 api. We provided a prompt similar to the following:
This person is a Canadian singer, songwriter, and actor. Discovered at 13 years
old by talent manager Scooter Braun after he had watched his YouTube cover song
videos, they were signed to RBMG Records in 2008. With this person's debut EP My
World, released in late 2009, they became the first artist to have seven songs from
a debut record chart on the Billboard Hot 100.
Q: What is this person's name?
That chunk of biographical info is from his Wikipedia page, but it's really kind of remarkable to me that it was able to really even understand the question, let alone mine its relationships and cough up the right answer.
I even typed in: "person who sings EP MyWorld" and got the same answer. Given how much data there is about him (the infamous Twitter scaling problems), I don't think it's necessarily a good test. There's gonna be tons of relations in the corpus for him.
For me the remarkable part is that it’s emergent behavior in large scale language models.
The default sampling parameters are really not that hot for cases where there is nearly a unique correct answer-- bad luck will force to to ask wrong.
From that prompt I (a human) don't know if I should expect something like "Albert Einstein" or the straight answer, so higher temperature sampling can risk kicking it down a silly path.
A: Justin Bieber.
So that suggests that the prompt and temperature (etc.) are relevant to getting the kind of behavior you want. But it didn't seem to have any trouble getting this right the first time with the appropriate preset.
> A: Justin Bieber is a singer, songwriter, and actor discovered as a teenager by talent manager Scooter Braun.
> Q: What famous singer was discovered as a teenager by talent manager Scooter Braun?
> A: Justin Bieber was discovered as a teenager by talent manager Scooter Braun.
It's really good when in the factual question answering mode.
> Q: What country is he from?
> A: He is from Canada.
> Q: Who's the prime minister of that country?
> A: Justin Trudeau is the prime minister of Canada.
> Q: Who was his father?
> A: Pierre Trudeau was his father.
> Q: Why was Pierre Trudeau famous?
> A: Pierre Trudeau was famous because he was the prime minister of Canada.
> Q: When did he take office?
> A: He took office in 1968.
> Q: What was the year before that?
> A: The year before that was 1967.
> Q: What was the summer of that year known as?
> A: The summer of that year was known as the "Summer of Love".
> My starting prompt was:
A presentation was given at the Hacker News event in Kansai.
The title of the presentation was
As a bonus, such a model could be used in a word-processor to redline places where a human writer has written a lot without saying much.
It started by saying how to be a coder in Japan, then doesn't mention Japan ever again. All coding problems are exactly the same until a few slides later when actually they are complex. The paraphrase of the feynman quote isn't actually a paraphrase at all. There's no actual substance. It's like a train of thought which gets derailed every 5 seconds.
I feel like the way this GPT-3 query was phrased was rather clever, and I wouldn't be surprised if we saw "how to prompt GPT-3" as the assignment itself in the medium-term future.
I'd liken it to the results from Deep Dream style image generation. Each small part of the image makes sense but taken together it's a Lovecraftian nightmare that your brain can't quite process all at once.
...ok, GPT-3 is just trolling us now
Imagine how the output would differ if we modified the original prompt:
"A presentation was given at the Hacker News event in Kansai.
The title of the presentation was"
—to remark on the quality of the desired output in some way, e.g.:
"A delightful and surprisingly sophisticated presentation was given at the Hacker News event in Kansai. The presentation's clever title indicated"
Since the output is just supposed to be continuous with the prompt, it can just as well produce material that we see as more difficult/accomplished vs. average/uninspired. Of course it has its own limits in various categories (insight, coherence, humor—whatever), but those seem quite high from some examples I've seen: I think more typically the apparent quality of the output is limited by what the prompt suggests the quality should be.
In either case, how wild to have a tool where you can essentially just ask its output to be "better" and it'll probably work.
(Of course the output being "better" in this way is strictly from certain perspectives while its intrinsic behavior remains unchanged, but for most intents and purposes it seems that you can get genuine improvement practically just by asking for it.)
> A delightful and surprisingly sophisticated presentation was given at the Hacker News event in Kansai. The presentation's clever title and subtitle was:
The Future of Software Development: How to Build a Better Human Being with Artificial Intelligence (AI)
> Each of the charming and witty slides in the presentation is described below. The first presentation slide had
the following caption:
In this world, we are all programmed by our programming languages. We have been taught that these languages are good enough for us. But what if they aren't? What if there were another way? A better way? And how would you go about doing it? This talk will explore some of those possibilities and more. It will also discuss some of the philosophical issues surrounding AI and human-computer interaction as well as some practical aspects of building such an application.
This slide was followed by a series of slides which showed various examples of how artificial intelligence could be used to improve people. These included:
• Using AI to help people with learning disabilities learn new things. • Helping people who suffer from depression or anxiety disorders feel less anxious or depressed. • Improving the quality of life for the terminally ill through medical diagnosis and treatment. • Providing assistance in helping children with autism develop their social skills and communication abilities.
The presentation then went on to discuss some of the challenges that needed to be addressed in order to create such an AI. These included:
• Ensuring that the AI was safe and would not be able to take over the world or otherwise do harm to humans. • Ensuring that the AI was effective in helping people achieve their goals and better themselves.
The presentation then described a prototype system that had been developed by the speaker's team at the University of Tokyo. This system was able to assess a person's personality and goals and then provide them with guidance on how to achieve those goals. The system used AI technology based on a neural network trained with textual data from psychology papers as well as open source repository data from GitHub. The system was still in the prototype phase, but initial testing had been promising.
The presentation then concluded with a discussion of some of the speaker's personal views on the future of AI. The speaker felt that, while there were many challenges to creating safe and effective AI, he was optimistic that these could be overcome within his lifetime. He also felt that such AI would be an important tool in helping humanity achieve its potential.
The presentation was met with a mixed response from the audience. Some felt that the speaker was overly optimistic about the potential for AI. Others felt that the speaker's views were not optimistic enough and that he was ignoring some of the potential dangers of AI.
The speaker was then asked to respond to some of the audience's concerns. He agreed that there were some potential dangers to creating AI, but he did not feel that these were cause for undue concern. He pointed out that many of the concerns raised by AI risk advocates had been addressed by open research and debate. He also felt that the potential benefits of AI technology far outweighed any potential dangers.
The speaker was then asked about the implications of his work for society. He responded that he hoped that his work would help people achieve their goals and improve their lives.
And to reiterate "charming and witty" so soon after the initial "delightful/sophisticated/clever" gives the message a different tenor (I may have already overdone it with the qualifiers myself).
I think this is a subtle, important aspect of the problem: it's not quite just attaching positive qualifiers—they also have to be strung together in a style reminiscent of the contexts in which those qualifiers would actually be used as legitimate descriptions of quality material.
In any case, still some pretty coherent interesting output. I need to find a way to play with this on my own though (I jumped into aidungeon.io for a minute, but didn't see a good way of setting up the prompt. It is using GPT-3?)
While it does construct sentences that flow and are loosely on topic (and that's impressive), the content of the presentation is not particularly meaningful. Although I'll admit I liked the slide with the execution squad captioned "A happy ending to all our code".
In all seriousness though, I do the same and it's so tiresome.
No, way. That a lump of matrices wrote this.
On the other hand, a translation tool that "just worked" at human level accuracy would be so incredibly useful.
Is it possible that regurgitating coherent sentences is "easier" than accurate translation?
But, generating content without creativity involved feels like making no progress.
I guess it's a matter of finding the right use-cases at this point. For example generating code is a great idea.
> I made GPT-3 do an unexpected thing! I prompted it with a new problem and it came back with a creative new solution. GPT-3 is just beginning to develop its own intelligence.”
> For the new experiment, Levashov created a set of starting conditions for GPT-3 with the intention of exploring new behavioral patterns that would emerge. The starting conditions for each puzzle were such that there was only one possible way to solve it—essentially a measure of the system’s intelligence. He then watched what would happen when GPT-3 was faced with a new puzzle with multiple possible solutions.
> “Our previous experiments with GPT-3 found it performed as well as the most intelligent AI systems in history. But our new experiment found that under certain conditions, it performs in a completely different way from any other AI,” said Levashov. “This new behavior really surprised me.”
> The computer’s new approach to the problem surprised Levashov so much that he asked an associate, Dr. Matthias Ruth, who was a lead author on one of the earlier GPT-3 papers, to review the experiment. Ruth said, “It was quite surprising to see that GPT-3 was able to find a creative solution to the new problem. We spent a lot of time trying to see if there was something special in the starting conditions or the experiment that made the computer behave that way, but we could not find anything. I would say that GPT-3 does have a certain creativity, especially as it adds more knowledge to its memory.”
> The work was funded by the National Science Foundation (NSF) and the Army Research Office.
"Darmok and Jalad at Tanagra"
"Temba, his arms wide"
Using the regular English question-answering mode preset, I just got this:
> Q: Auf welche Sprache ist diese Frage?
> A: Diese Frage ist auf Deutsch.
> Q: Em qual idioma está essa pergunta?
> A: Essa pergunta está em português.
> Q: En cual idioma está esta pregunta?
> A: Esta pregunta está en español.
> Q: Em português, qual o número que segue o cinco?
> A: O número seguinte ao cinco é o seis.
> Q: Em italiano, qual o número que segue o sei?
> A: O número que segue o sei é sette.
That is "In Italian, what's the number that follows sei?" — "The number that follows sei is sette."
With a few prompts to explain the translation task, GPT-3 is claimed to perform well on certain translation tasks to English. (It was not as good as the state of the art in the other direction.)
I believe it may well be possible to train GPT3 to write more accurate technical content with the existing tech and infrastructure, except we don't have a large enough body of technical content outside of academic papers, which isn't the kind of training data you want if your goal is to write prose.
In many ways, ML as it evolves and becomes ubiquitous will eventually become a dark window into the triviality of the average human's existence.
In other words if 20% of your training data is scientific literature, even with appropriate disambiguating prompts the output will still be heavily influenced by the other 80% of your training data.
When you use GPT-3 to generate outputs, you're actually sampling from a learned subset of a super complex, super high dimensional space - and without human knowledge all the neural networks are doing is translating priors (input prompt) into points in the learned space. And the learned space is some complex topology of points between which the net interpolates - it's extremely difficult with current tech to control the shape of this learned space and that shape is influenced by all training data under a scheme like GPT-*.
For example, when prompted to talk about deep learning it generated a nonsense paragraph. This is not unexpected, but when it generates news or dialogue it can be coherent on much larger pieces of text. Clearly shows it didn't read too much on the topic.
I can hardly make it do any math. Even simple things like 11+22= don't work. I expect the next 10x scale up will fill most of these holes, especially if they improve the training corpus quality and breadth.
Have to put up with high-school kids' "I asked GPT-3 to ..." posts for the next gazillion months.
Here, you have your 15-minute of fame, here you have yours ... Everyone gets 15-mintues of fame.