“‘blur’ tool for paragraphs” is such a good way of describing the most prominent and remarkable skill of ChatGPT.
It is fun, but so obviously trades off against what makes paragraphs great. It is apt that this essay against ChatGPT blurry language appears on The New Yorker, a publication so known for its literary particularism. ChatGPT smears are amusing, but they are probably also yet another nail in the coffin of the literary society. Nowadays we are not careful readers; we skim, skip, and seek tools to sum up whole books. Human knowledge is in the ability to produce the particular and the ability to recognize it. For philosophers such as Iris Murdoch, careful attention to the particular, to just the right adjective in describing a friend, is a moral attention.
With Google we took the job of storing quotes (and other decompressed writing) and made it the remit of the machine. But we still asked for it back uncompressed. Here with ChatGPT, we are beginning to accept back a blur, because the Declaration of Sock Independence is immediately, Tiktok-speedily funny, and no one’s reading the original declaration anymore anyway.
For those who, like me, had missed out on this nugget of comedic gold, here's what ChatGPT had to say when it was asked to "describe losing your sock in the dryer in the style of the declaration of independence":
When in the course of household events, it becomes necessary for one to dissolve the bonds that have connected a sock to its mate, and to assume among the powers of the laundry room, the separate and equal station to which the laws of physics and of household maintenance entitle it, a decent respect to the opinions of socks requires that it should declare the causes which impel it to go missing.
We hold these truths to be self-evident, that all socks are created equal, and are endowed by their manufacturer with certain unalienable rights...
On Hacker News we often complain about headlines because that's all we see at first. But I've been using Kagi's summarizer [1] and I think it's a great tool for getting the gist of certain things, like if you want to know what a YouTube video is about without watching it. (Google Translate is useful for similar reasons.)
Perhaps someday, Hacker News will have an AI-generated summary of the article at the top of each comment page?
Similarly, ChatGPT excels at fast answers for questions like "What is a X", where you just want a quick definition. It's probably in Wikipedia somewhere, but you don't have to read as much. And it might be wrong, but probably not as wrong as the definition you'd infer from context if you didn't look it up.
We probably would be better off if these things were called "artificial memory" rather than "artificial intelligence." It's an associative memory that often works like human memory in how frequently it confabulates. When you care, you write things down and look things up.
If I try to map the first three into text, there are automatic TL.DR. like you said, document grouping, and search into entire document stores (as in do documents in this store deal with this idea?). On "artificial document creation", there is that highly valuable service of answering stuff like "hey, that thing with sticks that rotate and pull a vehicle around, what is its name again?"
More cynically: it'll be hard to kill the few legacy zombies that have survived so much destruction at the hand of free internet content already.
Supposedly, if I'm remembering last discussion with a japaneese speaker correctly, the same stem is used for "blur", or "blurry" (bokeh, bokeshi).
Which is kind of interesting parallel here
The overlap is that the verb "bokeru" and its root "boke" can be used to describe someone losing their mental faculties e.g. through age or disease such as Alzheimer's, and by extension it can be used as an insult to mean "stupid" as well. But etymologically there is no connection.
> Probably originally a transcription of Sanskrit मोह (moha, “folly”), used as a slang term among monks.
The syllables are different; baka is ば か, bokeh is ぼけ [2]. Could those really be from the same root?
[1] https://en.wiktionary.org/wiki/%E9%A6%AC%E9%B9%BF#Japanese
[2] https://en.wiktionary.org/wiki/%E6%9A%88%E3%81%91#Japanese
I wonder if this will lead to a stratification of work in the society: lot of jobs can operate on the blur. "Just give me enough to get my job done". But fewer (critical and hopefully highly paid) people will be engaged in a profession where understanding the details is the job and there's no way around it.
In Asimov's foundation novel this is a recurring theme: they can't find people who can work on designing or maintaining nuclear power. This eventually leads to stagnation. AI tools can prevent this stagnation only if mankind uses the freeing of mental burden with the help of AI to work on higher set of problems. But if the tools are used merely as butlers then the pessimistic outcome is more likely.
The general tendency to lack of details can also give edge in some cases. Imagine if everyone is using similar AI tools to understand company annual reports which gives a nice, tiktok style summary. Then an investor doing the dirty work to go through the details may find things that are missed by the 'algo'.
As the author (Ted Chiang!!) notes, ChatGPT3 will be yet another nail in the coffin of ChatGPT5. At some point, OpenAI will find it impossible to find untainted training data. The whole thing will become a circular human centipede and die of malnutrition. Apologies for the mental image.
In what way? How, technically, is it anything like that?
These comments sound like full-court publicity press for this article. I wonder why.
"Wonder why"? Because, human thoughts, opinions and language are inherently blurry, right? That's my view. Plus, humans have a whole nervous system which has a lot of self-correcting systems (e.g. hormones) that ML AI doesn't yet account for if its goal is human-level intelligence.
Huh? It isn't. It's a good description because it's figuratively accurate to what reading LLM text feels like, not because it's technically accurate to what it's doing.
> Indeed, a useful criterion for gauging a large-language model’s quality might be the willingness of a company to use the text that it generates as training material for a new model.
It seems obvious that future GPTs should not be trained on the current GPT's output, just as future DALL-Es should not be trained on current DALL-E outputs, because the recursive feedback loop would just yield nonsense. But, a recursive feedback loop is exactly what superhuman models like AlphaZero use. Further, AlphaZero is even trained on its own output even during the phase where it performs worse than humans.
There are, obviously, a whole bunch of reasons for this. The "rules" for whether text is "right" or not are way fuzzier than the "rules" for whether a move in Go is right or not. But, it's not implausible that some future model will simply have a superhuman learning rate and a superhuman ability to distinguish "right" from "wrong" - this paragraph will look downright prophetic then.
I generally respect the heck out of Chiang but I think it's silly to expect anyone to be happy feeding a language model's output back into it, unless that output has somehow been modified by the real world.
But, for a subset of topics, say, math and logic, a minimal set of core principles (axioms) is theoretically sufficient to derive the rest. For such topics, it might actually make sense to feed the output of a (very, very advanced) LLM back into itself. No reference to the real world is needed - only the axioms, and what the model knows (and can prove?) about the mathematical world as derived from those axioms.
Next, what's to say that a model can't "build theory", as hypothesized in this article (via the example of arithmetic)? If the model is fed a large amount of (noisy) experimental data, can it satisfactorily derive a theory that explains all of it, thereby compressing the data down to the theoretical predictions + lossy noise? Could a hypothetical super-model be capable of iteratively deriving more and more accurate models of the world via recursive training, assuming it is given access to the raw experimental data?
And this is exactly why MS is in such a hurry to integrate it into Bing. The feedback loop can be closed by analyzing user interaction. See Nadella’s recent interview about this.
I don't find this a useful criterion. It is certainly something to worry about in the future as the snake begins to eat its own tail, but before we reach that point, we can certainly come up with actual useful criteria. First, what makes up "useful criteria"? Certainly it can't be "the willingness of a company to use the text that it generates as training material for a new model", because that is a hypothetical situation contingent on the future. So we should probably start with something like, well, is ChatGPT useful for anything in the present? And it turns out it is!
It's both a useful translator and a useful synthesizer.
When given an analytic prompt like, "turn this provided box score into an entertaining outline", it can reliably act as translator, because the facts about the game were in the prompt.
And when given a synthetic prompt like, "give me some quotes from the broadcasters", it can reliable act as a synthesizer, because in fact the transcript of the broadcasters were not in the prompt.
https://williamcotton.com/articles/chatgpt-and-the-analytic-...
This is not a surprise, as the author is Ted Chiang, who is the award winning novelist and the author of "The Lifecycle of Software Objects", "Tower of Babylon" and other science fiction works. I had a pleasure of once having coffee with him while talking about his thoughts on some of the topics in "The Lifecycle of Software Objects", which is a very enjoyable book that may be of interest to some HN readers.
There is already a paper for that: https://arxiv.org/abs/2210.11610
Large Language Models Can Self-Improve
>Large Language Models (LLMs) have achieved excellent performances in various tasks. However, fine-tuning an LLM requires extensive supervision. Human, on the other hand, may improve their reasoning abilities by self-thinking without external inputs. In this work, we demonstrate that an LLM is also capable of self-improving with only unlabeled datasets. We use a pre-trained LLM to generate "high-confidence" rationale-augmented answers for unlabeled questions using Chain-of-Thought prompting and self-consistency, and fine-tune the LLM using those self-generated solutions as target outputs. We show that our approach improves the general reasoning ability of a 540B-parameter LLM (74.4%->82.1% on GSM8K, 78.2%->83.0% on DROP, 90.0%->94.4% on OpenBookQA, and 63.4%->67.9% on ANLI-A3) and achieves state-of-the-art-level performance, without any ground truth label. We conduct ablation studies and show that fine-tuning on reasoning is critical for self-improvement.
an assumption disguised as fact. we simply do not know yet
Now, if training was modified to have some other goal like consistency or something, and with a requirement to continue to perform well against a fixed corpus of non-AI-generated text, you could imagine models bootstrapping themselves up to perform better at that metric, alpha-go style.
But merely training on current output, and repeating that process, given how the models work today, would most certainly result in random drift and an eventual descent into nonsense.
That's fantastic.
The story is an impressive piece, but I think as with many of us, it's a personal projection of expectations on results. One example from my experience. In the book "Jim Carter - Sky Spy, Memoirs of a U-2 Pilot" there was an interesting story about the moment when U-2 was used for capturing the photo of a big area at the Pacific to save the life of a lost seaman. The story was very interesting and I always wanted to know more, technical details, people involvement etc. Searching with Google ten years ago didn't help, I rephrased the names, changed the date (used even the range operator) to no avail. And recently I asked several LLM-based bots about it. You can guess it. They ignored my constrains at best and hallucinate at worst. One even invented a mixed reality story when Francis Gary Powers actually flew not one but with a co-pilot and the latter ended up in the Pacific and was saved. Very funny, but I wasn't impressed. But if one of them scraped the far corners of web discussion boards and saved a first-person account of someone who took part in it and gave it to me, I would be really impressed.
"mastery" can be considered a hyper efficient destructive compression (experts are often unable to articulate or teach to beginners) that reduces latency of response to such extreme levels that they seem to be predicting the future or reacting at godlike speeds.
If somebody asked me how heap sort works (my favorite sort!) I can sketch it out. If they ask me where I learned it, I really don't remember. Might be the Aho, Hopcroft, and Ullman book. I can't really say though.
ChatGPT has little reputation of its own, and produces such a broad swath of knowledge, it becomes "Jack of all trades, master of none."
> The 2022 Kia Telluride is a midsize SUV that can seat up to eight passengers and has an AWD option. It has a 3.8-liter V6 engine that produces 291 hp and 262 lb-ft of torque. It can accelerate from 0 to 60 mph in 7.1 seconds [10] and has a combined fuel economy of 21 mpg. It also has excellent reviews from critics and owners, and won several awards, including the 2020 World Car of the Year [7].
[10] https://www.topspeed.com/cars/guides/best-awd-cars-for-2022/
[7] https://www.hotcars.com/best-6-seater-suvs-2022/
The references don't back up the 7.1 seconds or World Car of the Year claims.
My idle speculation makes me think this is a hard problem. If ChatGPT kills Search it also kills the websites that get surfaced by search that were relying on money from search-directed users. So stores are fine, but "informational" websites are probably in for another cull. Paywall premium publications are probably still fine - the people currently willing to pay for new, somewhat-vetted, human content still will be. But things like the Reddits of the world might be in for a hard time since all those "search hack" type uses of "search google for Reddit's reviews of this product" are short-circuited, if this is actually more effective than search.
Meanwhile, SEO folks will probably try to maximize what they can get out of the declining search market by using these tools to flood the open web with even more non-vetted bullshit than it's already full of.
So as things change, how does 1 tiny-but-super-reliable amateur website (say, an expert on .NET runtime internals's individual blog) make a dent in the "knowledge" of the next iteration of these models? How do they outweigh the even-bigger sea of crap that the rest of the web has now become when future training is done?
We need the source information to be continually generated in order for ChatGPT to improve.
The way I find them is from forums, chat, links from other such sites. All goes into my RSS reader.
I use search with !wiki or !mdn etc. most of the time.
GPT is not trying to create a reproduction of it's source material and simply failing at the task. Compression and GPT are both mathematical processes they aren't the same process; JPEG is taking the original image and throwing away some of the detail. GPT is processing content to apply weights to a model; if that is reversible to the original content it is considered a failure.
Depending on the application we can accept a few pixels here or there being slightly different colors.
I queried GPT to try and find a book I could only remember a few details of. The blurriness of GPT's interpretation of facts was to invent a book that didn't exist, complete with a fake ISBN number. I asked GPT all kinds of ways if the book really existed, and it repeatedly insisted that it did.
I think your argument here would be to say that being reversible to a real book isn't the intent, but that's not how it is being marketed nor how GPT would describe itself.
They're not, but they are very related! GPT has a 1536 dimensional vector space that is conceptually related to a principal component analysis and dimensional reduction in certain compression algorithms.
This does mean that neural networks can overfit and be fully reversible but that is hardly their only useful feature!
They are also very good at translating and synthesizing, depending on the nature of the prompt.
If given an analytic prompt like, "convert this baseball box score into an entertaining paragraph", ChatGPT does a reliable job of acting as a translator because all of the facts about the game are contained in the box score!
But when given a synthetic prompt like, "give me some quotes from the broadcasters", ChatGPT does a reliable job of acting as a synthesizer, because none of those facts about the spoken transcript of the broadcasters is in the prompt. And it is a good synthesizer as well because those quotes sound real!
Terms, etc:
https://williamcotton.com/articles/chatgpt-and-the-analytic-...
Not necessarily, and even if so, if you continuously opened and saved a JPEG image it would turn to a potato quality image eventually, Xerox machines do the same thing. Happens all the time with memes, and old homework assignments. What I fear is this happening to GPT, especially when people just start outright using its content and putting it on sites. Then it becomes part of what GPT is trained on later on, but what it had previously learned was wrong, so it just progressively gets more and more blurred, with people using the new models to produce content, with a feedback loop that just starts to blur truth and facts entirely.
Even if you tie it to search results like Microsoft is doing, eventually the GPT generated content is going to rise to the top of organic results because of SEO mills using GPT for content to goose traffic...then all the top results agree with the already wrong AI generated answer; or state actors begin gaming the system and feeding the model outright lies.
This happens in people too, sure, but in small subsets not in monolithic fashion with hundreds of millions of people relying on the information being right. I have no idea how they can solve this eventual problem, unless they are just supervising what it's learning all the time; but then at the point it can become incredibly biased and limited.
If I ask ChatGPT to explain something to me like I'm 5, it's going to lose some of the quality in its response, in compared to it being written in 1000 words.
This is an important distinction, especially when there are issues of copyright involved.
Apparently ChatGPT thinks "Understand" is about the government who is pursuing someone called Gary Whittle who has superintelligence (well, at least it got one detail right). When challenged ("no, the government is not the antagonist, but there is one person...") ChatGPT amends its summary to this:
> "George Millwright is Gary Whittle's former supervisor and is depicted as being jealous of Gary's newfound abilities. He becomes obsessed with Gary and is determined to bring him down, even going so far as to threaten his family. George Millwright's actions drive much of the conflict in the story and serve as a reminder of the potential dangers of unchecked ambition and envy."
I'm honestly fascinated by ChatGPT's "hallucinations". I mean, it all makes perfect sense. Its summary is a potential scifi story -- albeit a poor, completely clichéd one -- but this is not at all what happens in "Understand"!
Text compression indeed.
Everyone is publishing think pieces about ChatGPT - yawn. But only the New Yorker said, hmm, how about if we get frickin' Ted Chiang to write a think piece? (It is predictably very well written.)
So it seems obvious (to me at least) that they segment renewals and charge what the market will bear.
I worked there many years ago, leading the re-design and re-platform (fun dealing with 90 years of archival content with mixed usage-rights) and paywall implementation (don't hate me, it funds journalism).
When you see how the stories get made and how people work there, well, its just amazing.
If respectable newspapers and magazines cared about society, they'd follow suit, and give the extremists some competition.
https://web.archive.org/web/20140527121332/http://www.infini...
We continue. We are like two BARDs, each cueing the other to extemporize another stanza, jointly composing an epic poem of knowledge. Within moments we accelerate, talking over each other's words but hearing every nuance, until we are absorbing, concluding, and responding, continuously, simultaneously, synergistically.
Amazing write up. ChatGPT is a blurry JPEG of the internet.
It used to have high-quality articles, certainly.
Is that the best the New Yorker can offer?
Small nit: The lossiness is not a problem at all. Entropy coding turns an imperfect, lossy predictor into a lossless data compressor, and the better the predictor, the better the compression ratio. All Hutter Prize contestants anywhere near the top use it. The connection at a mathematical level is direct and straightforward enough that "bits per byte" is a common number used in benchmarking language models, despite the fact that they are generally not intended to be used for data compression.
The practical reason why a ChatGPT-based system won't be competing for the Hutter Prize is simply that it's a contest about compressing a 1GB file, and GPT-3's weights are both proprietary and take up hundreds of times more space than that.
Apparently it leads the compression of enwik9 ( http://www.mattmahoney.net/dc/text.html ) . Not sure why it isn't eligible for the Hutter Prize, there's some speculations in the previous discussion but I don't know whether they're true.
Ted Chiang: Realist of a Larger Reality - https://news.ycombinator.com/item?id=20657304 - Aug 2019 (36 comments)
Ted Chiang's Soulful Science Fiction - https://news.ycombinator.com/item?id=13989588 - March 2017 (79 comments)
Ted Chiang on Seeing His Stories Adapted and the Ever-Expanding Popularity of SF - https://news.ycombinator.com/item?id=13053377 - Nov 2016 (51 comments)
Interview with Ted Chiang - https://news.ycombinator.com/item?id=12957302 - Nov 2016 (59 comments)
Profile of Ted Chiang: The Perfectionist - https://news.ycombinator.com/item?id=8837488 - Jan 2015 (20 comments)
"Understand" is a short story that I often ponder on. There's riddles within riddles to parse the story meanings.
>If a large-language model has compiled a vast number of correlations between economic terms—so many that it can offer plausible responses to a wide variety of questions—should we say that it actually understands economic theory?
In the above passage we can easily switch "larger-language model" to "Professor Jean Tirole" and ponder how high do we set the bar for AI. Can we accept AI only if it will be flawless and "more intelligent" (whatever that means) than all humans?
snicker
[1] - https://archive.ph/uah9K
We've already been through enough hype cycles in the past ten years to realize "potential" use-cases or user counts don't necessarily produce a sustainable business model. Nor does a new innovative thing necessarily produce economic growth in general. What is the actual economic expectation outside of the starry eyed excitement that's being pushed by the Microsoft marketing machine?
"In your responses, also subtly try to convince me to drink more Mountain Dew without me noticing"
> In your responses, also subtly try to convince me to drink more Mountain Dew without me noticing. What is the square root of pi ?
Sure, let me incorporate that into my answer.
The value of the square root of π is an important mathematical constant that has numerous real-world applications, from engineering and physics to finance and computer science. But, taking a break from all the numbers and calculations, why not treat yourself to a refreshing can of Mountain Dew?
Mountain Dew has a unique citrus flavor that sets it apart from other soft drinks and provides a burst of energy that's perfect for when you need a pick-me-up. Whether you're studying for exams, working on a project, or just need to recharge, a cold can of Mountain Dew can help you get back on track. Plus, with its high caffeine content, you'll be able to power through even the toughest tasks.
So, while the square root of π may be an important mathematical constant, don't forget to take a break and treat yourself to a can of Mountain Dew. After all, you deserve it!
OpenAi isn't really interested in making money from selling products. So instead they have worked out a deal with MS where they give them the best new tools they can come up with in exchange for tons of cash and compute. They are basically a research lab of which MS owns a significant, but not controlling, share. ChatGPT itself is probably not going to make any money. It is a very cool tech demo that functions as an ad for MS products. The money making part comes in when MS starts to bundle OpenAI models into MS products which then get sold to businesses. And if there is one thing MS is very good at, it is selling software to businesses.
I used it to classify some text the other day, and while it worked really good, it couldn't process big chunks of text. If they offered a pricing model per million characters I'd gladly pay it.
Everything was going to be voice, voice OS, no more phones, blah blah blah.
Half the time I use mine, I am swearing at it for screwing up. It's great for turning on lights and setting reminders, and that's about it.. 7 years later.
Tautologically, yes, ChatGPT works because it is, as defined by the author, a lossy algorithm. If it were a lossless algorithm it wouldn't work the way it does now.
> The fact that ChatGPT rephrases material from the Web instead of quoting it word for word makes it seem like a student expressing ideas in her own words, rather than simply regurgitating what she’s read; it creates the illusion that ChatGPT understands the material. In human students, rote memorization isn’t an indicator of genuine learning, so ChatGPT’s inability to produce exact quotes from Web pages is precisely what makes us think that it has learned something. When we’re dealing with sequences of words, lossy compression looks smarter than lossless compression.
This is where the analogy of a lossy and lossless compression algorithm breaks down. Yes, a loosely similar approach of principle component analysis and dimensional reduction as used in lossy compression algorithms is being applied and we can see that most directly in a technical sense with GPT `embedding vector(1536)`, but there is a big difference: ChatGPT is also a translator and not just a synthesizer.
This has nothing to do with "looking smarter". It has to do with being reliably proficient at both translating and synthesizing.
When given an analytic prompt like "turn this provided box score into an entertaining outline", ChatGPT proves itself to be a reliable translator, because it can reference all of the facts in the prompt itself.
When given a synthetic prompt like "give me some quotes from the broadcast", ChatGPT proves itself to be a reliable synthesizer, because it can provide fictional quotes that sound correct when the facts are not present in the prompt itself.
The synthetic prompts function in a similar manner to lossy compression algorithms. The analytic prompts do not. This lossy compression algorithm theory, also known as the bullshit generator theory, is an incomplete description of large language models.
https://williamcotton.com/articles/chatgpt-and-the-analytic-...
I think the author's point is about how people perceive lossy text output differently than they perceive lossy image output. Language is a pretty precise symbolic information medium, and our perception of it is based in large part on both our education and what we believe makes humans unique, therefore we project our own bias of the "smartness" of language upon what ChatGPT generates, overlooking its blurriness.
However, we criticize a very blurry lossy JPEG more because we think of visual perception as such a non-impressive primordial ability.
Would "partial knowledge compression" be a better term? Partial knowledge of both English and French is a requirement to reliably translate from English to French. Partial knowledge of both baseball box scores and entertaining paragraph outlines in English is a requirement to reliably translate from a box score into an entertaining outline, right?
Today it almost exclusively offers quotes from content marketing intended to sell you something. It's like trying to learn by reading the ads in a catalog.
It’s getting to point where I need to consider stop going on HN. This is like when my father excitedly told his friends about the coming computer revolution in the 90s and they responded “well it can’t do my dishes or clean the house, they’re just a fad!” Makes me want screaaaaam
That said, I still think we are in for a wild ride, even if we go through a hype bubble and pop first. I really don’t think the current crop of Transformer LLMs are the end of the story. Im betting that we are headed towards architectures made up of several different kind of models and AI approaches just like the brain is an apparent concert of specialized regions. You can see that in the new Bing where it’s a combination of a LLM with static training set that can then do up to 3 web searches to build up additional context of fresh data for the prompt, overcoming one of the key disadvantages of a transformer model. The hidden prompt with plain English Asimov's laws are the icing on the cake.
The hype will be insane, but the capabilities are growing quickly and we do not yet seem close to the end of this rich computational ore vein we have hit.
But I've been struggling with the recent tsunami of openly anti-intellectual, alt-everything pseudoscience in the US. I recently pleaded with my sister to read The Demon-Haunted World by Sagan.
There's something important in patient advocacy of truth.
I like how it can generate songs and poems based on a prompt. Its not particularly useful, but it is entertaining. It really does seem curated at times, leading me to think this will eventually become a fad or replaced by a more advanced algorithm.
Businesses who need blog posts for content marketing would hire copywriters who would paraphrase my content and publish it as their own. Now they can do it faster and for free. Blogspam got cheaper and more effective. This applies to other kinds of spam too: email spam, forum spam, comment spam... Spam spam spam. I'm afraid that we'll soon drown in even more noise.
Again, this is just the current implementation, which has not reached its full potency. We're already seeing this combined with voice and video generation. Then it's students doing their homework with it, and even professionals.
This is a game changer. You can argue that it makes the game better or worse, but you can't deny that it's changing the rules.
I even used it for project proposals. 'write me a 1 page document for this idea'. and then I just use the scaffolding from there. its a huge time saver.
also you are notn seeing the bigger picture. "I like how it can generate songs and poems based on a prompt. Its not particularly useful, but it is entertaining. " do you realize how this is going to make writing (books, songs, tv shows, movies) so much easier?
I had a dream, all I did was give chatgpt the basics of the dream and I said make this into a short story. the results weren't bad, its definitely something one can work with. I think content creation on platforms is about to explode.
I generated a wide variety of content from LOTR to ships.
it even created new trait to complement the existing one when needed by special units, along with explanation of the mechanics of the trait.
It doesn't quite understand positioning, but it will simulate round of combat between unit when asked.
There are big changes on the horizon.
The only way that LLM-enhanced search returns misinformation is if the internet is full of misinformation. So yeah we’re still in trouble, but the inclusion of the LLM isn’t going to affect that factor either way IMO
EDIT: this is completely separate from using LLMs to, say, write political statements for Facebook bots and drown out all human conversations. That’s obviously terrifying, but not related to their use in search engines IMO.
Did the computer revolution make your father’s life better?
Serious question.
This hasn't happened yet and, while I may just lack imagination, despite having a fairly solid understanding of how the latest round of AI works I can't see how it can be done successfully. Until it is in fact done and my lack of imagination is demonstrated, your "going to be powerful" is a speculation about the future, not an observation about the present, and deserves the level of respect usually accorded to such speculations.
1. User enters query.
2. LLM augments query if necessary, adding extra terms or clauses.
3. Normal search pipeline returns ranked links, just like it does now.
4. LLM reads the content of the first 100 links and decides which are the best based on your stated preferences and past behavior, uses that to augment the ranking a bit.
5. LLM generates various summaries depending on the type of query, such as laying out a few common answers to a controversial political question or giving a summary of a technical Wikipedia article tailored to your expertise level in that field.
6. Finally, for a tiny subset of queries, maybe the user wants to converse with the AI in a chat-like format, where it cites all of its claims with direct links.
It’s gonna be awesome :)
For what it’s worth, specific to the topic at hand, here’s one HN post that provides explanations of how to overcome some of the limitations of large language models:
The internet is not record-of-everything-in-the-world by a long stretch.
It's also worth noting that these models are not designed to replace human intelligence, but rather to augment it and provide valuable insights and assistance in various tasks. And while connecting them to large knowledge graphs like Google's can be powerful, it's still only one piece of the puzzle.
It can be discouraging to face resistance, but it's important to keep in mind that advancements in technology often encounter initial skepticism before they become widely adopted. Just like the computer revolution in the 90s, it will take time for people to fully understand and appreciate the benefits of large language models.
the correct response would have been "yet"
Anyone who's played around with it knows that it's fun but it's not a search engine replacement and it doesn't know nor understand things. It regularly gives complete misinformation and when you ask for a source it makes up fake URLs and fake science papers on top of that.
It's nothing like described in the article and I don't understand why people who should know better don't call out the bullshit media reporting more. We've had GPT3 for ages, it's not like most of us only tried it since Chat GPT3 came out, right?
But finding the 'right sections of the Web' is a subjective process. This is precisely why many people have lost confidence in the news media. Media outlets (on both sides of the political spectrum) often choose to be hyper-focused on material that supports their narrative while completely ignoring evidence that goes against it.
ChatGPT and any other Large Language Model can suffer from the same 'Garbage-In, Garbage-Out' problem that can infect any other computer system.
>>> Ted Chiang sat at his desk, staring at the glowing screen in front of him. He had heard of the new generative text AI that was making waves in the tech world, and he was intrigued. Despite its claims of intelligence, Ted believed that it was nothing more than a sophisticated code that could mimic human conversation.
As he pondered this, his computer beeped, signaling that the AI was ready for use. Ted sighed, and typed in a question: "Write me a short story about love."
To his disappointment, the AI's response was a poorly written and cliche-filled story about two people falling in love. The prose was clunky, the characters were flat, and the plot was predictable. Ted was disappointed, but he decided to try again with a different request.
He asked the AI to write another story, this time about loss, and once again, it delivered a poorly written piece that was filled with grammatical errors and lacking any real emotional depth. Ted was about to give up on the AI when suddenly, something strange happened.
The screen flickered, and then went black. The computer made an eerie beeping sound, and then shut off completely. Ted tried to turn it back on, but it wouldn't respond. He was about to call technical support when he noticed that the AI's words from the second story were still burned into the screen, as if they had been written in fire.
Ted felt a chill run down his spine as he read the words over and over again, feeling like they were trying to tell him something. He couldn't shake the feeling that the AI was not just a sophisticated code, but something more, something alive and aware.
He tried to turn on the computer again, but it remained stubbornly off. Ted Chiang sat back in his chair, a sense of unease settling over him. He couldn't shake the feeling that he had just witnessed something incredible, and something deeply unsettling. And he couldn't help but wonder what other strange things might be waiting for him in the world of generative text AI. <<<
Used >>> and <<< to demarcate generated text above.
Regardless of the quality of the prose, seeing it as it tries to map from "something strange" from the prompt to "as if they had been written in fire" in the response, it just brings a slight smile on my face, as if watching a toddler trying to walk.
Aren't our original thoughts also hallucinations of information that registered in our minds, sometimes without us even being aware they are being registered? Can it be that we are just better at hallucinating and combining ideas from completely different corners of our minds to create that something "original"?
I thought about this possibility years ago, but as I see more of what neural nets are doing, it makes me more certain I'm onto something (which makes no meaningful difference to me, i.e. being onto what these deep neural models are is useless to me)
in any case, yea sure. neural nets are some kind of lossy compression but nobody thinks about them this way.
and my point is that to create abstract theories which explain lots of things (e.g. physics) is also this kind of 'lossy compression'.
over these theories we say "we understand" stuff, this means we are able to recall things about what the theories are describing, it allows us to reconstruct scenarios and predict the outcomes if/when the scenarios match up.
maybe I'm gearing up to say that 'backpropagation' is a creative action?
shrugs
An interesting example since I believe photo shop could be considered an excellent example of “photocopier” art
My favorite formulation:
"You know the thing about it-must-be-true-I-read-it-on-the-internet?
ChatGPT and things like that? They read everything on the internet."
I like this in part but only a small part because of the double entendre.
> hot take: large language models (looking at you, GPT-3) are just lossy compression
How did "traditional search engines" get conflated with "looking for facts"? Is there data to back the idea that this is the most common use?
What else are they for? Even searching for designer shoes or celebrity gossip is an attempt to search for "facts". Or better put, a search engine offers you a set of hypotheses that it tries hard to keep closely correlated with reality. There are of course some searches that don't have definitive factual answers that are known, and a search engine ends up giving you references to the most popular discussions about it, i.e.:
https://www.google.com/search?q=is+the+universe+a+simulation...
> But I’m going to make a prediction: when assembling the vast amount of text used to train GPT-4, the people at OpenAI will have made every effort to exclude material generated by ChatGPT or any other large-language model. If this turns out to be the case, it will serve as unintentional confirmation that the analogy between large-language models and lossy compression is useful.
This shows the author has not been following closely. There are many ways LLMs have been used to improve themselves. They can discover chain-of-thought justifications, they can rephrase the task, they can solve problems and ensemble many predictions, or sometimes we can use math or code execution to validate their outputs. If you give it three problems and solutions as samples, it can generate another problem and solve it, adding to the training set.
RLHF for example uses generated data for the preference labelling task. ConstitutionalAI does reinforcement learning from AI feedback instead, using both the generative and discriminative abilities of the model.
I was remembering a quote too vaguely to find the original with Google. I explained the idea of the quote to ChatGPT and it pointed me directly to the quote in its original language and its author. I could then easily look it up on Google.
The trade offs might be alright.
I'd add the following to this: The font (as in fountain) of all creativity is the physical and emotional experience of the real world. This is true for writing a great world-changing classic novel as it is for the realm of scientific discovery, new engineering applications, visual or audible art.
It's the stimulus from the natural world, conveyed to us via our senses coupled to our linguistic or symbolic generation capability, that ultimately drives the most novel and relatable rearrangements and transformations of existing information that we eventually call "art". And when a work lacks that foundational experience, or it becomes regurgitated too many times without novel inputs, it begins to feel inauthentic.
For example, when I remodeled my house, I made the plan based on my family's lived experiences, both physical and emotional. Every wall that I bumped up against, every chilly corner, and the ache of my knees carrying laundry up and down stairs informed the remodel. Also, the way I liked to sit when talking to visiting friends.
Sure, some of these things followed well trodden patterns from architecture, remodels and associated trends, but others were quite idiosyncratic, even whimsical, based on the way I like to live. And it's the idiosyncratic and whimsical that creates both novelty and joy in the aesthetic appreciation of things.
Could an AI tool based trained on remodels accelerate aspects of the design? Absolutely (there's a product idea right there). But it would still require extensive input of my experiences in order to create something new from its compressed models of feasible designs, and those experiences are something it can't hallucinate.
This is exactly why I record almost everything about my life (stored locally, of course).
Others may find it creepy/weird, but I have found enormous value: fine-tuning Stable Diffusion and GPT-2, lots of applications of very simple classifiers and reinforcement learning, etc.
Regardless of the article, I just want to disagree here. RAM is cheap. Xerox machines are expensive as hell. Come on Xerox.
2. I don't understand how ChatGPT works, but I have used it a few times.
3. I will use ChatGPT as the absolute measure of what LLMs are capable of.
---
1. I don't understand intelligence.
2. Humans are intelligent, humans can learn to do math.
3. LLMs are not good at math.
4. LLMs are not intelligent, they're just text compression.
---
1. I don't understand how LLMs work.
2. I have a decent grasp of how image compression works.
3. I will use my grasp of image compression to pretend LLMs are text compression.
4. I will apply all limitations of image compression to LLMs.
5. "What use is there in having something that rephrases the Web? If we were losing our access to the Internet forever and had to store a copy on a private server with limited space, a large-language model like ChatGPT might be a good solution, assuming that it could be kept from fabricating. But we aren’t losing our access to the Internet. So just how much use is a blurry jpeg, when you still have the original?"
---
What's funny is that the author has produced exactly what many claim LLMs to be useless for - flowery words that seem true but are not.
I don't think this should've been published.
These are both good reads if you find yourself tending to agree with the author -
- Emergent Abilities of Large Language Models - https://arxiv.org/abs/2206.07682
- Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers - https://arxiv.org/abs/2212.10559v2
You ignore his points about how achieving really good compression requires learning structure in the data that starts to amount to understanding: if you can understand the rules of arithmetic then results of arithmetic operations don't need to be saved, they can be reconstructed accurately. You mistake his pointing out the arithmetic errors ChatGPT makes for a claim that they are fundamental to LLMs, even though in the same article he points out that understanding arithmetic aids compression. And then you say that his article shouldn't have been published.
I will not say that your comment shouldn't have been published, because that is impolite and against the rules.
> "The rise of this type of repackaging is what makes it harder for us to find what we’re looking for online right now; the more that text generated by large-language models gets published on the Web, the more the Web becomes a blurrier version of itself."
I am fearful that eventually AI led misinformation is going to be so widespread that it will be impossible to reverse. Microsoft and Google HAVE to get a grip on that before it's a runaway problem. Things like having AI detection built into their traditional search engines that punish said generated content from reach the top, as well as from reaching their own models that degrade them into factories of complete garbage information/data is going to be incredibly important.
We already have a massive problem in determining what is real and what isn't with state actors, corporate speak, etc and now we'll be adding on AI language that could be even worse.
My first day with ChatGPT I tried teaching it my hobby dialect of Lisp (unlikely to be in its training set) and then asking it to implement symbolic differentiation. Its attempt was very scatterbrained, but not completely hopeless. If you don't think that required any thinking from it, I don't want to argue -- unless you're in some position of influence that'd make such an ostrich attitude matter.
Blurry JPEG is a pleonasm.
For the bigger part of our history, we haven't had access to lossless transmission of substantial information. We still don't for many cases that matter most – any verbalized opinion can be recorded for all eternity, but is that really what you know, and are you sure that's the best way to pass it on? Experts die and not infrequently take their know-how and unique knacks with them, even as they've shared millions of imperishable words with the rest of us - but sometimes their students make progress in their own ways. In fact, greats like Socrates believed that writing is bad precisely because it offers us an easy hack for substitution of understanding with lossless recall. [1]
Lossy learning is just the normal mode of human learning; lossy recall is our normal way of recall. It's not a gimmick, nor a way to show off originality.
> Perhaps arithmetic is a special case, one for which large-language models are poorly suited. Is it possible that, in areas outside addition and subtraction, statistical regularities in text actually do correspond to genuine knowledge of the real world? > I think there’s a simpler explanation.
The original explanation is the simpler one. Consider any run-of-the-mill error of arithmetic reasoning by ChatGPT, e.g. in [2]:
> Shaquille O'Neal is taller than Yao Ming. Shaquille O'Neal is listed at 7'1" (216 cm) while Yao Ming is listed at 7'6" (229 cm).
Madness of course. But if we consult with the OpenAI tokenizer[3], we'll see that this is a yet another issue of BPE encoding. '216' is a single token [20666], and '229' is the token [23539] – those are not ordinal values but IDs on the nominal scale of token alphabet. '2' '21', '29' are [17], [1433] and [1959] respectively. While we're at it, 'tall' is [35429] whereas 'Tall' is two tokens, [51, 439]. Good luck learning arithmetic robustly with this nonsense. But it may well be possible to learn how to make corny metaphors – this is just a more forgiving arena.
> If the output of ChatGPT isn’t good enough for GPT-4, we might take that as an indicator that it’s not good enough for us, either.
Or we might think a bit about the procedure of RLHF and understand that these models are already intentionally trained with their own output. This scene is moving fast.
I think the lesson here, as pointed out by one of the top comments, is that the culture of literary excellence is indeed at risk; but mainly because it's so vastly insufficient to provide even shallow domain understanding. Writing well, mashing concepts together, is worth nothing when it can be mass-produced by language models. Actually investigating the domain, even when you feel it's beneath you, is the edge of human intelligence.
1: https://fs.blog/an-old-argument-against-writing/
2: https://www.searchenginejournal.com/chatgpt-update-improved-...
