[HN Gopher] OpenAI API pricing update FAQ
___________________________________________________________________
OpenAI API pricing update FAQ
Author : thorum
Score : 65 points
Date : 2022-08-22 17:32 UTC (5 hours ago)
(HTM) web link (help.openai.com)
(TXT) w3m dump (help.openai.com)
| keepquestioning wrote:
| What are people actually using GPT-3 for?
| aaroninsf wrote:
| I can comment that a friend teaching college philosophy said
| his department is eliminating papers at the undergraduate
| level,
|
| because it is now too easy to generate-then-polish papers at
| that level.
|
| They're too good in other words: better than baseline even. And
| when touched up by a student who's putting in a modest effort,
| are disruptively better.
| paulryanrogers wrote:
| Could that have something to do with the subjective nature of
| philosophy? (IANAP)
| elefanten wrote:
| Probably has more to do with how slowly the field evolves
| (esp. wrt what undergrads are learning)... so I imagine
| there's a huge training corpus for what is ultimately a
| very limited number of meaningful assignments to give.
| nicksrose7224 wrote:
| I am using it for a little project to make deciding between
| Airbnbs easier: https://www.tripwise.me/
|
| You basically just enter in the Airbnb URLs you're considering,
| and it'll use GPT-3 to scrape through the reviews in order to
| find anything negative or positive people are saying about the
| listings.
|
| You can also ask any question you want at all, and it'll return
| answers (if people have mentioned it in their reviews). For
| example "Is the air conditioning loud?"
|
| I would love to hear what others are using GPT-3 for!
| breck wrote:
| 1. Generating text content for websites and blogs
|
| 2. Translating documents from one language to another
|
| 3. Writing e-mails, letters, and other forms of correspondence
|
| 4. Crafting resumes and cover letters
|
| 5. Writing marketing materials, such as brochures and flyers
|
| 6. Responding to comments on HN.
|
| (I added the last one)
| candiddevmike wrote:
| None of these usecases are things I want to be on the
| receiving end of. Ick.
| carvking wrote:
| Did gpt3 write the first 5 ones ?
| seibelj wrote:
| Is any of that actually going to be a massive industry-
| defining feature? Marketing blogs are already negative value
| to me, relying on AI to write something as important as my
| resume is a non-starter, and marketing emails already go
| straight to the trash.
|
| I'm very impressed with the AI image generation, but again,
| it replaces... stock art for blog posts?
|
| If I was a creative writer then I think the AI could help me
| with plot outlines or get over writing blocks. But otherwise
| I'm not grasping why this is going to automate some huge
| number of jobs.
| insightcheck wrote:
| > "If I was a creative writer then I think the AI could
| help me with plot outlines or get over writing blocks. But
| otherwise I'm not grasping why this is going to automate
| some huge number of jobs."
|
| Writing definitely looks like the key use case. The New
| Yorker used GPT-3 to write the concluding sentence for one
| of their articles [0], and I believe The Economist did the
| same (but for a slightly greater length; though I couldn't
| find the source just now). It's actually a bit hard to come
| up with a good conclusion, so this could save some effort
| and trouble. Separately, GPT-3 can also likely be used for
| articles about sports, especially if the purpose is to
| track changes on a scoreboard and present the changes with
| an article written in prose, versus displayed in a table.
|
| It's quite fair that marketing blogs may not be interesting
| to many readers, but they can be useful for SEO/boosting
| the search engine rankings of a website. So, a cash-
| strapped early or small company could save money from
| freelance copywriting to GPT-3 if they're not looking for
| anything fancy, and a lot of people work as freelance
| copywriters.
|
| I agree that this may not displace anyone in the high-
| end/high quality segment of copywriting, but it could
| reduce demand for content farms in the future (i.e. any
| application where low-quality copywriting written on a
| short notice is in-demand).
|
| [0] https://www.newyorker.com/magazine/2019/10/14/can-a-
| machine-...
| hda2 wrote:
| Any GPT-3-level fully-opensource models yet?
| minimaxir wrote:
| BLOOM and OPT are both GPT-3 sized models that are open source
| and similarily sized (175B parameters) but a) text generation
| is not as good as GPT-3 for whatever reason and b) getting them
| to run in a cost-effective manner is not easy and with this new
| price decrease, it may be more economical to use GPT-3 for
| deployment despite that.
| edgyquant wrote:
| Is this due to entirely to economies of scale?
| minimaxir wrote:
| Not entirely. There are _many_ ways to optimize models for
| deployment both at the software and hardware levels: some
| are public such as quantization /fusing, others are not.
| tehsauce wrote:
| Economies of scale and years of optimization, some of which
| likely have not been publicly shared.
| tehsauce wrote:
| The reason the similarly sized open source models aren't as
| good is because gpt-3 has had a 2 year head start of
| additional development and improvement. The gpt-3 that is
| available today is Much better than what was initially
| produced in 2020.
| mad_ned wrote:
| More Marshmallows!
| hcks wrote:
| I really wonder about the economics and business models of large
| models APIs, mainly because of:
|
| * large running costs due to the expensiveness of the inference
|
| * low barriers to entry: the tech behind Dalle appeared 1.5 years
| ago if I recall right and there are already a few competitors
| (Midjourney, Imagen, Stable Diffusion)
|
| * low value at the present time of the raw APIs
| vanadium1st wrote:
| Why is it still closed for users in Ukraine? Are there many other
| countries excluded, or are we the only unlucky ones?
| jacobr1 wrote:
| I'm not sure about OpenAI's internal policies, but I've worked
| for several SaaS companies that complied with Export
| Administration Regulations (EAR) to limit access to "Embargoed
| and Sanctioned Countries" which has meant CRIMEA - REGION OF
| UKRAINE, CUBA, IRAN, NORTH KOREA, and SYRIA. ITAR (defense
| related) and OFAC (finance related) both have further
| restrictions. For us, it was easier to block all of Ukraine
| rather than limit to access to Crimea in particular.
| jon_adler wrote:
| Trade compliance requirements may require embargoing occupied
| Ukrainian territories however it isn't necessarily possible to
| distinguish between occupied and unoccupied regions. Export
| controls might be applied based on geoIP with granularity at
| the country level. Unfortunately the safest position from a
| compliance perspective is to block the entire country than risk
| getting it wrong.
| mccorrinall wrote:
| Microsoft does microsoft things.
| minimaxir wrote:
| This is actually a big deal since this includes the davinci model
| everyone uses and was the biggest obstacle to cost-affordable
| deployment of GPT-3.
|
| The exemption for finetuned models is interesting: since they
| were 2x the price of the old prices, they're now 4x-6x more
| expensive than the base models. I bet that's how OpenAI _really_
| makes their money with enterprise.
| dr_dshiv wrote:
| Any good use cases for fine tuned models? I've been wanting to
| put in all my previous academic works and references and see
| how that changes things.
|
| Otherwise, I've been using a model finetuned on the complete
| works of Plato and I have really been enjoying the new
| dialogues.
| minimaxir wrote:
| I made a blog post just last week about finetuned GPT-3,
| albeit only on the lower end and not finetuning davinci:
| https://news.ycombinator.com/item?id=32471208
|
| I suspect some of the more custom "be a better writer"
| services use a finetuned davinci.
| teaearlgraycold wrote:
| CopyAI uses fine tuning extensively
| arbol wrote:
| Any chance of this making GitHub copilot cheaper?
| learndeeply wrote:
| Out of curiosity, is $10/month prohibitively expensive for you
| or other developers? Copilot is free for open source developers
| and students.
| karamanolev wrote:
| Does Copilot use GPT-3 directly? I haven't found resources on
| this, but sounds doubtful?
| simonw wrote:
| It uses Codex, which is a descendant of GPT-3:
| https://openai.com/blog/openai-codex/
| lukev wrote:
| This makes me sad. I hoped to see less use of language models in
| the wild; looks like we're heading the other direction.
|
| I was recently able to articulate to myself why I dislike
| language models like GPT-3 so much.
|
| Language is fundamentally about _communication_. I have a mental
| state, and language lets me share that some of that mental state
| with another human being. It 's quite remarkable, and the
| cornerstone for pretty much every aspect of our lives as social
| creatures.
|
| GPT-3 can generate text that's convincingly human-like; it's an
| amazing technical achievement. But (so far, anyway!) it is _just_
| that; a generator of plausible text. To borrow a philosophical
| term, there 's no "interiority" there.
|
| You can see this clearly in GPT-3's output; it is at its weakest
| when writing about the relationships between a set of concepts,
| or when trying to carry a line of thought or argument through a
| longer text. This is because there is no underlying _thing_ that
| is being communicated; no mental model or grounding concept. Just
| text, generated solely based on plausibility in a given context.
|
| So while GPT-3 is truly remarkable in its ability to generate
| _text_ , it cannot, by definition, _communicate_ (except on the
| meta level via prompt selection and output curation.)
|
| Does the world really need more words but with less
| communication?
| iLoveOncall wrote:
| > So while GPT-3 is truly remarkable in its ability to generate
| text, it cannot, by definition, communicate
|
| GPT-3 does nothing without a human inputting what it wants it
| to output. GPT-3 is as much a tool for communication as are
| sounds, words, symbols, etc.
|
| Whether it was carved in stone by a human hand or generated on
| the cloud by an AI, the intent to communicate is always coming
| from a human.
|
| If you think the text generated by GPT-3 does not carry the
| right meaning or has "no underlying _thing_ that is being
| communicated", it just means that the human behind is not using
| the tool properly. Just like sometimes you use a word that
| doesn't mean what you think it means.
| ComplexSystems wrote:
| I thought this was interesting so I literally pasted the entire
| thing into OpenAI's playground and asked DaVinci to write a
| rebuttal of your argument. Here is what it said:
|
| ---
|
| There are a few problems with LukeV's argument. First, he
| conflates the ability to generate human-like text with the
| ability to communicate. Just because GPT-3 can generate text
| that sounds like it was written by a human does not mean that
| it cannot communicate. In fact, GPT-3 is quite good at carrying
| a line of thought or argument through a longer text, as
| evidenced by the fact that it is often used by writers to
| generate ideas and outlines for their articles.
|
| Second, LukeV claims that GPT-3 is at its weakest when writing
| about the relationships between a set of concepts. However,
| this is not necessarily true. GPT-3 may not be able to generate
| text that is perfectly grammatical or that makes perfect sense,
| but it is often able to generate text that is nonetheless
| meaningful and insightful. For example, GPT-3 has been used to
| generate essays on complex topics such as the philosophy of
| mind, and these essays have been well-received by readers.
|
| Third, LukeV argues that the world does not need more words,
| but this is clearly not the case. The world needs more
| communication, and GPT-3 can help to facilitate this by
| generating text that is meaningful and insightful. In fact,
| GPT-3 is already being used by writers to generate ideas and
| outlines for their articles, and it is likely that this use
| will only increase in the future.
|
| In conclusion, LukeV's argument against GPT-3 is flawed. GPT-3
| is a valuable tool that can help to facilitate communication,
| and the world needs more communication, not less.
|
| ----
|
| I'm not sure who I agree with, but that's GPT-1's response to
| you regarding your critique of itself. Have at it!
| WithinReason wrote:
| I noticed that when GPT-3 has trouble continuing a sentence
| or create a difficult argument it relies on filler words to
| stretch out a sentence until it has no choice but to write
| something meaningful.
| reidjs wrote:
| I'm siding with GPT in this debate. GPT is a writing tool
| like MS word, grammarly, or the printing press. Its
| innovative not destructive
| stephendause wrote:
| The argument seems very poorly reasoned to me.
|
| > First, he conflates the ability to generate human-like text
| with the ability to communicate.
|
| This is incorrect. In fact, lukev does the opposite. That is
| one of the fundamental parts of his argument -- that those
| two things are different.
|
| > Second, LukeV claims that GPT-3 is at its weakest when
| writing about the relationships between a set of concepts.
| However, this is not necessarily true. GPT-3 may not be able
| to generate text that is perfectly grammatical or that makes
| perfect sense, but it is often able to generate text that is
| nonetheless meaningful and insightful. For example, GPT-3 has
| been used to generate essays on complex topics such as the
| philosophy of mind, and these essays have been well-received
| by readers.
|
| I believe this is the best paragraph of the argument, but it
| is also the most difficult to rebut because it is rather
| subjective. Whether a text is meaningful or insightful is up
| the individual reading it. I would be surprised, however, if
| experts on the philosophy of mind found the essays mentioned
| by GPT-3 to be meaningful or insightful -- as opposed to
| regurgitations of concepts that are in the texts that have
| been fed to GPT-3's model.
|
| > Third, LukeV argues that the world does not need more
| words, but this is clearly not the case. The world needs more
| communication...
|
| The presence of more words in the world does not necessarily
| entail more communication. The two concepts are fairly
| closely related but are definitely not synonymous.
|
| This doesn't necessarily mean that I agree with lukev, of
| course. I do think that GPT-3 as it currently exists should
| not be used to generate text that is meant for human
| consumption without being edited first. I can certainly see
| how it would be useful as a tool for generating an outline of
| an essay, especially with well-crafted prompts.
|
| I am of course open to more arguments and data on the subject
| =)
| AJRF wrote:
| > We have been looking forward to reducing pricing for a long
| time. Our teams have made incredible progress in making our
| models more efficient to run, which has reduced the cost it takes
| to serve them, and we are now passing these savings along to our
| customers.
|
| Nothing to do with Stable Diffusion then, no?
| tvhahn wrote:
| Why bother use a GPT-3 model when you can use the free BLOOM
| model? Large "foundation" models will become a commodity -- a
| race to the bottom.
| grej wrote:
| I have used BLOOM a little, and I struggle to get it to
| produce the same kind of output as GPT-3. Anyone have tips
| there? It often seems to not keep the right context of the
| previously generated text.
| aljungberg wrote:
| GPT-3 has been fine-tuned after release to better interpret
| prompts (see InstructGPT). Perhaps Bloom is more like the
| original GPT-3; a little more raw and requiring better
| prompt engineering?
|
| In my small amount of testing of Bloom so far it seems
| capable of advanced behaviour but it can indeed be trickier
| to coax that out. Playing with temperature and sampling
| matters for sure.
| lee101 wrote:
| Yes this move is I think forced hand by competitors like
| https://text-generator.io etc which is already 10x cheaper.
|
| If the open source community then other company's didn't follow
| along with them then we would still be being price gauged in a
| monopoly situation, hopefully same thing happens to dalle soon
| JimmyAustin wrote:
| Given that Dall-E 2's pricing hasn't changed, probably not.
| aaroninsf wrote:
| Now that StableDiffusion is released, I expect that to
| change, unless there is a (certainly ultimately doomed)
| attempt to Hold the Line.
| choppaface wrote:
| It's not just Stable Diffusion the model, but the research is
| become really actually _open_ unlike "open ai"
| cma wrote:
| Could be the GPU price crash as well (even if they use Google's
| TPUs, TPU demand would presumably go down in a GPU price
| crash).
| tomComb wrote:
| Microsoft bought control of OpenAI so I believe this would
| all be running on Azure (so would not be using Google TPU's).
| intrasight wrote:
| Honest question: What does GPT-3 add to my tookbox as a
| developer?
| ivalm wrote:
| Maybe not for a developed, but for an AI based startup:
|
| 1. Generate synthetic data that is well aligned to your needs.
| With careful prompting + ensembling + after-fact human
| filtering you can generate a lot of very particular human-like
| data that you can then used to train/etc your product.
|
| 2. Generate labels. gpt-3 can give pretty good NLU results
| through appropriate prompting. You can do multiple prompts +
| ensembling to get very good labels on free text (sentiment,
| entity linking, intent, etc).
|
| In both above use cases you can actually avoid deploying gpt-3
| as part of client facing product, but instead leverage gpt-3 to
| train smaller "on-rails" models/rules/etc.
| thorum wrote:
| GitHub Copilot is built on GPT3.
| powerhour wrote:
| I wonder if anyone has successfully used it to create library
| documentation. Obviously you'd have to tweak whatever output
| you get but can GPT-3 provide a substantial starting point?
| ianbutler wrote:
| I've used it in a previous tool to generate documentation
| from code snippets, it works out pretty well.
| moffkalast wrote:
| Yes, there are several VScode plugins for it. Not sure if
| they use GPT-3 specifically or one of the slightly smaller
| versions though.
| guipsp wrote:
| One thing to note (without commenting if this applies in this
| case or not) is that sometimes a bad starting point is worse
| than no starting point
| simonw wrote:
| We're still figuring that out. It's a really fascinating piece
| of tech, and has all kinds of non-obvious applications.
|
| I wrote about using it to explain code (and mathematical
| formulas and suchlike) a few weeks ago:
| https://simonwillison.net/2022/Jul/9/gpt-3-explain-code/
|
| I've been experimenting with using it to build a human-
| language-to-SQL tool, so that people can ask questions of their
| data "what country had the highest GDP in 2019" and it will
| turn them into the correct SQL query, given a table schema. I'm
| still iterating on this but it's shown some very promising
| initial results.
|
| I use it a lot when I need to get something small working in a
| language that I don't have day-to-day familiarity with. "Write
| a bash script that loops through every MOV file in this folder
| and extracts the audio as MP3" is a good example of that kind
| of prompt.
|
| Riley Goodside on Twitter posts weird and interesting new
| things you can do with GPT-3 on a daily basis:
| https://twitter.com/goodside/ - his instructional template
| trick was on HN the other day, it's really clever:
| https://news.ycombinator.com/item?id=32532875
| a-dub wrote:
| it's mostly just kinda like this https://youtu.be/5KMzpZjhUiQ
| dbrueck wrote:
| Is it just me, or are phrases like "3x cheaper" hard for other
| people to grok too? For some reason they always require me to
| pause and try to sort it out. Like, is the price being reduced by
| 66% or 75% or something else? What would "1x cheaper" mean?
| redox99 wrote:
| I process "3x cheaper" as "for the same money, I can get 3x the
| original amount".
|
| Which would be 33% the original price.
| [deleted]
| noja wrote:
| The problem is the word "cheaper".
|
| For the opposite word, "expensive", it all depends on the
| word before it: "as expensive" or "more expensive".
|
| "100 widgets cost $100. Unit price is $1." They are now twice
| _as_ expensive -> they now cost $200. Unit price is now $2.
|
| "100 widgets cost $100. Unit price is $1." They are now two
| times _more_ expensive -> they now cost $300. Unit price is
| now $3.
|
| But How do you do this with the word "cheap"? Does "cheaper"
| clearly mean "3x as cheap" or "3x more cheap" (which even
| sounds a bit wrong)? I guess it means "more cheap" means
| "cheaper".
|
| Better to avoid the problem and say "They are now two times
| the cost, or half the cost". Which is much clearer.
| rfiat wrote:
| > For the opposite word, "expensive", it all depends on the
| word before it: "as expensive" or "more expensive".
|
| Frustratingly, I find this isn't always true in practice.
| Lots of people use "x times as y" and "x times more y"
| interchangeably. To avoid ambiguity I try to only use the
| former in any context where precision is useful.
| noja wrote:
| True. But people also say "percentage" when they mean
| "percentage points". Once they notice the difference they
| tend to stay right.
| synu wrote:
| What would 1x cheaper mean? 100% of the original price?
| [deleted]
| mattnewton wrote:
| Yes?
| shard wrote:
| That reminds of the sign "Buy one, get one". Does that mean
| you pay for an item and you get that item, or you pay for
| an item and you get another item for free? I expect the
| meaning to the be the second one, but my brain parses it to
| be the first one.
| mattnewton wrote:
| That's because it they have left off the word "free" -
| it's just an odd shortening of the less ambiguous "buy
| one get one free", probably made by someone who is very
| familiar with seeing "buy one get one free"
| squeaky-clean wrote:
| To open.ai's credit, I don't see that text anywhere on the page
| or in the page title. The only info I see on the page about the
| price change is.
|
| > We're making our API more affordable on September 1, thanks
| to progress in making our models run more efficiently.
|
| If you visit the page the price change is pretty clear, they
| show the before and after. 1k tokens will be anywhere from 1/2
| to 1/3 the current price depending on which model you're using.
| solarkraft wrote:
| Yep, every time.
| papandada wrote:
| From my copy editing days, it's drilled into me to never write
| "n times less" -- I get that it means "1/n" and that's how I'd
| rewrite it, but yes, it's notoriously confusing, or at least
| imprecise.
| copperx wrote:
| I think it's very precise. Just multiply the last cheapness
| value times three. If last month there was a 10% discount,
| today's discount is 30%.
| papandada wrote:
| How does that apply here?
| epicide wrote:
| For me, I tend to think of "3x" and "cheaper" as separate
| operations. So "3x cheaper" sounds like you're saying
| _new_price = price - 3*price_.
|
| That (usually) makes no sense, so I assume people mean
| something else when they say it, but I never have any clue
| what. Is it a third of the original price? Is it two thirds (
| _new_price = price - price /3_)?
|
| Percentages also work this way. If I say "10% cheaper", most
| people understand that I mean the price is 90% of what it was
| previously. Although percentages get weird when increasing the
| price.
|
| e.g. if it was a flat doubling, I would say that as "200% of
| the price" ( _new_price = price*(200 /100)_).
|
| However, I take "200% _more_ expensive " to mean _new_price =
| price + price*(200 /100)_. To me, the "more" implies addition
| specifically.
| Judgmentality wrote:
| https://xkcd.com/985/
| Jensson wrote:
| People mix up these two:
|
| "Its cheaper, you get 3 times as much for the same price"
|
| "Its cheaper, it costs 66% less"
|
| Most people aren't well versed in math and just says
| something that kinda makes sense to them based on the numbers
| they know.
| JRandomHacker42 wrote:
| One of my former colleagues who was always in charge of
| publishing our team's performance testing results was a
| complete hardass on the rest of us for using proper language
| around multipliers and superlatives. It's well worth the
| clarity to avoid precisely this situation.
| kredd wrote:
| I usually read that as "new price = old price / X" where X =
| "3" in this scenario. In my head, "1x cheaper" would mean "new
| price = old price / 1", so no reduction, I guess.
| cbm-vic-20 wrote:
| 3x cheaper = (1/3)x more expensive. I suppose that also means
| when tripling the price of something we can say it's just
| (1/3)x cheaper.
| dr_dshiv wrote:
| I know what you mean. 1x cheaper would be same price. 3x
| cheaper means "the new price times 3 equals the old price."
| However this is easier than percents or fractions. 100% cheaper
| means free. Do you want something 67% cheaper, 2/3s cheaper or
| 3x cheaper?
| floxy wrote:
| >1x cheaper would be same price.
|
| Let's say you have a product for sale at $32. Then you have a
| sale to boost name recognition, and have a coupon for $32
| dollars off (limited time offer). Or equivalently, that would
| be $32 cheaper. So the net price is free ($0). $32 cheaper =
| 100% cheaper = 1x cheaper. Likewise, 25% cheaper = 25% less
| expensive, or doing the math $32 - 0.25*$32 = 0.75*$32 = $24.
| [deleted]
| dr_dshiv wrote:
| That's precisely why it's confusing, yes. You can't equate
| 100% cheaper with 1x cheaper. 99% cheaper is sensible. 200%
| cheaper is not. 2x cheaper is. I'd love a cogent reason to
| explain this convention.
| Jensson wrote:
| > I'd love a cogent reason to explain this convention.
|
| "cheaper" isn't a defined operation except for "a is
| cheaper than b".
|
| So the statements "6% cheaper" and "2 times cheaper" are
| shorts for "it is cheaper, it costs 6% less" and "it is
| cheaper, you get 2 times more for the same amount of
| money".
| floxy wrote:
| >2x cheaper is <sensible>.
|
| No, it isn't sensible, and is certainly confusing, and
| that is why you should commit to never using that
| phrasing from this day forward. It isn't like there is a
| hardship you have to overcome when using precise
| language. There are plenty of alternative ways to state
| the desired objective that are clear and unambiguous:
| - The product is now half-priced! - The item costs
| half as much! - The unit comes with a 50% discount!
| ckosidows wrote:
| I think 1x is baseline. If you can buy two for the
| original price, it's 2x cheaper. 10 for the same price?
| 10x cheaper.
|
| The parent you're replying to seems to have things
| confused. 100% off isn't 1x cheaper -- it's infinitely
| cheaper.
| osigurdson wrote:
| It probably means that it has 3X better value. If I spent $1
| previously to do X, I can now do 3X for the same $1.
|
| I think this is more intuitive for most people than using
| percent difference for the same reason using a raw ratio (speed
| up) is better for expressing performance improvement.
| throwawaycuriou wrote:
| Contrarily I wish people used 'Nx times' more often, especially
| for 10x in place of 'an order of magnitude'. It's more
| welcoming and less pretentious.
| bitdivision wrote:
| I'm not sure about using 10x in place of 'an order of
| magnitude'. An order of magnitude conveys an approximation,
| whereas 10x is precise.
| IncRnd wrote:
| 10x is literally the difference of an order of magnitude.
| An order of magnitude is an exponential change of plus or
| minus 1 in the value of a quantity or unit. The term
| is generally used in conjunction with power-of-10
| scientific notation. Order of magnitude is used
| to make the size of numbers and measurements of
| things more intuitive and understandable. It is generally
| used to provide approximate comparisons between two
| numbers. For example, if the circumference of the Sun
| is compared with the circumference of the Earth, the
| Sun's circumference would be described as many orders of
| magnitude larger than the Earth's. [1]
| An order of magnitude is an approximation of the logarithm
| of a value relative to some contextually understood
| reference value, usually 10, interpreted as the base of the
| logarithm and the representative of values of magnitude
| one. [2]
|
| [1] https://www.techtarget.com/whatis/definition/order-of-
| magnit...
|
| [2] https://en.wikipedia.org/wiki/Order_of_magnitude
| bitdivision wrote:
| Yes, an order of magnitude literally means 10x. But in my
| experience, in common speech it's often used to convey an
| approximation. i.e. 'Changing this will decrease
| performance of that endpoint by an order of magnitude',
| when it's really somewhere around 10x. If someone said
| 'decrease performance by 10x' that seems much more
| concrete to me.
| IncRnd wrote:
| Not exactly. An order of magnitude change doesn't always
| mean 10x in base 10! 15 and 150 differ by an order of
| magnitude but so do 15 and 180.
| sebzim4500 wrote:
| Yeah but it's like the difference between someone saying
| that their height is 1.8m and saying it is 1.800m. They
| imply different levels of precision.
| [deleted]
| gausswho wrote:
| To a mathematician the 0 signals the author intends less
| precision, but this is not colloquial use
| umanwizard wrote:
| Consider "cheapness" to be the reciprocal of price; thus,
| something that costs $30 has a cheapness score of 1/30
| antidollars.
|
| For this item to become 3x cheaper would mean for its cheapness
| score to be multiplied by 3, thus 1/10 antidollars. Thus "3x
| cheaper" means the same thing as "price multipled by one
| third".
| copperx wrote:
| I like this hypothesis; however, if that was indeed the
| original meaning, it would have more sense to advertise it as
| a 33% discount, or as slashing the price by 1/3. "3x cheaper"
| seems to be aimed to the average Joe shopping for shoes, not
| to a developer who knows arithmetic.
| umanwizard wrote:
| It's not the same thing as a 33% discount, nor slashing the
| price by 1/3. It's slashing the price by 2/3.
|
| A 33% discount would be "1.5x cheaper" by my analysis.
| IncRnd wrote:
| No, it's not just you. When you "times" something it is
| multiplication, not division. The phrasing is a logical
| impossibility, where the reader has to guess the intent of the
| author - of which there are several interpretations. The key
| here is that this is a language "thing" only and certainly not
| a construct of logic or math.
|
| In the headline of this page, it wouldn't have taken but a
| moment to write a phrasing that would be understandable to all
| readers of the page. It could read, "GPT-3 will be Two Thirds
| Less," or, "GPT-3 will cost One Third the Price."
|
| This example from a non-native English speaker shows the
| difficulties of having several possible interpretations, at
| least three! [1]
|
| [1] https://forum.wordreference.com/threads/%C2%ABx-times-
| less%C...
| hiccuphippo wrote:
| I wonder how does GPT-3 understands that phrase.
| sebzim4500 wrote:
| Ironically GPT-3 probably understands this headline fine.
| (For a suitably generous definition of understands).
| copperx wrote:
| It's hard to understand because "cheaper" only makes sense as a
| relative comparison.
|
| Assuming that if, say, the service was 25% cheaper than the
| nominal price last month, it is now 0.25 * 3 = 75% cheaper than
| the nominal price. However, it would make more sense to
| advertise that as a 75% discount over nominal price, so
| probably that's NOT what they meant.
|
| That's the only explanation that makes sense arithmetically, I
| believe. There cannot be another interpretation of "3x cheaper"
| unless you reinterpret the word "cheaper."
| miohtama wrote:
| Is this free markets in action, subvention by VC money or both?
| aabhay wrote:
| It's an indication that OpenAI picked the wrong place to
| monetize. Picks and shovels are rapidly falling to zero margin.
| itake wrote:
| My guess is lower pricing makes the product more accessible to
| more people (and business models).
| thorum wrote:
| I'm sure those are factors, but it's mainly (1) GPU prices have
| dropped significantly, and (2) a lot of progress is happening
| in optimizing large language models to be more efficient while
| maintaining performance.
| imdsm wrote:
| Great to see. GPT-3 has been very useful to me, though looking
| forward to whatever the next version is.
| londons_explore wrote:
| I'm really surprised they don't charge a very high price with a
| generous free tier, and then have an army of salespeople who will
| offer you whatever discount is necessary to make your business
| model work.
|
| If you want to use GPT-3 to build an AI-lawyer, it'll be very
| expensive... but to build a tool for customer support for walmart
| will be cheap, etc.
| gkoberger wrote:
| Do they need an army of salespeople, or just a finely tuned
| GPT-3 bot?
| choppaface wrote:
| The OpenAI CEO Sama is primarily an investor, not an operator,
| so the model is tuned towards giving small companies an
| opportunity versus enticing enterprise customers. Sama want
| somebody to figure out how to run & productive his business
| versus actual customers. In particular because of efforts like
| Stable Diffusion--- it's going to be a lot easier for
| enterprise to build off tech that's _actually_ Open.
| lee101 wrote:
| If your looking for a free teir that allways is there checkout
| https://text-generator.io which has 100 free requests a month.
| The free their really helps people get started with it or run
| demos etc without needing to commit to anything
| thdxr wrote:
| making things cheap encourages experimentation and
| paradoxically increases total spend
| rvz wrote:
| Or how about opening everything up and releasing all the models
| as open source?
|
| Since even with these price decreases, lots of competitors are
| out there with more parameters and are open source, and are
| already matched or just as good as GPT-3 and are generally
| running OpenAI's pricing to the ground.
|
| Might as well open everything up since you can't compete with
| free anyway.
| colejohnson66 wrote:
| The free alternatives to OpenAI are not as good as OpenAI. For
| example, Craiyon (formally DALL-E Mini), is good, but it's
| nothing compared to the real DALL-E.
| simonw wrote:
| That's true for Craiyon, but Stable Diffusion came out today
| and looks like it may be able to beat DALL-E in terms of
| quality some of the time:
| https://github.com/huggingface/diffusers/releases/tag/v0.2.3
| rvz wrote:
| > For example, Craiyon (formally DALL-E Mini), is good, but
| it's nothing compared to the real DALL-E.
|
| Yet Stable Diffusion is already getting open sourced and is
| just as good, if not better than what I am seeing with DALL-E
| 2.
| RcouF1uZ4gsC wrote:
| Just in time for the 2022 Midterms!
| jon_adler wrote:
| Are any plagiarism detectors capable of recognising generated
| content? I'm not even sure how they might ever go about it?
| dane-pgp wrote:
| Is this because GPT-4 is about to be released and they want to
| charge full price for that?
| layer8 wrote:
| Maybe demand has slowed and they want to keep it up.
| teaearlgraycold wrote:
| GPT-J was about the same cost to self-host as GPT-3 (ignoring
| maintenance costs). They're getting ahead of competitors IMO.
| whoisburbansky wrote:
| Why wouldn't they just charge more for the better, improved
| GPT-4?
| lee101 wrote:
| Also checkout https://text-generator.io which is already 10x
| cheaper... I think they know text generation is no longer a
| monopoly any more hence having to move pricing, the openai
| margins are still really high though honestly.
| RobotToaster wrote:
| It still bugs me that a closed source company calls it's product
| "Open"AI.
| [deleted]
| Mimmy wrote:
| Same. What they're doing is cool but the name is sacrilegious.
| cbm-vic-20 wrote:
| I lack imagination. What is GPT-3 (and generative text models in
| general) useful for, other than toys? It can write essays, can we
| expect it to replace writers for newspapers and magazines? Can it
| write coherent technical documentation? Replace speechwriters?
|
| Edit: looks like the comment thread below is similar
| https://news.ycombinator.com/item?id=32554955
| dan_mctree wrote:
| I've used it a bit to help with creativity. For example, I
| wanted to brainstorm some unit designs and gameplay mechanics
| for a RTS game I wanted to build. I prompted GPT-3 with an
| interview with a game designer where unit designs and mechanics
| were discussed. For a prompt I used a few questions and answers
| and then a single question I wanted GPT-3 to answer for me.
| After a few attempts with slight variations it spat out a bunch
| of ideas for me. While few of the designs were fully worked out
| and immediately usable, a couple of suggestions by GPT-3 were
| able to spark enough creativity to create some cool things.
|
| My favorite reply was:
|
| "A: I think the best example of this is the ability to swap
| positions with a friendly unit. This ability can be used in so
| many different ways. You can use it to support an ally, or you
| can use it to escape a tricky situation. You can use it to
| surprise an enemy by swapping with a unit they didn't expect,
| or you can use it to put yourself in a better tactical
| position. It's a simple idea, but it actually turns the whole
| game on its head."
| dr_dshiv wrote:
| It's incredibly good at generating scholarly text. Put in a
| title and abstract and it will come up with a strong intro that
| is clear and compelling. It helps me write academic papers more
| clearly, as a result. Also, great for early stages of grant
| writing or proposals. It came up with a fantastic conference
| proposal for me that I spent 20 minutes editing and then just
| sent, unedited.
|
| It will aid speechwriters or help more people write their own
| speeches, I guess.
|
| Assuming that AI tech is a person replacement is, IMO, the
| wrong mental model. It helps talented people be more efficient.
| And will help a lot of hacks "fake it till they make it." Power
| to the people, if they can handle it.
| dr_dshiv wrote:
| I also asked it to help me write a letter to my homesick
| daughter at summer camp. It was really helpful. I feel that
| GPT3 has an enviable degree of emotional intelligence, nuance
| and conceptual understanding. Writing and communicating
| effectively with people is very hard. Our own emotions get in
| the way. Now we have technology that can help people be
| better communicators with each other. It's a big deal.
| slavik81 wrote:
| When you say you're an empath, do you mean to claim that
| you have psychic powers? An empath is a being from science
| fiction with the psionic ability to sense emotions, like
| Counselor Troi on Star Trek. The term originates from the
| short story "Empath" by J. T. McIntosh, published in New
| Worlds Science Fiction #50, August 1956.
| dr_dshiv wrote:
| Yes, that is correct. I have psychic powers, specifically
| the psionic ability to sense emotions. AMA
| itsyaboi wrote:
| When did you first become aware of your powers?
| dr_dshiv wrote:
| It has always seemed natural (to me) to be able to
| directly feel what other people are feeling. Most people
| can. Sometimes, however, it can feel shocking when I
| realize I'm talking to someone who doesn't feel what I'm
| feeling. Or, that doesn't feel that I'm feeling what they
| are feeling.
| donkarma wrote:
| wtf is an empath?
| matthewmacleod wrote:
| _It came up with a fantastic conference proposal for me that
| I spent 20 minutes editing and then just sent, unedited._
|
| Was this comment written by GPT-3?
|
| (That said - are _all_ comments written by GPT-3?)
| layer8 wrote:
| > Was this comment written by GPT-3?
|
| You should submit that to GPT-3 as a prompt.
| [deleted]
| DaSHacka wrote:
| I assume what was meant was that they spent 20 minutes
| editing it, before realizing it was perfect as it was
| originally and sent the unedited copy.
| blagie wrote:
| I've started asking GPT-3 for relationship advice. It's
| often... insightful.
|
| There is a bit of prompt engineering. If you start your
| question with things like "As a qualified therapist, what
| would you recommend to" .... There is also a bit of
| engineering with the question. I often ask about an analogous
| situation, rather than my own.
|
| I'm not batting 100%, but I often get strategies and things
| to think about I wouldn't have come up with myself.
| dr_dshiv wrote:
| > I often get strategies and things to think about I
| wouldn't have come up with myself
|
| Yes. It's a dialectic. Very powerful for personal
| reflection.
| Traubenfuchs wrote:
| It's been out 2 years already and the non-toy application with
| the biggest mass appeal is the glorified autocomplete / google
| shortcut Copilot.
|
| Anyone being honest should admit it (was) more hot air and hype
| than reality.
| dr_dshiv wrote:
| I think GPT3 is just as amazing as DALLE, but gets less
| public awareness because the things it creates requires
| critical reading.
|
| Which makes me think: everyone needs to teach kids to speed
| read. And develop their bullshit detectors.
| mg wrote:
| GPT-3 is useful for a lot of things. It can write essays, it
| can write technical documentation, it can write speeches, it
| can write fiction, it can write poetry, it can write jokes, it
| can write jokes about jokes, it can write jokes about jokes
| about jokes, it can write jokes about jokes about jokes about
| jokes, it can write jokes about jokes about jokes about jokes
| about jokes, it can write jokes about jokes about jokes about
| jokes about jokes about jokes, it can write jokes about jokes
| about jokes about jokes about jokes about jokes about jokes.
|
| This answer was written by GPT-J when I gave it the following
| prompt:
|
| question: I lack imagination. What is GPT-3 (and generative
| text models in general) useful for, other than toys? It can
| write essays, can we expect it to replace writers for
| newspapers and magazines? Can it write coherent technical
| documentation? Replace speechwriters?
|
| answer:
| layer8 wrote:
| At least it didn't go into an infinite loop. Maybe there's
| explicit logic to prevent that.
| keepquestioning wrote:
| What are thresholds used in generative text to stop
| generating characters?
| layer8 wrote:
| Must be a bit more sophisticated than that, as it forms a
| complete sentence.
| stavros wrote:
| There's a penalty for generating text it's generated
| before (two penalties, actually, one for words and one
| for phrases).
| ml_basics wrote:
| I'm not sure about GPT-3 specifically, but often these
| models are trained with an explicit "stop token", which
| the model can output when generating text to indicate
| that no more text should be produced.
|
| That said, there's no reason it couldn't go into an
| infinite loop, just that the models are pretty
| sophisticated and therefore are less likely to do this
| than earlier generations of models (like predictive text
| on smart phones in the past)
| jahewson wrote:
| I had no idea that there were so many jokes about Church
| encoding.
| moonchrome wrote:
| >it can write technical documentation
|
| For the love of god please NO.
| nonethewiser wrote:
| This is hilarious.
| renewiltord wrote:
| My friend used it to "explain like I'm 5" a medical report he
| had. I sent that to my dad (a surgeon in that specialty) and he
| said it was all accurate. I thought that was interesting.
|
| But I think the principal use for me is CoPilot.
| tedsanders wrote:
| As someone who's used the models a fair bit (I work at OpenAI),
| I mentally sort applications into four buckets:
|
| - Generative use cases, where you give the model the kernel of
| an idea and then you curate its output (e.g., blog writing,
| code completion, etc.)
|
| - Extractive use cases, where you give the model some big piece
| of text, and then process it in some way (e.g., extract names
| and addresses, classify it, ask a question about the text)
|
| - Transformational use cases, where you need to fix/adjust a
| piece of text, or translate from one domain to another (e.g.,
| sometimes I'll use GPT-3 for little tasks like copying and
| pasting a table from a presentation and then asking the model
| to translate it to markdown; saves me a visit to Google and
| finding some table generator website)
|
| - Comparisons, where you use embeddings to do
| search/clustering/recommendations over any set of strings
| (e.g., can combo nicely with the Q&A use case above, where you
| search over a knowledge base)
|
| I started a repo here with some barebones examples of each:
| https://github.com/openai/openai-cookbook/
|
| If you're looking for examples of commercial applications,
| OpenAI published two blog posts highlighting a few:
|
| - GPT-3 use cases (2021): https://openai.com/blog/gpt-3-apps/
|
| - Codex use cases (2022): https://openai.com/blog/codex-apps/
| nicksrose7224 wrote:
| This is a really nice breakdown -- I made a little side
| project that falls into your "Extractive" and "Comparisons"
| bucket: https://www.tripwise.me/
|
| My tools uses GPT-3 to dig through Airbnb reviews to find the
| "cons" of staying at a particular place and summarize them
| neatly. You can also ask any question at all in natural
| language about all the listings you're evaluating.
|
| I'm bookmarking your repo for future reference, this is very
| useful
| patientplatypus wrote:
| leesec wrote:
| Write now it's a great writing-assist tool. Eventually all the
| rest.
| alexb_ wrote:
| In a few years, when a generative text model that's actually
| open is made, erotic text will 100% be a main use. But of
| course people don't like thinking about that...
| SamPatt wrote:
| I don't think porn is as bad as some people say, but there
| are downsides, and good quality erotica seems like a
| healthier alternative.
|
| Whether a human or a computer writes it seems unimportant.
| alecco wrote:
| Besides all the ideas of well meaning people in HN, I fear
| GPT-3 (and its competitors) will just bring almost impossible
| to spot fake Amazon reviews, SEO garbage sites, fake blogs,
| fake podcasts, etc.
|
| And even worse, now corporations and governments don't even
| need to have troll farms. Just rent some AI, give it basic
| directions, and let it loose.
|
| The Dead Internet Theory will become real.
| nicksrose7224 wrote:
| i think this is a bit pessimistic. You can also use GPT-3 or
| similar technologies to much more easily train a fine-tuned
| "real vs fake" review classifier with fewer training examples
| than was previously necessary.
|
| GPT-3 like all tech is double-edged I think. Has good & bad
| things about it
| moonchrome wrote:
| I doubt this will happen - at some point the generated
| content should be indistinguishable from human written text
| - and AI can produce it in droves and learn to exploit
| existing algorithms.
| visarga wrote:
| Until Google starts to expect better garbage from SEO
| providers. The bot can simply ask a language model if the
| page looks well written and truthful. So SEOs will have to
| spam us with well written useful articles about topics we
| like.
|
| Maybe Google should require webmasters to mark the automated
| content with a special HTML tag or attribute. Failure to
| comply leading to deranking. This would be necessary for the
| future - to know what data was human generated when training
| the next model, and to have official reason for penalising
| spammers who try to pass artificial text as human written.
| kleiba wrote:
| Language models are few-shot learners.
| [deleted]
| floxy wrote:
| Maybe someone should ask GPT-3 what it is good for?
| machineleaning wrote:
| Marketing copy - https://www.copy.ai/ Coding help -
| https://github.com/features/copilot
| simonw wrote:
| I wrote a few notes in this comment:
| https://news.ycombinator.com/item?id=32554955
|
| Here's one that I find personally really interesting:
|
| Imagine you have a disability, and the government agencies
| responsible for helping you have denied your claim. You need to
| write them a letter. You don't have much (if any) experience
| writing letters to government agencies, so you're finding that
| task challenging.
|
| GPT-3 can write that letter for you, and it will de a really
| good job of it.
|
| Of course, you need access to GPT-3 and you need to learn how
| to drive it with prompts, so this isn't necessarily an easy
| thing. But I think it helps lean in the direction of the kind
| of benefits people can get from this class of technology
| outside of just playing with the AI.
| aabhay wrote:
| How is this different or more useful than providing a
| template with madlibs-style fill in the blanks?
| dr_dshiv wrote:
| Because you can tell GPT3 what the concept is -- ie,
| vaguely what you are going for and it will produce. Waaay
| more flexible than a template.
| aabhay wrote:
| Still requires you to have an understanding of the
| concept, an understanding of how to prompt GPT-3, and how
| to verify the accuracy/veracity of the claims the AI
| model makes.
| [deleted]
| simonw wrote:
| Because providing a template requires someone with
| knowledge of that particular problem space (in this case
| "writing letters to government agencies to inquire about
| disability benefits") to put in the work of designing the
| template, coming up with likely placeholders and predicting
| how people might need to use it.
|
| GPT-3 can do a good job of this all today, without any
| additional training.
|
| An expert could help out by providing a few example
| prompts, but the result would be a lot more powerful and
| require a lot less development work to put together than
| trying to build some kind of placeholder wizard from
| scratch.
| aabhay wrote:
| A madlibs is more predictable, requires only one example,
| easy to understand for people with language issues or
| disabilities, more regulation-safe as it doesn't spit out
| unpredictable things.
|
| And the madlibs is free to use, for everyone.
|
| All things considered, GPT-3 is a more of a shibboleth of
| AI revolution than an actual one. Much better to give
| models like GPT-NeoX to talented development teams who
| can really optimize and fine tune it, attach great
| sampling strategies to it, and create great products from
| there. The API is just too limited for me to want to
| build a company atop it.
| simonw wrote:
| Right, but someone still has to build it.
|
| If no-one has built the madlib template for "a letter to
| the council asking about my disability benefits" then
| madlibs being more predictable isn't going to help you.
| [deleted]
| [deleted]
| unixhero wrote:
| The got their hands on the latest Nvidia GTX cards, aha I see. I
| hear new cards are on their way.
| dvfjsdhgfv wrote:
| The so-called "open" in their name is an oxymoron. The whole
| thing is a trap. We need to work on our own, possibly publicly
| founded but really open solutions rather than depend on
| proprietary ones.
| naillo wrote:
| We really gotta come up with another thing to repeat as the go-
| to diss than this. I'm all for putting pressure on them to
| release weights etc but they are a lot more open than e.g.
| google or meta, and the whole "ClosedAI" is so over-repeated at
| this point.
| TigeriusKirk wrote:
| They brought it on themselves. They chose the name OpenAI. It
| was a terrible choice on their part, and the repeated
| criticism is a direct result of that choice.
| person3 wrote:
| I definitely agree, "open" in the name is pretty annoying
| and wrong. I'm a bit torn though - I tend to think GPT-3 is
| approaching a level where ML is becoming dangerous. Spam
| bots + GPT-3 is not my idea of a fun time. So the
| restrictions they put on usage do seem important.
|
| Regardless of that moral question, I don't think a fully
| open model on the level of GPT-3 is even possible. Given
| the required cost to train and the expertise involved, big
| tech will always be a few years ahead. And it's unlikely
| they would give it away with how much they invest in
| creating it. Unless capitalism suddenly ends, I don't see
| any of the major tech companies parting with state of the
| art ML.
| naniwaduni wrote:
| It's not an oxymoron, it's just a lie.
| rvz wrote:
| It is a known scam executed by the VCs.
|
| Thankfully we have free alternatives to GPT-3 (BLOOM [0]) and
| DALL-E 2 (Stable Diffusion [1])
|
| [0] https://huggingface.co/bigscience/bloom
|
| [1]
| https://github.com/huggingface/diffusers/releases/tag/v0.2.3
___________________________________________________________________
(page generated 2022-08-22 23:01 UTC)