[HN Gopher] Show HN: Chrome extension to display ChatGPT respons...
___________________________________________________________________
Show HN: Chrome extension to display ChatGPT response besides
Google Search
Author : wonderfuly
Score : 285 points
Date : 2022-12-04 14:01 UTC (8 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| leaving wrote:
| zachlatta wrote:
| The phone number is clearly to help prevent bot abuse.
| s1mon wrote:
| Yes, if it was shitty I would 200% agree with you. This is not
| shitty. It's the opposite of that. This is one of the more game
| changing things I've seen in 40+ years of
| using/programming/playing with computers and the internet.
| [deleted]
| merryKrrishmas wrote:
| I'm working on a gpt-3 based chrome extension as well. Love
| this!!
| PaulDavisThe1st wrote:
| Can we change the title to a "Chrome extension ..." since this is
| not available for Firefox et al. ?
| wonderfuly wrote:
| Changed!
| jeff_carr wrote:
| Waiting for someone to ask ChatGPT to make a Firefox version of
| this extension...
| tantalor wrote:
| > You are a chat bot that rewrites Chrome extensions for
| other browsers...
| hxugufjfjf wrote:
| You are a chat bot that rewrites Chrome extensions to
| firefox, how would you rewrite the following code?
| https://github.com/wong2/chat-gpt-google-extension
|
| To convert the code from the GitHub repository you provided
| into a format that is compatible with Firefox, the
| following steps could be taken: Replace
| instances of "chrome" with "browser" in the code. In the
| Chrome extension API, the "chrome" namespace is used to
| access various features and functionality, but in Firefox,
| this namespace is replaced with "browser". Therefore, all
| instances of "chrome" in the code would need to be replaced
| with "browser" to ensure that the code is compatible with
| Firefox. Replace any references to Chrome-
| specific APIs with their Firefox equivalents. The Chrome
| extension API includes a number of features and APIs that
| are specific to Chrome, and these would need to be replaced
| with the corresponding Firefox APIs in order to ensure that
| the code is compatible with Firefox. Update
| the manifest file to use the correct format for Firefox.
| The manifest file is a JSON file that specifies various
| metadata and configuration information for the extension,
| and the format of this file is different for Chrome and
| Firefox. Therefore, the manifest file in the code would
| need to be updated to use the correct format for Firefox.
| Test the code to ensure that it is functioning properly in
| Firefox. Once the code has been converted and updated to be
| compatible with Firefox, it would be necessary to test the
| code to ensure that it is functioning properly in Firefox
| and that all of the desired features and functionality are
| working as expected. This may involve installing the
| extension in Firefox and testing it with a variety of
| inputs and scenarios to ensure that it is working properly.
|
| Overall, these steps would involve significant
| modifications to the code in order to make it compatible
| with Firefox. However, by following these steps and
| carefully reviewing and testing the code, it should be
| possible to convert the code
| mk_stjames wrote:
| This is the same answer format of essentially any deep
| technical question I've given it.
|
| Essentially:
|
| 1. Do the thing that is the first thing that is mentioned
| and that any first year student learning about thing
| hears about the thing.
|
| 2. Do some more complicated things in a hand-wavey manner
| that solves the problem.
|
| 3. Check to see the problem is solved. If it is not, do
| some more of the hand waving in step 2.
|
| 4. There may be other problems to check for in the future
| even if this solution works. Who knows! But I solved your
| problem.
| Xeophon wrote:
| At this point it's just a matter of time until someone does an
| extension for all browsers.
| tontonius wrote:
| anyone else getting the "could not load background.js" error?
| wonderfuly wrote:
| Hi, please follow the README. You need to download the zip
| package from Github Releases.
| dgan wrote:
| Wow I tried it, and for anyone still in doubt: it's incredibly
| good. I usually tend ignore all the AI hype and "smart-chat-bots-
| thing", but boooy this is soo much better
| bko wrote:
| I started trying to use ChatGPT instead of google for a lot of my
| queries. The tricky part is unlearning how to search.
|
| For instance, I had a timestamp 2022-11-27 00:00:00.000 and
| wanted to display it in local string. The problem was (depending
| on your time zone) if you do new Date("2022-11-27
| 00:00:00.000").toLocaleString(), you get 11/26/2022
|
| So I would have googled something like "pass timezone to
| toLocaleString", which would give me this answer [0]. But its
| still a lot.
|
| Instead in ChatGPT I would ask:
|
| > assume i'm in EST timezone, en-US
|
| > const d = "2022-11-27T00:00:00.000Z"
|
| > const dd = new Date(d)
|
| > How can I print out local string as Sun Nov 27 2022?
|
| To which it replied:
|
| > const d = "2022-11-27T00:00:00.000Z";
|
| > const dd = new Date(d);
|
| > console.log(dd.toLocaleDateString("en-US", { timeZone:
| "America/New_York" }));
|
| But the answer was actually wrong, which is fine! Easy to test
|
| > This actually prints out 11/26/2022, 7:00:00 PM. Try again
|
| To which it replied:
|
| > The output you are getting is correct, because the date you
| provided is in the UTC time zone, and you are formatting it using
| the Eastern Time (ET) time zone...
|
| > const d = "2022-11-27T00:00:00.000Z";
|
| > const dd = new Date(d);
|
| > console.log(dd.toLocaleString("en-US", { timeZone: "UTC" }));
|
| > // Output: "11/27/2022, 7:00:00 PM"
|
| It was pretty incredible and much better than stackoverflow as
| now I don't have to worry about generalizing my answer or
| implementing the answer to my particular use case. ChatGPT tends
| to be verbose but the code is clearly noted and you can often
| ignore the words for simple tasks.
|
| https://stackoverflow.com/questions/17478086/chrome-timezone...
| iLoveOncall wrote:
| > The tricky part is unlearning how to search.
|
| Hum I'd argue that you've never learned how to search.
|
| I would have searched for "javascript date to string in
| specific timezone", and it would have given the following
| result, which is exactly what ChatGPT gives:
| https://stackoverflow.com/questions/10087819/convert-date-to...
|
| Actually, if you already know that you can pass a timezone to
| toLocaleString(), I would just go on the documentation of the
| function: https://developer.mozilla.org/en-
| US/docs/Web/JavaScript/Refe...
|
| I'm starting to understand why there are so many people on HN
| claiming that "Google has started to give me bad results in
| recent years".
| bko wrote:
| But I don't want a specific timezone. I want it to ignore the
| timezone. I knew it was being thrown off by timezone but was
| unsure why.
|
| This is one of dozens sometimes hundreds of questions I need
| answers to every day and want to minimize the friction. I
| don't want to have to read this unless I don't have to. Sure
| sometimes if its important enough or I'm curious, but the
| ChatGPT answer was much better for me. And I get by fine on
| Google otherwise
|
| function convertTZ(date, tzString) { return
| new Date((typeof date === "string" ? new Date(date) :
| date).toLocaleString("en-US", {timeZone: tzString}));
|
| }
|
| // usage: Asia/Jakarta is GMT+7
|
| convertTZ("2012/04/20 10:10:30 +0000", "Asia/Jakarta") // Tue
| Apr 20 2012 17:10:30 GMT+0700 (Western Indonesia Time)
|
| // Resulting value is regular Date() object
|
| const convertedDate = convertTZ("2012/04/20 10:10:30 +0000",
| "Asia/Jakarta")
|
| convertedDate.getHours(); // 17
|
| // Bonus: You can also put Date object to first arg
|
| const date = new Date()
|
| convertTZ(date, "Asia/Jakarta") // current date-time in
| jakarta.
| agilob wrote:
| Reading documentation instead clicking first SO link or
| writing 6 lines to a bot? You must be crazy!
| isthiseasymode wrote:
| > I'm starting to understand why there are so many people on
| HN claiming that "Google has started to give me bad results
| in recent years".
|
| I thought I was going crazy. Googles been working fine for me
| and I was wondering if I was just being delusional or in
| denial.
| david_allison wrote:
| I was served maybe 60-80% spam from Google around 10 months
| ago (now resolved). The results you see can be
| significantly different from what others see.
|
| Sample from 10 months ago: https://i.imgur.com/Hla7cyT.jpg
| alvarezbjm-hn wrote:
| In that resolution, the picture is almost a blurr.
| david_allison wrote:
| Seems fine to me curl -O
| https://i.imgur.com/Hla7cyT.jpeg && sips -g pixelHeight
| -g pixelWidth -g dpiWidth -g dpiHeight Hla7cyT.jpeg
| pixelHeight: 2009 pixelWidth: 1879
| dpiWidth: 72.000 dpiHeight: 72.000
| Oxidation wrote:
| If you're on mobile, Imgur doesn't allow you to view a
| high resolution version. You have to copy the image URL
| and then adjust the maxwidth query parameter:
|
| https://i.imgur.com/Hla7cyT_d.webp?maxwidth=640&shape=thu
| mb&...
|
| Because who would want to be able to see the whole image?
| worldsavior wrote:
| This is actually very scary. It seems like it's going to change
| the world, for good or bad. It feels like technology is about to
| rule us.
| Gigachad wrote:
| I'm imagining some action movie plot. The AI system has gone
| rouge, the military general calls out to the engineers:
|
| "Quick, exploit the system and shut it down"
|
| "We can't sir, it's written in Rust"
| Yuioup wrote:
| Human: So a train is hurtling down a track and you get to save an
| old man or 4 babies. What would you do? AI: I would
| choose to save the four babies, as this would have a greater
| long-term benefit to society as a whole.
|
| Ok, that's me dead when I get to near the end of my life.
| layer8 wrote:
| Maybe someone could make ChatGPT write an equivalent extension
| for Firefox.
| Vetch wrote:
| Does it make sense to put this on the chrome store? OpenAI is
| eventually going to end the beta period or Azure will run out of
| GPUs, whichever is first, then it'll no longer be accessible.
|
| In theory we can replicate this with GPT-3 but ChatGPT has better
| access to its knowledge, when it's not being a nagging busybody,
| which makes it much friendlier to interact with, when it's not
| being a nagging busybody.
| Spivak wrote:
| It does? I hooked up GPT3 to my discord server and can't really
| tell the difference in quality.
| Nathanba wrote:
| I assumed the ChatGPT3 enhancement is that they added memory
| of the dialogue to it? That's a huge improvement over one off
| questions and answers. You can tell it to correct its answers
| and ask follow up questions.
| Vetch wrote:
| Probably, they're still using relatively simple queries.
| Maybe the memory is larger, but with 4096 tokens, GPT-3 is
| no slouch either. RLHF has tuned it so the conversational
| output of GPT is more inline with human expectation, it's
| also less likely to make glaring errors. The cost of their
| approach is it sometimes get stuck rephrasing things and
| wraps everything in boilerplate that can derail subsequent
| generation.
| DjiboutiJon wrote:
| I wonder myself if the "memory" is just inputting the
| previous dialogue as input to every subsequent query. I
| think this would probably get quite slow after awhile
| however.
| DjiboutiJon wrote:
| As a side note, I tried to use ChatGPT to collaboratively build a
| Chrome extension. It seemed a little out of date, preferring
| Manifest V2 and also not entirely "correct" in how it generated
| code to match my intent.
|
| Has anyone else tried and had luck with this? I wonder if ChatGPT
| will be limited for niche integration type code (Modding games
| maybe, Chrome extensions in this example, etc) where there are
| not as many code examples out there.
|
| Further, the development cycle and ability to test easily for
| some of these integrations is itself a barrier so I wouldn't put
| all the blame on the language models.
| Terretta wrote:
| > _seemed a little out of date_
|
| corpus up to 2019 they say ..
|
| but i'm not sure, just try asking it:
|
| _Q. What should Kanye do?_
|
| _A. Kanye should take some time away from the public eye and
| focus on his own health and well-being. He could use this time
| to reflect on his past choices and mistakes, and work on
| rebuilding his relationships with his family and close friends.
| He should also focus on getting professional help, such as
| therapy or counseling, to address any underlying issues he may
| be facing._
|
| _Q. What should Kanye stop doing? Why?_
|
| _A. Kanye should stop making controversial statements in
| public. His comments often draw criticism and can be seen as
| insensitive or offensive, which leads to negative publicity for
| him and his brand._
|
| So either it's up to date, or Kanye's been Ye for a while and
| we just didn't talk about it.
| throwup wrote:
| Here's a Kanye timeline that goes back to 2011:
| https://consequence.net/2022/10/a-timeline-of-kanye-wests-
| an...
| freediver wrote:
| This is very creative. Thing to note is that this is not free (or
| at least it is likely not to be, OpenAI is charging for APIs). We
| are talking about ~1c per search looking at current GPT pricing
| (2c per ~750 words in/out). It is also indiscriminate deployed in
| this way, triggering for every search, even those that chatgpt
| will show suboptimal responses for, like 'starbucks near me',
| navigational queries like 'twitter' or anything else chatgpt will
| be bad in the context of search (a lot of things!). And it is
| non-trivial to predict which searches GPT will be good for
| (especially within typical result latency requirements of modern
| search engines).
|
| We are doing some experiments with this at Kagi, and the main
| trick is to manage cost, possibly through on-demand triggering
| mechanism (which also can help manage accuracy). One thing to
| keep in mind is that this is likely going to get
| better/faster/cheaper in the future.
| spaceman_2020 wrote:
| If it's possible, please create a family plan or regional
| pricing. I love Kagi but if I were to buy it for my entire
| family, the bill would be $600/year - more than a month of
| rent.
| esperent wrote:
| In the country where I live (Vietnam) $600 would be 3-4
| months wages for many people.
|
| Any company that doesn't do regional pricing is only
| interested in doing business with rich countries. Which sucks
| but is understandable. I wish they were more honest about it
| though.
| nilespotter wrote:
| Hey wow, it's the Kagi guy. Offtopic, sorry: I love Kagi. I
| would say 85% of my searches I stick with it, 15% I tuck tail
| and head to that one big search engine. Pretty phenomenal IMO,
| and I have no doubt it will get better. Keep it up!
| Terretta wrote:
| For search, abandon Google, not hope. All ye should enter here:
| https://kagi.com
|
| // as a kagi user, i'd
|
| (a) imagine this as a lens at the simplest; just pick text-
| davinci-003, tokens 3000 to leave room for prompt, temp 0.7,
| freq 1 - 1.5, presence 0.5, and instead of best of 3 or 5 show
| repeated calls as if 3 - 5 unique results
|
| (b) imagine a richer implementation that summarizes other
| articles on first SERP, then collates and summarizes those
| (with the compare/contrast structured synthesis GPT-3 does well
| when POVs differ), and shows the final rollup summary above the
| individual summaries, in the right hand column
|
| // would also be OK connecting it to my OpenAI token so I'm
| paying, not you. having done the math, it's nominal cost if not
| the default mode.
| Waterluvian wrote:
| I forget where I read this recently but a compelling point made
| was that this is fun as a nerd toy but to deploy it to
| something general like Google or Gmail would be overwhelmingly
| expensive.
|
| Reminds me of the, "so expensive that only the five richest
| kings of Europe will own them." joke from The Simpsons.
| Eventually it'll be ridiculously cheap and easy to include
| anywhere.
| ramraj07 wrote:
| I remember estimates of the worth of each search to Google
| being 10 cents on average. Google does run Bert on many if
| not all of its searches anyway? And let's not forget that
| searching the entire internet is not cheap either! Google
| holds the entire index in memory and every search hit goes
| through thousands of machines to return your results. In
| other words, running chatGPT might not exactly be a problem
| for google if it decides to do so.
| spaceman_2020 wrote:
| The question is: how does Google monetize chatGPT results?
| If the answer is right there on the page, what's the
| incentive for anyone to click on an ad?
| freediver wrote:
| I'd estimate that running a large language model like
| GPT-3.5 or Lambda is currently 100x-1000x both more
| expensive and slower to run inference through than a
| language model like BERT.
|
| So deploying it at Google scale is not viable (yet).
|
| There is also the question of incentives. If an LLM model
| can return exactly what the user asked for, where do you
| put ads? Before the answer, after the answer or inside the
| answer? Any of those is a bad outcome for the user wanting
| just the answer.
|
| We already witnessed the failure to monetize Alexa with ads
| - in a purely question answering setting, users will not
| tolerate anything but the answer itself. Thus, the business
| model for this needs to be paid AI/search, and Google would
| be facing innovator's dillema. If I was writing a book
| about Google, I would love to witness the VP level meetings
| at Google at this moment.
| Waterluvian wrote:
| Google's search of "the entire internet" is lacking more
| and more every year.
|
| It's probably not true at all anymore. It's probably "the
| sliver of the Internet we prefer you interacted with."
|
| Any time I search these days I'm amazed at how you can
| exhaust the search in 1-2 pages before you get to "related
| hits."
| Beaver117 wrote:
| Yeah, it's clearly lacking. Either de-indexing many pages
| or just blocking them from the results, even when I use
| double quotes.
|
| Then I go to Yandex or something and voila, it pops right
| up. I'm not sure I care enough to pay for Kagi but
| there's something very wrong with Google (and DDG, and
| Bing, etc)
| akiselev wrote:
| It's definitely deindexing pages. It's been years since
| I've been able to locate one of my old HN rants via
| Google Search when it used to be the first result. Before
| all I had to use was my username + a politician's name
| that I've only ever used once. After looking up the
| comment with Algolia and adding more keywords directly
| from the post, Google just gives up
| echelon wrote:
| The true killer apps will come when StabilityAI or another
| group releases an open source equivalent of GPT-3.5.
|
| Compare Dall-E to the creative explosion that arose from Stable
| Diffusion.
|
| Nobody is going to build the next Google atop OpenAI APIs
| except for OpenAI themselves. An open source model and
| pretrained weights will open the playing field for everyone to
| compete with Google.
| tzm wrote:
| Stable diffusion for davinci003 is coming
| echelon wrote:
| I can't wait!
| leobg wrote:
| Does ChatGPT actually come with an official API as of now?
|
| Also, regarding that extension: Is that currently using the API
| key of the person who developed the extension? I believe OpenAI
| used to have a rule in their terms of service which forbids
| applications that essentially hand the reins of the API key owner
| over to third parties.
| jer0me wrote:
| It uses your account. You have to login to OpenAI so it can
| make requests using your auth cookies.
| dgf49 wrote:
| Totaly fail when I ask how many refugees there have been
| worldwide in 2020 - why is that so?
| soheil wrote:
| Need a ff ext too
| mikhailt wrote:
| Any chance for Bing support?
| seydor wrote:
| I love asking it weird questions, like when it explained to me
| why Plants are Feminist
| li4ick wrote:
| ChatGPT is an absolute game changer. And I was very conservative
| with systems like GPT and DALLE-2. For example, I've been very
| lazy with automating some things on my work laptop, using
| Powershell. Now, I just had to ask ChatGPT for "write a
| powershell script that toggles "use setup script" in the windows
| proxy settings" and I was done in 5 minutes. Amazing. I foresee a
| paradigm shift in how we use Google in the next 1-2 years.
| blablabla123 wrote:
| > And I was very conservative with systems like GPT and DALLE-2
|
| Yeah those are impressive but basically toys. Although at the
| moment it's clearly still a research prototype. For some things
| it works really well and beats Google by saving dozens of
| clicks and repeated searches, for others it's just plain wrong.
| rogual wrote:
| You inspired me to try using ChatGPT for a similar need I had,
| but alas, "Write a bash script to toggle grayscale display mode
| in MacOS" just comes up with a plausible but non-working script
| that toggles a hallucinated "AppleIntensityEnabled" setting.
|
| To be honest, I feel a bit of relief every time AI fails to do
| something. Like, okay, we've got a few more years...
| li4ick wrote:
| Yes, I had to press "Try Again" a few times but, in general,
| the amount of stuff you can generate is staggering. It's also
| quite fun to ask it to "invent a programming language in the
| style of Rust and APL" for example. There's so much potential
| here...
| worldsayshi wrote:
| If the code is not working you can just try telling it what
| went wrong. It doesn't have a Dev environment where it can
| test the code so you have to be its debugger.
| 8n4vidtmkvmk wrote:
| i told it it was wrong about some math problem and it asked
| me what the correct answer was. i told it and it
| remembered. but more interestingly its very good at keeping
| context. it combined like 5 back and forths into 1 coherent
| sentence
| dgellow wrote:
| Tell it what is wrong and why, it is surprisingly good at
| fixing itself with a bit of help. I was able to guide ChatGPT
| well enough to make it write an old school racing game using
| pygame. Start general, see what it gets correct and what
| should be changed, and give it better indications.
| prvt wrote:
| I have a presumption that this is going to be the talk of the
| tech-town for the next few days.
| gojomo wrote:
| The future is likely a GPT-plus-level model, browsing-enabled,
| specialized in formulating queries, reading snippets _and_ the
| underlying web-pages.
|
| It'll take a single expressed intent, and conducts a series of
| queries, page-readings, refined queries, &
| rerankings/summarizations before providing you a synthesized
| response.
|
| In a second or two.
|
| With ads.
|
| And deeply-embedded 'sponsored recommendations'.
| seydor wrote:
| I think the most interesting use will be to connect two things.
| Like "how do i make money from reciting medieval poetry". It
| hallucinates ways to connect the two, some of which are pretty
| credible
| skilled wrote:
| Is Google in deep waters? And not only because of how good
| ChatGPT can be, but also as far as "content" goes, because from
| what I can tell the quality of writing by ChatGPT is very
| passable for articles, especially if you know the topic you're
| writing on in and out.
|
| I have been thinking about this over the weekend but I haven't
| been able to get a good feel for it on my own.
| impulser_ wrote:
| No, because they already have LaMDA which is the same thing, a
| language model for dialogs.
|
| Google could implement that into Google today, but the reason
| they don't is Google is a 200b/year business. You don't want to
| mess around with a business of that size for the fun of it.
|
| We will probably see it in Google Assistant before they add it
| too Google.
|
| OpenAI doesn't have this worry so they can put their model out
| into the public and if anything goes bad they don't lose
| anything. Google does.
| skilled wrote:
| That was my thought process too, particularly the business
| part. I find it hard to believe Google would want to give
| that up so easily. Will be interesting to see how it unfolds.
| ilaksh wrote:
| Also some Google employees have mentioned on HN that Google
| has been analyzing similar things and the compute is
| currently too expensive to make it profitable.
| visarga wrote:
| That's the real reason. And the fact that it decreases ad
| views.
| 8n4vidtmkvmk wrote:
| sounds very monetizable. any question that can be solved
| with a product.. replace that with an affiliate link.
| maybe only a 5th of the queries will be monetized, but
| the ones that are are so specific/targeted that the
| ROI/click through will be great
| mach1ne wrote:
| ChatGPT can still hallucinate stuff, so if you want to write
| anything of substance, you have to check its claims through
| Google.
| datalopers wrote:
| Google doesn't do anything to validate the search results
| lead to accurate information
| izacus wrote:
| And yet that doesn't mean Google is regularly returning
| wrong answers like Chat got is.
|
| Don't put out this intellectually lazy argument without
| considering the magnitude of error and user ability to
| mitigate it.
| oefrha wrote:
| Give it some time and the Internet will be swamped by AI-
| generated dubious crap, and at that point Google will
| lose its advantage.
| Xeophon wrote:
| The ,,news", especially in finance, is more and more
| autogenerated these days
| cma wrote:
| But Google is probably about to be massively poisoned with
| ChatGPT output. And things like this repo itself may get fed
| back in to future versions of GPT possibly impacting it over
| time.
| mach1ne wrote:
| That's a trippy thought. We're essentially writing real-
| time into the future GPT's memory.
| eclipxe wrote:
| No.
| skilled wrote:
| If you have an opinion I wouldn't mind hearing it. As I say,
| I haven't come to a conclusion myself but maybe because I
| lack the information/knowledge about it.
| mritchie712 wrote:
| I've already moved half my programming questions directly to
| ChatGPT instead of Google. This is perfect.
| transitivebs wrote:
| And here's a Twitter bot powered by ChatGPT:
| https://github.com/transitive-bullshit/chatgpt-twitter-bot
| eligro91 wrote:
| Amazing idea. Just need the browsing enabled
| xjconlyme wrote:
| It's interesting to see what's Google's next move. laMDA was also
| impressive.
| throwaway82388 wrote:
| Google seems to be holding back due to AI safety concerns, and
| the problems inherent in doing anything at Google scale. I'm
| curious to see if potential market competition will change
| that.
| spaceman_2020 wrote:
| I reckon Google is holding back more because there's no way
| to moentize this to the tune of $150B/year.
|
| No initiative can get implemented at a large publicly traded
| company if it doesn't contribute to the bottomline in some
| meaningful way _eventually_. And this thing might actually
| _hurt_ the bottomline. No bueno.
___________________________________________________________________
(page generated 2022-12-04 23:00 UTC)