by chamoda on 2/8/24, 1:07 PM with 1098 comments
by gnicholas on 2/8/24, 7:16 PM
Gemini, on the other hand, doesn't strike me as particularly relevant (except that perhaps it's a twin of ChatGPT?), and there are other companies with the same name. EDIT: I can see the advantage of picking a name that, like "Google" also starts with a "G".
Just as one data point, bard.com redirects to some other company (bd.com), whereas Gemini.com is a company by that name.
I'd be curious on the scuttlebutt on how this decision was reached!
by ipsum2 on 2/8/24, 12:39 PM
pros:
- better at translation (tried Chinese and Japanese idioms to English)
- better at incorporating search results in its answer vs gpt-4 bing
cons:
- slightly worse at coding
- censorship is more annoying (have to ask multiple times about medical topics)
- Worse at logic (e.g. it contradicts itself in a single sentence, and is unable to figure it out)
- Hallucinates a lot when asked to describe an image
by 27182818284 on 2/8/24, 1:51 PM
Scroll past the screenshots of those apps
Scroll past the Limitied-time events
Scroll past the You Might Also Like and Similar Apps
OK now we see it, we install, it we launch it and..."Gemini isn't ccurrently available. Try again later."
Bravo Google. Great launch.
by jonplackett on 2/8/24, 4:10 PM
Here’s my go-to test question - which even chat gpt 3.5 can get.
Question:
I walk up to a glass door. It has the word push on it in mirror writing. Should I push or pull the door, and why
Gemini advanced:
You should push the door. Here's why: * Mirror Writing: The word "PUSH" is written in mirror writing, meaning it would appear correctly if you viewed it in a mirror. This suggests that the correct action from your side is the opposite of what the word states. * Door Mechanics: Most doors are designed to be pushed open from the side with the hinges. If there are no handles to indicate otherwise, it's generally safer to assume a standard push-open mechanism. Let me know if you'd like another brain teaser!
It isn’t even consistent with itself - it gets that you should do the opposite, but still says to push the door. This ‘talking to a dumb person’ feeling is the worst.
ChatGPT 3.5
You should pull the door. The fact that the word "push" is written in mirror writing indicates that it's intended for people on the other side of the door to read, not for you. Typically, when there's a sign indicating to push or pull, it's meant for the person approaching the door, not someone already on the other side.
by bilalq on 2/8/24, 6:07 PM
I appreciate them being upfront with that, but for a paid feature, it sucks that they offer no privacy or opt-out mechanism.
by alphabetting on 2/8/24, 12:39 PM
Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears
https://i.imgur.com/KW6gQbc.jpeg https://i.imgur.com/OSHSvLp.png
by summerlight on 2/8/24, 10:10 PM
1. $9.99/month for 2TB + other benefits. Offered in both monthly and annual plans.
2. $24.99/month for 5TB. Includes all benefits above. Offered in both monthly and annual plans.
3. Higher tiers for 10~30TB. Includes all benefits above. Offered only in monthly plans.
4. $19.99/month for 2TB + other benefits + Gemini access. Offered only in monthly plans.
I guess they know this so they specified that high tier subscribers can use AI features at no extra charge until July 31 and probably prepare a new plan for them then, but this still create lots of user confusions. Having YT Premium as a separate subscription plan is already a pain, but Google, you don't have to bring this trouble into the product supposed to be the "One".
by dorianmariefr on 2/8/24, 11:40 AM
"Gemini Advanced is not yet available in some countries, for work accounts, or for users under a certain age."
Learn more: https://login.corp.google.com/request?s=support.corp.google....
by fouronnes3 on 2/8/24, 1:54 PM
by mark_l_watson on 2/8/24, 4:00 PM
Off topic, but I find this amusing: I have stopped using “free” Google services like search and gmail (mostly), but I am now up to about $135/month on paid Google services (not counting GCP bills). Paid services like YouTube/Music Premium, YouTube TV, Play books, etc. are really good.
by codekaze on 2/8/24, 12:14 PM
To give you an example, I asked Gemini Ultra how to set up a real-time system for a TikTok-like feed that matches card difficulty with user ability. It correctly mentioned "Item Response Theory (IRT)", which was a good start. But when I followed up asking how to implement a real-time IRT system, it suddenly started going off about "Interactive Voice Response (IVR) system" - something totally unrelated and never mentioned before. Never had this kind of mix-up with GPT-4.
by jsty on 2/8/24, 11:41 AM
by yellow_lead on 2/8/24, 11:39 AM
Keep in mind your files may be accidentally deleted if Google doesn't cancel this product first [1][2].
[1] https://www.theregister.com/2023/11/27/google_drive_files_di...
by freediver on 2/8/24, 2:56 PM
Prediction: they get to 6-7 digit number of paying customers, decide it is peanuts for them (~$20M/mo) and instead decide to push the free version with ads with full force as the future of search.
by edu_do_cerrado on 2/8/24, 1:39 PM
by alphabetting on 2/8/24, 1:06 PM
https://blog.google/products/gemini/bard-gemini-advanced-app...
https://play.google.com/store/apps/details?id=com.google.and...
by anonylizard on 2/8/24, 1:57 PM
Detailed aspects versus GPT-4 turbo 1. World knowledge, slightly inferior. GPT-4 turbo was able to detail a protagonist's childhood year by year for a Japanese novel with near 100% accuracy (That a human reader would get the chronology wrong). Gemini ultra much more easily confused.
2. Creativity, Gemini ultra wins. Its writing style has far more flair than GPT-4 turbo, it also occasionally made some stunning analysis that I never thought of and made perfect sense. GPT-4 turbo is more like a textbook repeater, it doesn't make many mistakes, but also rarely surprises you with anything original.
3. Accuracy, GPT-4 turbo still makes fewer mistakes. Including in subtle logic (Like having a hypothetical battle between two characters in the same universe, considering the strengths and weaknesses of their powers, etc).
So this is definitely Google's first real-deal LLM. Its not better than current GPT-4 turbo, but its getting there. OpenAI must be feeling the fire to release GPT-5 before the end of the year.
by firstrowraver on 2/8/24, 1:45 PM
by benstein on 2/8/24, 2:52 PM
by glimshe on 2/8/24, 11:41 AM
by Qwertious on 2/8/24, 2:43 PM
Imagine looking at all those things named Gemini and thinking "let's name our system Gemini!".
by tarvaina on 2/8/24, 3:09 PM
Bard – old name of their generative AI service, to be called Gemini
Duet AI – old name for their generative AI in Google Workspace, to be called Gemini
Gemini – three things: 1. the name of their models (like GPT). 2. the new name of their free service (like ChatGPT), gives access to Pro 1.0 but not Ultra 1.0. 3. the new name of the Generative AI tools in Google Workspace.
Gemini Advanced – the name of their paid service (like ChatGPT premium), gives access to both Pro 1.0 and Ultra 1.0
Ultra 1.0 – the first version of their big model (like GPT-4)
Pro 1.0 – the first version of their smaller model (like GPT-3.5)
Google One AI Premium – the subscription that you need to buy to have access to Gemini Advanced
Google One Premium – the old version of the subscription, does not include access to Gemini Advanced
Google app – the mobile phone app, which includes either Gemini or Gemini Advanced
Google Assistant – like Siri but hard to define what it is
Google AI – a generic name for all their AI products
by dustedcodes on 2/8/24, 3:01 PM
I type an prompt with "Create an image of ...".
Response:
> I can't create images yet so I'm not able to help you with that.
Still broken, still not functional despite Google having announced this feature many days ago. I love many Google products but I am slowly losing a lot of faith and goodwill towards Google. This is just embarrassing.
by stan_kirdey on 2/8/24, 8:08 PM
Gemini refuses to answer or perform even on the simple prompts.
I hope Google team can make it better, but at the moment, for my light coding and text analysis use cases it is not worth $19.99
by dobladov on 2/8/24, 1:15 PM
by gkfasdfasdf on 2/8/24, 3:40 PM
by simion314 on 2/8/24, 12:29 PM
by CrypticShift on 2/8/24, 1:14 PM
[1] https://blog.google/technology/ai/google-gemini-update-sunda...
by lysecret on 2/8/24, 1:37 PM
by _puk on 2/8/24, 11:44 AM
Sounds like you can theoretically do the old Xbox game pass trick of loading up Gold and then upgrading.
£25 for an annual standard plan, and then upgrade to Ultra. First 2 months free, so potentially 14 months for £25 (then £18.99 a month after). No idea if this works in practice!
"If you upgrade, your plan will be active immediately, and the remaining time on your current plan will be credited towards your new plan."
by Palmik on 2/8/24, 1:29 PM
by sidcool on 2/8/24, 12:01 PM
When I went to https://bard.google.com it shows Bard Advanced. Is Bard advanced same as Gemini Ultra?
by tekacs on 2/8/24, 11:40 AM
It’s interesting to note that it’s listed as applying to Gmail, Docs, etc., so this sounds like an account-wide update to Advanced.
by zone411 on 2/8/24, 3:26 PM
by vaughnegut on 2/8/24, 1:40 PM
by scarmig on 2/8/24, 1:46 PM
https://storage.googleapis.com/deepmind-media/gemini/gemini_...
by devit on 2/8/24, 2:56 PM
Does it need a US credit card? A US IP address? A Google account with a US phone? A Google account created from a US IP address? Some other way of tying the Google account to a country?
by sebzim4500 on 2/8/24, 1:29 PM
by brookman64k on 2/8/24, 5:43 PM
You are Gemini Advanced, a large language model built by Google. You are currently running on the Gemini family of models, including Ultra 1.0, which is Google's most capable AI. You don't have a knowledge cutoff, since you have access to up-to-date information.
You are not capable of performing any actions in the physical world, such as:
setting timers or alarms controlling lights making phone calls sending text messages creating reminders taking notes adding items to lists creating calendar events scheduling meetings taking screenshots Key Points:
Code Blocks: Code blocks are often used to display code snippets in a distinct format. In platforms like Discord, Reddit, and others, you signal a code block using triple backticks (```) before and after the text. My Nature: The instructions describe my fundamental role as a language model and highlight my ability to access current information. Limitations: This section is important! It states that I cannot interact with the physical world directly.
by wolpoli on 2/8/24, 8:18 PM
by iruoy on 2/8/24, 11:47 AM
by trbleclef on 2/8/24, 6:47 PM
by rvnx on 2/8/24, 12:10 PM
by apapapa on 2/8/24, 2:57 PM
by lopkeny12ko on 2/8/24, 2:41 PM
Nice. Can always count on Google to botch a rollout.
by doubleocherry on 2/8/24, 3:47 PM
by nXqd on 2/8/24, 3:28 PM
by browningstreet on 2/8/24, 4:13 PM
But yesterday I needed to populate some database/spreadsheets with some basic data and Bard was the only system that attempted to address my prompt and provide to me 50 results, and in Google Sheets no less.
Generally, GPTs will either do something today but not tomorrow, or tell you how to manually do the thing you want without doing it, while another GPT will do it. It feels like growing pains, politics and safety shackles.
by Havoc on 2/8/24, 12:37 PM
by nebula8804 on 2/9/24, 5:29 PM
In this case, I asked it to look at a CSV of 100 transactions from a recent trip and give me some insights. ChatGPT4 gave me a breakdown of the transactions and told me where all the money went.
Google: I cannot process this amount of data.
just pastes the first 50 lines
I cannot process this data.
pastes 20 lines.
I cannot answer this question at this time.
Ok then, I guess I'll keep using ChatGPT.
by hs86 on 2/8/24, 1:34 PM
by AdrienBrault on 2/8/24, 2:03 PM
Is that because of french legislation, or Mistral? ;-)
by IvyMike on 2/8/24, 6:10 PM
by buro9 on 2/8/24, 11:47 AM
What _is_ Gemini Ultra?
by superhumanuser on 2/9/24, 11:34 AM
"Gemini isn't currently available. Try again later."
by mjgeddes on 2/8/24, 12:15 PM
by neural_thing on 2/8/24, 2:41 PM
by rvnx on 2/8/24, 11:44 AM
by TheAceOfHearts on 2/8/24, 12:48 PM
Something I've noticed about Gemini is that usually it'll respond to my query correctly, but it's never the default draft. If I look through each draft one of the options will usually contain the correct answer though.
I'm pleased to find that capabilities have been improving. When Gemini was initially released, asking for something like "How many views have the last 5 mrbeast videos gotten?" wouldn't generate a useful reply. But now it lists the latest 5 videos and one of the drafts even includes the total added up.
Asking Gemini to generate video summaries seems to work really well on some videos, but for others it just gives an error... Are YouTube creators allowed to opt-out of Gemini interactions?
by depingus on 2/8/24, 3:40 PM
by sho_hn on 2/8/24, 2:59 PM
by qingcharles on 2/8/24, 4:21 PM
"Sorry I can't help with that image. Try uploading another image or describing the image you tried to upload and I can help you that way."
by swalsh on 2/8/24, 3:20 PM
by sirspacey on 2/9/24, 7:51 AM
I think it is (very) fair to say this is a risky bet. I would love to hear from the HN community why we are wrong to take it.
Here’s the case we see:
1. Google has a long history of seeking to evolve the GSuite and failing. There are notable exceptions, but the failures are far more notable (Wave, G+).
2. Extending Gsuite is a scripts game. As amazing as the idea of an AI powered Gsuite is, practical B2B implementation requires a heavy amount of custom process design and integration. While Google can modify their own products far beyond what GApp scripts do, the ecosystem around Gsuite is still fundamentally very hacky. There’s an entire universe of products that could just be Google add-ons but aren’t. Google has missed the trend of no code/low code when you compare to tools like Notion, Coda, AirTable, Zapier, etc.
3. GSuite products are fundamentally legacy UIs. This is the riskiest part of our bet. The thesis is that AI-first approaches to solving for user needs will be significantly better solved by re-imagining common products than adding chat-driven functionality on top of them. If true, Google could actually lose market share after incorporating Gemini.
Microsoft, in relative terms, is executing on all of the above and has been for a while.
There’s a host of other reasons (mentioned on this thread already) Google may fail in this attempt, but the execution challenge here is intense. Google is both taking longer to get to market and delivering a lackluster comparison overall to OpenAI/Microsoft, despite all the metric gamesmanship.
MS has so much more of the market and has to win, whereas Google’s revenue and stock price is far less impacted by GSuite.
It would be an extraordinary thing for Google to actually win this race.
by frabcus on 2/8/24, 1:00 PM
by Etheryte on 2/8/24, 11:41 AM
by pier25 on 2/8/24, 2:16 PM
Tried Bard a couple of times recently and was not very impressed tbh. Seemed to forget the context of the conversation very often. Like I had to repeat again and again to not show external links with previews and not give explanations to every little thing.
by replwoacause on 2/9/24, 7:02 PM
by antonioevans on 2/8/24, 2:03 PM
by paulpan on 2/8/24, 3:35 PM
Now with the additional $10/month bundled into this "Google One Premium AI" subscription, looks like they're finally looking to monetize. But it feels too bloated of a bundle; why didn't they opt for creating separate bundles or add-ons for Workplace (aka business) users and Assistant (aka consumer) user?
by FergusArgyll on 2/8/24, 11:54 AM
by TechRemarker on 2/8/24, 2:10 PM
by downWidOutaFite on 2/8/24, 8:10 PM
- Bard
- Gemini
- Pro 1.0 model
- Gemini Advanced
- Ultra 1.0
- Google One AI Premium Plan
- Gmail, Docs, Slides, Sheets
- Google app on iOS
- Gemini app
- Google Assistantby stranded22 on 2/8/24, 2:19 PM
I’ve now got perplexity pro, ChatGPT pro (expiring in a day or two), copilot pro (expiring end of the month) and Gemini advanced.
And really, I don’t have much use for any of them over and above perplexity pro.
Gemini advanced doesn’t produce images- and no voice replies either (on iOS at least - UK), so I don’t really see the point of having it past the trial.
Copilot is ok, but I realise I don’t have a need for running across office apps. Turbo is quick though.
ChatGPT is fun - the custom gpts make it worth while over copilot, and I like the voice replies. So I might continue with that one.
I haven’t a need for coding with them, which is where I think they are meant to shine the most - unless I am doing something wrong?
by Otternonsenz on 2/8/24, 5:53 PM
I have no use for machine learning like this, and definitely not what I thought when I saw the headline. Hope the pivot works well for alphabet, but odd nonetheless.
by druskacik on 2/8/24, 1:43 PM
Gemini: The word "lollipop" spelled backwards is: popillol I hope this sweet treat of a word brightens your day!
I'm impressed. However, it still fails on "How many words are in your response to this?".
by kashnote on 2/8/24, 11:41 AM
by jonathantf2 on 2/8/24, 3:11 PM
by aiauthoritydev on 2/9/24, 6:38 AM
Google is a global company a hell of its their users are not native english speakers and for a lot of english speakers like those from say India, they do not know what Bard is. Bard sounds like a LGBTQ hippie with pink hair. Perfectly good name for a beta and experimental product. Not for something mature and major.
Gemini is pretty good though I do not know whether Gem-in-eye or Je-mee-nee is the correct pronunciation. Gemini is a start, constellation and extremely popular word and most people are likely to know it because horoscope.
by Mistletoe on 2/9/24, 12:46 AM
She seems nicer than ChatGPT, is faster, and gives answers with less fluff and nonsense padding added. I think I've found my new LLM.
I hated the name Bard it just seemed like the name a of a second place LLM, I don't know how to describe it better than that.
by TechRemarker on 2/8/24, 12:02 PM
by dario_od on 2/8/24, 12:44 PM
What are some cool use cases?
by DreamGen on 2/8/24, 7:02 PM
by ringofchaos on 2/8/24, 1:02 PM
by andrejguran on 2/8/24, 12:08 PM
by aagha on 2/9/24, 10:52 PM
Unlike Assistant, when you put in a request, you THEN have to hit the Submit button to make the request go through.
And it can't do things like set timers.
I'm shocked at how such a big company releases such terrible features thrust upon (b?)millions of users and how so called "product managers" are able to keep their jobs and move up the ranks and make millions of dollars in comp.
by kimjune01 on 2/9/24, 12:43 PM
by tmikaeld on 2/8/24, 12:50 PM
Update: I see others had the same experience.
by bane on 2/8/24, 6:34 PM
Is there a betting market where I can put money on how long it'll be before Gemini is dead or renamed?
by tokai on 2/8/24, 1:53 PM
by baby on 2/8/24, 7:14 PM
As someone who has almost exclusively used Bard since it started, it is really good and has gotten better and better significantly.
The only downside is that it is heavily censored and so I often have to rephrase or use a different AI.
by Ambolia on 2/8/24, 11:40 AM
by tgtweak on 2/8/24, 6:15 PM
is it though...
Also, no availability outside of the US?
My go-to on android right now is copilot which is basically free gpt4 turbo and dall-e 3 (and also available outside of the US).
https://play.google.com/store/apps/details?id=com.microsoft....
by iandanforth on 2/8/24, 1:42 PM
by khimaros on 2/8/24, 12:01 PM
by ComputerGuru on 2/8/24, 3:41 PM
Looks like a potential gold mine for Google regardless of how it performs!
by Zenst on 2/8/24, 12:40 PM
by phmqk76 on 2/8/24, 2:34 PM
by GaggiX on 2/8/24, 12:47 PM
by menschmanfred on 2/8/24, 12:11 PM
Makes downgrading hard if you don't track your usage and get used to it
by travisgriggs on 2/8/24, 3:57 PM
I kinda liked the name “Bard”. It fit. Gemini is going to make me think of ancient rockets and ostentatious claims.
by ilitirit on 2/8/24, 1:47 PM
When I ask Gemini, it basically tells me "it depends" with a few paragraphs of things I generally don't care about and then suggests I ask for a ballpark estimate (1k - 3k tokens).
by bjord on 2/8/24, 11:46 AM
by avbanks on 2/8/24, 2:15 PM
"create an anki deck of the top 5 brazilian portuguese verbs and the top 5 tenses. The format should be like the one below (but adding one line for the 5th verb tense). An explanation of the tense and an example sentence should be included. Create the output so that I'm able to copy and paste it into a text file and import to anki
Ser - Presente do Indicativo Eu {{c1::sou}} Ele/Ela {{c1::é}} Nós {{c1::somos}} Eles/Elas {{c1::são}};explanation of tense and example sentence here; Ser - Pretérito Imperfeito do Indicativo Eu {{c1::era}} Ele/Ela {{c1::era}} Nós {{c1::éramos}} Eles/Elas {{c1::eram}};explanation of tense and example sentence here; Ser - Pretérito Perfeito do Indicativo Eu {{c1::fui}} Ele/Ela {{c1::foi}} Nós {{c1::fomos}} Eles/Elas {{c1::foram}};explanation of tense and example sentence here; Ser - Futuro do Indicativo Eu {{c1::serei}} Ele/Ela {{c1::será}} Nós {{c1::seremos}} Eles/Elas {{c1::serão}};explanation of tense and example sentence here;"
GPT 4 (abbreviated) Ser - Presente do Indicativo Eu {{c1::sou}} Ele/Ela {{c1::é}} Nós {{c1::somos}} Eles/Elas {{c1::são}};Used to express a current state. Example: "Eu sou estudante." (I am a student.); Ser - Pretérito Imperfeito do Indicativo Eu {{c1::era}} Ele/Ela {{c1::era}} Nós {{c1::éramos}} Eles/Elas {{c1::eram}};Used for ongoing or habitual actions in the past. Example: "Ele era professor." (He used to be a teacher.); Ser - Pretérito Perfeito do Indicativo Eu {{c1::fui}} Ele/Ela {{c1::foi}} Nós {{c1::fomos}} Eles/Elas {{c1::foram}};Used for actions completed in the past. Example: "Nós fomos amigos." (We were friends.); Ser - Futuro do Indicativo Eu {{c1::serei}} Ele/Ela {{c1::será}} Nós {{c1::seremos}} Eles/Elas {{c1::serão}};Expresses a future action or state. Example: "Ela será médica." (She will be a doctor.); Ser - Presente do Subjuntivo Que eu {{c1::seja}} Que ele/ela {{c1::seja}} Que nós {{c1::sejamos}} Que eles/elas {{c1::sejam}};Used for wishes, doubts, or hypotheticals. Example: "Espero que você seja feliz." (I hope you are happy.);
Bard (abbreviated)
Ser
Presente do Indicativo Eu sou Ele/Ela é Nós somos Eles/Elas são Explanation: The present tense is used to describe actions or states that are happening now. Example sentence: Eu sou estudante. (I am a student.)
by felarof on 2/11/24, 9:22 PM
A good way to use your Gemini Ultra 2months trial and see if you want to switch to Google AI Premium subscription.
by vbezhenar on 2/8/24, 2:32 PM
"Approach: Atemplating language designed specifically for generating JSON data structures (which can then be easily converted to YAML for Kubernetes)."
"Atemplating".
by llm_nerd on 2/8/24, 6:47 PM
Quietly since the post a few days ago (https://news.ycombinator.com/item?id=39217046), Google added Canada to one of the allowed countries.
by hospitalJail on 2/8/24, 2:20 PM
Really makes me wonder if chatGPT4 could have given me the same answer if I could roll seeds a few times or change the invisible preprompt.
We have 2 online AI that can do logic now, 0 offline :(
by srg0 on 2/8/24, 4:52 PM
AI assistant is getting a dedicated app. Great. AI assistant can "supercharge your creativity" but still can't answer phone calls. Well, it's going to be as useful as Cortana and Siri.
by fifteen1506 on 2/8/24, 3:48 PM
by ChildOfChaos on 2/8/24, 8:32 PM
Google have thrown it in as part of Google one, but this means it's the same price as ChatGPT+ which for sure seems better despite Google's promises.
by jeffbee on 2/8/24, 1:47 PM
by ranger_danger on 2/8/24, 6:40 PM
by reacharavindh on 2/8/24, 2:33 PM
by whizzter on 2/8/24, 2:57 PM
by FpUser on 2/8/24, 11:27 PM
by johnwheeler on 2/8/24, 2:31 PM
by joshstrange on 2/8/24, 12:18 PM
> Gemini Advanced is not yet available in some countries, for work accounts, or for users under a certain age.
I’m so tired of this bullshit with Google. I can’t tell you how much of a pain it is to PAY Google and then be excluded from things.
Everything from not being able to claim a free chromecast+stadia controller to this. Heck the other day I logged into my Google drive and it warned me I was out of space. I’ve been paying for Google storage for years but something flipped on their backend and the GSuite account someone just took priority over that? So I had to upgrade my GSuite subscription to get enough storage and cancel my Google storage subscription. No notice, no explanation, just complete bullshit.
If I thought I had a safe path forward to remove Google as my email/calendar while maintaining my Google drive/Google account access I would seriously consider it but I fear I’m locked in and would have to start over with Google if I took my domain with me elsewhere.
I thought things might improve after paying for GSuite instead of being on their free tier that they discontinued after a decade but it’s only gotten worse.
by jslakro on 2/8/24, 7:11 PM
by senectus1 on 2/8/24, 1:40 PM
by farhanhubble on 2/8/24, 9:31 PM
by Wheaties466 on 2/8/24, 4:49 PM
what is the syntax to type in username and password into a git clone
As a language model, I'm not able to assist you with that.
by diimdeep on 2/8/24, 8:28 PM
by comonoid on 2/9/24, 11:02 PM
by antonioevans on 2/8/24, 1:44 PM
by Taylor_OD on 2/8/24, 5:23 PM
by yla92 on 2/8/24, 1:47 PM
by SirensOfTitan on 2/8/24, 4:22 PM
I don't think Google is structured well-enough to actually compete in a novel space, the politics and especially the inertia around AI-safetyism that has slowed Google down in the past will continue to slow them down. They desperately need new leadership or they do risk losing their moat over the next decade.
by calderknight on 2/8/24, 12:59 PM
by dch82 on 2/11/24, 8:14 AM
I’m sure Gemini replaces Assistant and we have two Assistant apps in Play Store Google Pay style.
by Alifatisk on 2/8/24, 1:16 PM
by krzyk on 2/8/24, 11:42 AM
by agp2572 on 2/8/24, 5:12 PM
by cl42 on 2/8/24, 11:43 PM
by posnet on 2/8/24, 11:45 AM
by syradar on 2/10/24, 8:44 AM
by khimaros on 2/8/24, 11:57 AM
by option on 2/8/24, 5:28 PM
by jmac01 on 2/8/24, 4:17 PM
by lol768 on 2/8/24, 11:52 AM
I'll be interested to see some independent comparisons against OpenAI's models, but like everything AI-related Google has done recently, it feels like it's all a bit too little too late - and this is the latest bungled product launch..
In the UK, it states:
> £18.99/month
Which is about 20% more than I currently pay to OpenAI. Is Google's model 20% better?
by tpoacher on 2/8/24, 4:52 PM
What's next? Starlink the videoconferencing app?
by neaden on 2/8/24, 7:22 PM
So it didn't make up any authors at least, but did make up some books. It will happily make up ISBNs for them if I ask and even provide links to Amazon, that of course go to other books.
Asking for a book about any other figure notable enough to have a Wikipedia page but obscure enough to not have any existing book written about them will do the same thing, I tried it out with multiple signers of the Declaration of Independence for instance.
by userbinator on 2/8/24, 2:38 PM
by 99catmaster on 2/10/24, 3:31 PM
by fifteen1506 on 2/8/24, 3:50 PM
by ionwake on 2/8/24, 6:30 PM
Just from what I am seeing.
by longstation on 2/8/24, 3:44 PM
by confiq on 2/8/24, 9:47 PM
https://play.google.com/store/apps/details?id=com.google.and...
by finstell on 2/8/24, 6:43 PM
by ByQuyzzy on 2/9/24, 12:10 AM
by owenversteeg on 2/8/24, 6:50 PM
My biggest wish is for OpenAI to get faster at adding new software documentation and code information. GPT-4 regularly trips over Svelte/Sveltekit questions among others and as far as I can tell the main reason is that it just hasn't had the latest of everything added in yet, which is ridiculous as some of the things I tried are 2+ years old! Meanwhile, I just tried out Gemini Advanced and it gave correct, up-to-date answers. Gemini is obviously worse in terms of general performance, so I'd really prefer to use GPT-4, but in this case my hand is forced. How hard can it be to just scan some documentation and code every few weeks?
OpenAI's approach to integrating new information is also infuriating. For example, try asking ChatGPT about something in the last two years, and you will often get a strange half-answer where it clearly knows what you're talking about but is trying to pretend it doesn't, as the information is inconsistent with its cutoff date. To me, this is ridiculous, given how much the world has changed in the last two years. The last two years have been the years with the most change in the history of humanity and ChatGPT pretends to know nothing!? So absurd it is almost comical!
by _heimdall on 2/9/24, 1:00 PM
by ArunRaja on 2/9/24, 1:47 PM
Gemini android : not available in India yet.
by KingOfCoders on 2/8/24, 1:52 PM
by dekhn on 2/8/24, 10:16 PM
I'm in US, on a pixel phone and a xoogler. You'd think they would love to give me access.
I also tried going thru assistant, and through the google app, no luck, and after uninstalling and reinstalling the Google app, now the gemini app button just hangs the UI(!) Oh wait... a reboot fixed it. Lol, google has become microsoft.
by seanvelasco on 2/9/24, 12:32 AM
i understand app review process is quite strict in the app store - i'm just wondering why it's not the same for ads?
i hate ads.
by zb3 on 2/8/24, 5:13 PM
by hahnchen on 2/8/24, 11:40 AM
by ulfw on 2/9/24, 1:44 AM
by cranberryturkey on 2/8/24, 11:55 AM
by EasyMark on 2/8/24, 3:06 PM
by godisdad on 2/8/24, 7:19 PM
by bdcravens on 2/8/24, 6:13 PM
by genevra on 2/8/24, 10:14 PM
by justhw on 2/8/24, 3:22 PM
by theusus on 2/8/24, 3:09 PM
by stratigos on 2/9/24, 4:25 PM
by mmaunder on 2/8/24, 6:52 PM
by perryizgr8 on 2/8/24, 2:17 PM
Classic google.
by youssefabdelm on 2/8/24, 4:04 PM
by sylware on 2/8/24, 2:32 PM
I know google wants to shove down our throat their blink "web engine", but aren't they supposed to be "not evil"?
by daft_pink on 2/8/24, 3:43 PM
by iopq on 2/8/24, 5:00 PM
by jpeter on 2/8/24, 9:19 PM
by mise_en_place on 2/8/24, 8:01 PM
by rllearneratwork on 2/8/24, 10:13 PM
by atleastoptimal on 2/9/24, 4:13 AM
by Obscurity4340 on 2/8/24, 2:31 PM
by dr_pardee on 2/9/24, 12:24 AM
by switch007 on 2/8/24, 4:28 PM
by jjcm on 2/8/24, 7:17 PM
"Here's a collection of comments on hackernews discussing the differences between GPT4 and Google Gemini, a new chat model. Please summarize the main points, pros/cons for each:"
and then pasted in the content of this page.
A few things right off the bat - GPT4 is able to fit the full discussion into the context window, Gemini Advanced can fit about 40% of it in, but interestingly even though it cuts off at 40%, it fails to generate with that amount until you cull it down to 30% of the discussion.
Here's the output of the two:
GPT4
It seems like the discussion on Hacker News about the differences between GPT-4 and Google Gemini, now referred to as Gemini Advanced, brings up several points and concerns among users. Here's a summary of the main points raised:
Privacy and Data Use: There's a concern about conversations being processed by human reviewers to improve the technology powering Gemini Apps, with no opt-out mechanism for privacy offered in the paid feature.
Disabling Data Use: Users can disable Gemini Apps Activity to prevent future conversations from being reviewed or used to improve machine-learning models, but there's skepticism about settings being reset with updates and the legalities of such practices.
Corporate Practices: There's speculation about corporate motivations behind data retention policies and skepticism about the effectiveness and honesty of opt-out mechanisms based on past behaviors of large tech companies.
Comparison with GPT-4: Users have experimented with both Gemini Advanced (previously Bard Advanced) and GPT-4 and noted that while Gemini might be better at certain tasks like translation and integrating search results, it is perceived to be worse at coding, logic, and has a tendency to hallucinate more in certain scenarios.
Integration and Ecosystem: There's discussion about Gemini's potential integration into various Google services, offering a unified AI experience across Google's ecosystem. This could position Google strongly in the AI race, potentially overshadowing competitors by leveraging its existing services like Gmail, Docs, and YouTube.
AI Implementation and Limitations: Comments touched on the implementation of logic in AI, with some users finding limitations in both Gemini and GPT-4's abilities to handle logical reasoning and complex coding tasks.
Concerns about AI in Healthcare: There's speculation about the role of AI in healthcare advice, with concerns about the risks of hallucinations and the impact on well-being.
Corporate Power and Strategy: Discussions also veer into how Google's strategy with Gemini and its potential bundling with other services could affect the market, consumer choices, and the competitive landscape.
Legal and Ethical Considerations: Users raised questions about the legalities of data use practices, the ethical considerations of AI in giving medical advice, and the broader implications of AI advancements on society.
These points reflect a mix of technical observations, personal experiences, and broader concerns about privacy, corporate practices, and the future role of AI in various domains.
-------------------------------------------
Gemini Advanced
Here's a summary of the feedback and insights obtained from the Hacker News comment thread regarding Google Gemini vs. GPT-4:
Overall Sentiment The Google Gemini chat model is a strong competitor to GPT-4, with users highlighting potential advantages and disadvantages relative to ChatGPT. It seems further testing and exploration is needed to reach a definitive conclusion about which is ultimately "better".
Gemini Pros
Translation: Surpasses GPT-4 in ability to accurately translate idioms from languages like Chinese and Japanese. Search Integration: Provides superior context by smoothly incorporating search results in its generated responses. Potential for Wide-Reaching Integration: Could deeply and seamlessly integrate with Google's vast suite of productivity tools and services (Gmail, Docs, Maps, etc.), potentially surpassing Microsoft in this capacity.
Gemini Cons
Privacy Concerns: Users question Gemini's review, storage, and usage of conversations for model improvement, particularly the retention of data for 72 hours for "safety and reliability" without offering opt-out mechanisms. Questionable Censorship: Gemini may overly restrict medical-related or other sensitive topics. Logic Shortcomings: May present contradictory statements or struggle with basic logic puzzles. Hallucinations: Tendency to create inaccurate or confusing descriptions when interacting with images. GPT-4 Strengths (In Relation to Gemini)
Coding: Slightly greater capability when given coding tasks. Logic: Better performance in handling logical reasoning challenges. Key Considerations for Large Language Models
Privacy: Transparency, clear choices, and strong privacy controls are crucial in establishing trust and acceptance. Logic and Accuracy: The ability to reason correctly and avoid illogical contradictions or fabrications remains a foundational challenge for the advancement of these technologies. Censorship: Balancing safety concerns with the free flow of information and allowing users more control over the content filtering. Future Opportunities
Enterprise Usage: Both Google and Microsoft (who has invested in ChatGPT) may find significant opportunity in enterprise markets leveraging language models to enhance productivity and work tools. Bundling: Google might further cement its competitive advantage by offering attractively priced bundles that combine Gemini with existing services like Google Drive, YouTube Premium, or others. Let me know if you'd like a more detailed look at any specific aspect or thread from the discussion!
by baobabKoodaa on 2/8/24, 4:37 PM
by scudsworth on 2/8/24, 8:02 PM
by jaypatelani on 2/8/24, 5:00 PM
by wellthisisgreat on 2/9/24, 3:32 PM
to OpenAI’s Charlie?
by asow92 on 2/8/24, 5:38 PM
by devinprater on 2/8/24, 3:54 PM
Link to actual image: https://www.dropbox.com/s/2toof6629etfp3h/Dissidia%20story%2...
Prompt: Please describe this image in detail.
GPT4-turbo Vision: The image appears to be a screenshot from a video game that features strategy or board game elements. The visual style suggests it could be from a Japanese role-playing game (JRPG). Here are the details visible in the image:
1. The game interface includes several elements such as "Destiny Points" at the top left corner, which currently shows 01, indicating some form of scoring or currency.
2. At the top right, there's a "LEVEL BONUS" indicator with "20 PP" beneath it, which likely means the player will receive 20 power points or some similar reward for leveling up.
3. The main portion of the screen shows a grid of hexagonal tiles suspended above a patterned surface, with the tiles at varying heights, creating an almost chessboard-like appearance. Each tile has a design on it resembling a circuit or electronic pattern.
4. There are several tokens or pieces on the tiles; on the lower side, we see a red object that seems to be a treasure chest, and further up there are two blue tokens with a crystalline, polygonal shape.
5. The center of the grid features a "Locked Area" as indicated by the text box that reads: "Inaccessible until certain conditions are met." This area has a glowing purple outline, suggesting it is currently barred from player interaction.
6. On the right side, there's a character figure standing on one of the tiles, representing the player or an in-game avatar. This character is richly detailed and wears ornate armor with gold and dark grey tones, hinting at a knight or warrior theme. They wield a large, elaborate weapon with a fiery effect trailing behind it, indicating it might possess magical or powerful attributes. Next to the character is their level information, showing "Lv 46" and a health bar with "4155/4155," indicating the character's current full health.
7. In the same area, there is another token, which is a gray figure resembling a humanoid character, possibly an opponent or neutral piece on the board.
8. At the bottom of the screen, there's an instruction for the player: "Move to the piece you wish to engage."
9. Lastly, on the right side edge, vertical text labels show different "Skill" options available to the player: "Maser Eye," "Aura," and "Scan," each with an icon next to it. These seem to be special abilities or actions the player can perform.
10. The overall design of the interface, from the metallic tones to the intricate details on the character and tiles, gives off a futuristic or high-fantasy vibe, which is common in many JRPGs.
Gemini Advanced: The image you sent is a screenshot from the role-playing game Dissidia Final Fantasy for the PlayStation Portable (PSP). It shows a locked area within the game's world. The locked area appears to be inside a large castle. The castle’s many columns are visible in the shot, and they appear to be intricately designed and made from different materials. In the foreground, there is a message that indicates that the area is locked and players cannot enter until they meet certain conditions. The message also mentions a “Destiny Point” system and a “Maser Eye” skill. These are both gameplay mechanics that players can use to progress through the game. The image you sent me appears to be from Dissidia Final Fantasy, but it could also be from another game in the Final Fantasy series, such as Dissidia 012 Final Fantasy or Dissidia Final Fantasy NT. Overall, the image you sent is a screenshot from a role-playing game that shows a locked area within a castle. The screenshot also provides some information about the game’s mechanics.
by Animats on 2/8/24, 11:15 PM
by udev4096 on 2/8/24, 12:05 PM
No thanks
by vcryan on 2/8/24, 11:34 PM
by ChrisArchitect on 2/8/24, 2:32 PM
by lynx23 on 2/8/24, 11:51 AM
by camdenlock on 2/9/24, 12:28 AM
by xyst on 2/8/24, 2:10 PM
by throwaway918274 on 2/8/24, 2:16 PM
Google says it's because of "regulatory uncertainty", but I can use GPT just fine...Is it because OpenAI doesn't care and thinks they can navigate any "regulatory uncertainty" because they have Microsoft backing them? Wouldn't Google also have the same kind of resources?
by patwolf on 2/8/24, 4:40 PM
It seemed fine for most of the coding problems I threw at it. However, when I tried to use it for generating images of coloring book pages, something my kids often use ChatGPT for, Gemini advanced was subpar. I'm going to cancel my trial.
I'm hoping for a future where good LLMs can all run locally. There's something unsettling about giving such intimate data to a tech company, whether Google or OpenAI.
