"Extensions" and integration into the rest of the Google ecosystem could be how Bard wins at the end of the day. There are many tasks where I'd prefer an integration with my email/docs over a slightly smarter LLM. Unlike ChatGPT plugins, Google has the luxury of finetuning its model for each of their integrations.
The new feature for enriching outputs with citations from Google Search is also pretty cool.
Yes, exactly. Integration is where the real power of these agents can live.
I really want an agent that can help me with pretty simple tasks
- Hey agent, remember this link and that it is about hyper fast, solar powered, vine ripened, retroencabulators.
- Hey agent, remember that me and Bob Retal talked about stories JIRA-42 and JIRA-72 and we agreed to take actions XYZ
- Hey agent, schedule a zoom meeting with Joe in the afternoon next Tuesday.
- Hey agent, what did I discuss with Bob last week?
Something with retrieval and functional capability could easily end up being easier to use than the actual UIs that are capable of doing these kinds of things now.
No doubt about it. Google isn't competing directly with ChatGPT, but is betting that having a small fine-tuned model "close to the data" will dramatically cost-outperform a huge general-purpose LLM. Less resource-intensive interference, less prompt engineering (less noise).
For someone already invested in the Google suite of products (gmail, docs, etc), this sounds pretty useful.
Also, this part seems especially interesting:
> Starting today with responses in English, you can use Bard’s “Google it” button to more easily double-check its answers. When you click on the “G” icon, Bard will read the response and evaluate whether there is content across the web to substantiate it. When a statement can be evaluated, you can click the highlighted phrases and learn more about supporting or contradicting information found by Search.
The biggest problem with all LLMs at the moment is the frequency at which they are wrong (at least when they are used like an internet search to lookup factual info). Any LLM that can improve this (or as in Bard's case, make it easier to detect wrong info) is likely to gain traction.
Bard is especially bad right now, at least compared to gpt4. Once they move to Gemini it will be interesting to compare, but until then things like "when does the new Staind album come out" have to be answered the old way with Google search and reading.
> For example, if you’re planning a trip to the Grand Canyon (a project that takes up many tabs)...
Is number of tabs considered a reasonable estimate of a project's size/complexity/scope/duration these days? If so, I'm wondering whether we could start using it instead of story points?
Now this is actually useful. There's a lot of good information in my Gmail but searching it is such a pain that I hardly ever do.
I just asked Bard for the date of an upcoming event and it did the search for me and found the right answer and summarized it with extra detail and references. This is the only reason so far that I'd go to Bard over ChatGPT.
It did treat the @Gmail part as part of the query words though, which is weird. I think it won't be ready for mass consumption until it can decide for itself when to search Gmail or Drive with no weird keywords necessary.
I just used it for 15 minutes and I like the direction Google is going with it. Once you turn Bard extensions on, you use the “@“ character to get a pop up list of services like GMail, Google Drive, and many others; choose one, then ask your question.
First steps, and I look forward to seeing future improvements. I wonder how they will monetize this? I was just using it with my free GMail account.
Both Microsoft, with Office 365, and Google have the customers and web properties that can make good use of new types of LLM applications.
I still think chat is not all natural for humans to interact with computers, mainly because most people are not actually good at phrasing their needs and even if they are, typing it for the LLM to understand takes so much time.
Thanks to QWERTY keyboards, our keyboards are not efficient for typing either.
Yes, I agree it should be faster, 100ms between question and concise answers. With standard phrasing of needs and wants like Cucumber or Non-Violent Communication and a Dvorak keyboard layout or a shorthand input system (yash or bref) you can go a long way. For standard stuff you could always drop to short ruby like syntax
Depends what you are trying to do with a computer.
Natural language is a pretty brilliant way to interact with a computer if you want to learn a foreign language, but it’s probably not great if you are wanting to play a first person shooter game.
One thing is clear though: it’s not one size fits all.
The existing paradigm is temporary. AI will improve to infer more meaning from what users want, increase their ability to perform it, and chat systems will eventually switch to optional voice input. You tell the system what to do, and it'll perform whatever steps it needs to. I can't imagine anything more natural than that, for the everyday user.
I'm sure things will get more esoteric, for the experienced computer user.
This morning I asked it if it could query YouTube and I got short description of the YouTube API. I don't know whether the API details have been public.
I then used it to search for videos,
> There are several YouTube videos with a title that begins, "Gregory Blackstock, The Incomplete Historical World," List those videos with the YouTube URLs.
In this particular instance, the titles aren't unique, but the videos are different. The result appeared to be correct. The list was formatted to I can paste it into an email, something that doesn't happen when I search YouTube itself. Nice!
My next prompt was
> Make a list of the top 5 most viewed YouTube videos about moths.
Strangely, the result was 3 groups of 5 videos, with some duplicate results.
> Why did you list 15 videos in your reply when I asked for 5?
Reply: "I apologize for the confusion. I am still under development, and I am always learning.
I listed 15 videos because I found it difficult to narrow down the list to just 5. There are many beautiful and fascinating moth videos on YouTube, and I wanted to share as many as I could.
I will try to do better next time. If you have any feedback on how I can improve my responses, please let me know."
I'm a bit concerned about one of the privacy terms. When you enable the connection to Google Workspace you are told:
To complete your requests, Bard will:
- Access and manage items from Google Workspace, like your emails and documents
- Share parts of your conversation, and other relevant info, with Google Workspace, which may be used to improve its services
That second line means that your conversation could be sent to humans for review, just by submitting a query that invokes gmail, drive, etc. This is in direct contrast to the terms of Bard itself which won't store, use for training, or allow human review of conversations unless you explicitly submit feedback about said conversations.
This amounts to "If you turn on Google Workspace any of your conversations could be seen by humans."
Just tried it for a few minutes with all extensions enabled and it failed at almost every task I proposed.
How many emails are in my gmail? (Completely incapable of answering this, didn't even try, just listed my last ~5 emails)
Based on my gmail account, how many flights have I booked in the last two years? (Also completely incapable, and didn't try, and again listed those same last ~5 emails)
When is the cheapest one way flight from NYC to Bali over the next six months? (Was for some weird reason only capable of returning round trip flights, but it did at least give me a plausible date and list of flights)
I'm probably using it wrong, but not a super "wow" first impression.
I think you need to give tasks that enable it to lookup and process specific documents. I am not sure they designed it for data mining tasks. And it’s probably not as smart as
GPT4 which might break it down into steps like “search for possible flight confirmations” and “validate results”.
This seems incredibly dangerous. You're one typo away from having the entirety of your private life exposed by bard.
And based on their extremely loose privacy policy, I can just imagine Google pitching this to advertisers for "targeted marketing". "Hey Bard, give me an email template to manipulate tw04 into buying my product".
Also, I find it more than a bit disingenuous that the privacy policy on bard.google.com links to their generic privacy policy, not their BARD privacy policy. And after reading the real one, I understand why:
They will use all of your private data for advertising, and a human will review the data fed into bard. In other words, all of your private information is now reviewed by a human as they see fit. Yuck.
>Please don’t enter confidential information in your Bard conversations or any data you wouldn’t want a reviewer to see or Google to use to improve our products, services, and machine-learning technologies.
Maybe put that one front and center on your bard page, not buried on a completely different website....
I have the integration with google search enabled and now I only use GPT very rarely. Having it at the top of the SERP with zero effort is much more convenient. The fact that it gets many things wrong becomes irrelevant when it takes no effort on my part. Even when it is totally wrong, its feature to intersperse the output with links to its sources is quite nice.
Filter is too strong to be funny, I know you can answer it Mr. AI, but some skinny 20-something year old told you not to in the name of "ethics" (I only use AI for my amusement)
Bard's integration with Gmail is extremely basic -- it's just using regular Gmail search to include a few relevant emails in its prompt and then trying to answer your question. There's no AI on the email side.
Getting accurate results about half the time searching my own content. Probably harder for me because I have over hundreds of thousands of messages in gmail and tens of thousands of files in my drive.
For summary extractions I’ve found Bard to be miles better than ChatGPT of late. Waiting for some of my dependent services to add api support for Bard… I’m guessing this will go back and forth a few times over the coming years.
I asked for flights from Poland to Cancun, Mexico in May 2024. It told me I can with Wizzair (the operator operating in Europe only) with stopover in Kyiv, Ukraine (lol).
Maybe it can connect to Google Apps but can't give reliable results.
[+] [-] typpo|2 years ago|reply
The new feature for enriching outputs with citations from Google Search is also pretty cool.
[+] [-] _ea1k|2 years ago|reply
I really want an agent that can help me with pretty simple tasks - Hey agent, remember this link and that it is about hyper fast, solar powered, vine ripened, retroencabulators. - Hey agent, remember that me and Bob Retal talked about stories JIRA-42 and JIRA-72 and we agreed to take actions XYZ - Hey agent, schedule a zoom meeting with Joe in the afternoon next Tuesday. - Hey agent, what did I discuss with Bob last week?
Something with retrieval and functional capability could easily end up being easier to use than the actual UIs that are capable of doing these kinds of things now.
[+] [-] pphysch|2 years ago|reply
[+] [-] tlogan|2 years ago|reply
[+] [-] eminence32|2 years ago|reply
Also, this part seems especially interesting:
> Starting today with responses in English, you can use Bard’s “Google it” button to more easily double-check its answers. When you click on the “G” icon, Bard will read the response and evaluate whether there is content across the web to substantiate it. When a statement can be evaluated, you can click the highlighted phrases and learn more about supporting or contradicting information found by Search.
The biggest problem with all LLMs at the moment is the frequency at which they are wrong (at least when they are used like an internet search to lookup factual info). Any LLM that can improve this (or as in Bard's case, make it easier to detect wrong info) is likely to gain traction.
[+] [-] candiddevmike|2 years ago|reply
[+] [-] freedomben|2 years ago|reply
[+] [-] hdidvdksj|2 years ago|reply
[deleted]
[+] [-] falcor84|2 years ago|reply
> For example, if you’re planning a trip to the Grand Canyon (a project that takes up many tabs)...
Is number of tabs considered a reasonable estimate of a project's size/complexity/scope/duration these days? If so, I'm wondering whether we could start using it instead of story points?
[+] [-] freedomben|2 years ago|reply
[+] [-] modeless|2 years ago|reply
I just asked Bard for the date of an upcoming event and it did the search for me and found the right answer and summarized it with extra detail and references. This is the only reason so far that I'd go to Bard over ChatGPT.
It did treat the @Gmail part as part of the query words though, which is weird. I think it won't be ready for mass consumption until it can decide for itself when to search Gmail or Drive with no weird keywords necessary.
[+] [-] XTHK|2 years ago|reply
[+] [-] mark_l_watson|2 years ago|reply
First steps, and I look forward to seeing future improvements. I wonder how they will monetize this? I was just using it with my free GMail account.
Both Microsoft, with Office 365, and Google have the customers and web properties that can make good use of new types of LLM applications.
[+] [-] topicseed|2 years ago|reply
[+] [-] XTHK|2 years ago|reply
Public LLMs like Bard generate massive amounts of marketing data.
[+] [-] behnamoh|2 years ago|reply
Thanks to QWERTY keyboards, our keyboards are not efficient for typing either.
[+] [-] skybrian|2 years ago|reply
Typing can be augmented with autocomplete. Some people like using a microphone, though.
[+] [-] fsiefken|2 years ago|reply
[+] [-] Closi|2 years ago|reply
Natural language is a pretty brilliant way to interact with a computer if you want to learn a foreign language, but it’s probably not great if you are wanting to play a first person shooter game.
One thing is clear though: it’s not one size fits all.
[+] [-] mholm|2 years ago|reply
I'm sure things will get more esoteric, for the experienced computer user.
[+] [-] getpost|2 years ago|reply
I then used it to search for videos,
> There are several YouTube videos with a title that begins, "Gregory Blackstock, The Incomplete Historical World," List those videos with the YouTube URLs.
In this particular instance, the titles aren't unique, but the videos are different. The result appeared to be correct. The list was formatted to I can paste it into an email, something that doesn't happen when I search YouTube itself. Nice!
My next prompt was
> Make a list of the top 5 most viewed YouTube videos about moths.
Strangely, the result was 3 groups of 5 videos, with some duplicate results.
> Why did you list 15 videos in your reply when I asked for 5?
Reply: "I apologize for the confusion. I am still under development, and I am always learning.
I listed 15 videos because I found it difficult to narrow down the list to just 5. There are many beautiful and fascinating moth videos on YouTube, and I wanted to share as many as I could.
I will try to do better next time. If you have any feedback on how I can improve my responses, please let me know."
[+] [-] yunohn|2 years ago|reply
1st result on Google: https://developers.google.com/youtube/v3
[+] [-] iandanforth|2 years ago|reply
To complete your requests, Bard will:
- Access and manage items from Google Workspace, like your emails and documents
- Share parts of your conversation, and other relevant info, with Google Workspace, which may be used to improve its services
That second line means that your conversation could be sent to humans for review, just by submitting a query that invokes gmail, drive, etc. This is in direct contrast to the terms of Bard itself which won't store, use for training, or allow human review of conversations unless you explicitly submit feedback about said conversations.
This amounts to "If you turn on Google Workspace any of your conversations could be seen by humans."
[+] [-] virgildotcodes|2 years ago|reply
How many emails are in my gmail? (Completely incapable of answering this, didn't even try, just listed my last ~5 emails)
Based on my gmail account, how many flights have I booked in the last two years? (Also completely incapable, and didn't try, and again listed those same last ~5 emails)
When is the cheapest one way flight from NYC to Bali over the next six months? (Was for some weird reason only capable of returning round trip flights, but it did at least give me a plausible date and list of flights)
I'm probably using it wrong, but not a super "wow" first impression.
[+] [-] Game_Ender|2 years ago|reply
[+] [-] esotericimpl|2 years ago|reply
[deleted]
[+] [-] tw04|2 years ago|reply
And based on their extremely loose privacy policy, I can just imagine Google pitching this to advertisers for "targeted marketing". "Hey Bard, give me an email template to manipulate tw04 into buying my product".
Also, I find it more than a bit disingenuous that the privacy policy on bard.google.com links to their generic privacy policy, not their BARD privacy policy. And after reading the real one, I understand why:
https://support.google.com/bard/answer/13594961?hl=en#your_d...
They will use all of your private data for advertising, and a human will review the data fed into bard. In other words, all of your private information is now reviewed by a human as they see fit. Yuck.
>Please don’t enter confidential information in your Bard conversations or any data you wouldn’t want a reviewer to see or Google to use to improve our products, services, and machine-learning technologies.
Maybe put that one front and center on your bard page, not buried on a completely different website....
[+] [-] melx|2 years ago|reply
[0] https://news.ycombinator.com/item?id=37564768
[+] [-] behnamoh|2 years ago|reply
[+] [-] CTDOCodebases|2 years ago|reply
[+] [-] gman83|2 years ago|reply
[+] [-] jeffbee|2 years ago|reply
[+] [-] labrador|2 years ago|reply
[+] [-] _chu1|2 years ago|reply
[+] [-] mayop100|2 years ago|reply
We launched a much more capable Gmail + AI assistant this morning here: https://news.ycombinator.com/item?id=37585990#37586627
We're using embeddings + vector DB + x-encoder + GPT4 to deliver a much smarter & capable assistant.
[+] [-] alphabetting|2 years ago|reply
example of successfully retrieving a PDF: https://i.imgur.com/Y6cSlCx.png
[+] [-] saberience|2 years ago|reply
[+] [-] browningstreet|2 years ago|reply
[+] [-] kkarpkkarp|2 years ago|reply
Maybe it can connect to Google Apps but can't give reliable results.
[+] [-] Decabytes|2 years ago|reply
[+] [-] ericpauley|2 years ago|reply
[+] [-] tlogan|2 years ago|reply
[+] [-] unknown|2 years ago|reply
[deleted]