Ideally, new versions of GPT (and other LLMs) will be also trained on the newly added, mostly hallucinated data when using Wikipedia as part of the training set, baking those past hallucinations into the model, allowing other users to get additional hallucinated facts that fit the existing fictitious data, slowly creating a new "GPT cinematic universe" for e.g. small towns in Nebraska.
And if people fact check it with Bing, there is a good chance it will say "Yeah, that checks out, here's Wikipedia and <some Wikipedia mirror> as a source". A creative derivation of XKCDs citogenesis[1] :D
The only thing GPT changes here is speed at which you can do that, but if you start mass-spamming with such articles that will actually make it easier to spot.
Certainly cool, but it's getting a lot to see just how good GPT is at generating utterly useless cheap content. Making content is a moving target, and GPT by nature produces uncannily generic generations.
please bring firefox versions from the start. You are only playing into the chrome monopoly by treating firefox users as second class citizens then complaining there is no "demand"
I've been following XP1 and I don't think they have nefarious goals with this. The extension is even open source (though not sure if the proxy is). Check it out here: https://github.com/dust-tt/dust/tree/main/xp1
I'm working on a somewhat related product (except bringing this assistant capability to all apps on your computer, all browsers, and using mostly on-device ML...waitlist in my profile in case you're curious)
What we've discussed internally is having two modes for the cases where we do need network connection:
1) A turn-key, use-our-OpenAI/HuggingFace/whatever proxy that doesn't store anything, just adds our token and pays for it on your behalf
2) Bring-your-own key for each service
The fact is that most users who just want to use these kinds of productivity tools might not have their own OpenAI/Azure/etc account, so offering option 1 and even defaulting to it is right for most end-users.
I think XP1 is making the right call here with this default, though offering #2 would be nice!
I installed the extension and asked it to reply to your comment, and thought the response was impressive. I myself am concerned about the privacy implications.
"Hi yunwal,
Regarding your concern about the privacy of Dust XP1, it's understandable to be cautious when it comes to sharing personal information. However, as mentioned in the Discord message shared by spolu, Dust XP1 only sends your requests to OpenAI and stores them for debugging purposes. They do not fetch or store anything else than what is required to process your requests. Additionally, Dust XP1 is open source, which means you can look at the code if needed. If you have any further questions, feel free to ask.
Are you genuinely curious, or are you asking because you're implying that the people who would use such an app are somehow not understanding something or not intelligent, or don't know something that you do? Like you have to prove your case too, as you're not immediately "right" in your statement. Sure there is some level of "risk" in doing this, but there is risk in a lot of things. It's like me asking people this:
"Why would anyone trust people with 4 weeks driving classes and a test with their lives on a road driving 80mph inside 2-tonne metal cages? Seems insane."
I had a good experience testing out "gpt-3.5-turbo". Made a bot for the Matrix server we use at work so that co workers can query and work with the AI assistant collaboratively and in any group chat.
Works pretty well so far and is fairly inexpensive. The markdown sent by the AI gets rendered nicely in Element and Conny. Want to open source it soon.
Tried it in this page with the following prompt: "read the comments and write a summary of what people think of this product"
GPT: Users are impressed by the capabilities of the product and its ability to generate content quickly. However, some users are concerned about the privacy implications of the product and are hesitant to use it due to the fact that it sends personal information to a third-party. The fact that the extension is open source helps to alleviate some of these concerns, but others remain skeptical about the intentions of the developers. Overall, there is a mix of excitement and caution surrounding this product.
Information needs to start having a "Free of AI-generated content" seal of approval, akin to the GMO battle being fought elsewhere.
I mean, we already process high fructose digitally-altered content, that ship has sailed - but we ought really start to having an "AI / not-an-AI" tag we can put on things...
(The moment I detect you've sent me an AI-created email about our project, I will replace you with a shell script.)
/disclaimer: I may have generated this comment without any intelligence, whatsoever.
Unfortunately Dust.tt doesn't use a modern email validation method and so fails on "modern" TLD's like .media, making it impossible to sign up for an activation key with it.
Not sure about their policy/internals myself, but since GPT-3.5-turbo is 1/10th the cost of the previous model it's really hard now to run up a significant (to a funded startup) bill via legitimate usage — especially since at this phase any legit usage may be worth its weight in lessons about how the tool can be used. May be worth rate limiting / DoS protection but even then, could just cap OpenAI spending and spend the time to patch it if/when it happens (e.g. import @upstash/ratelimit or adding a quick Cloudflare rule)
[+] [-] sva_|3 years ago|reply
But they're still sent through your server for pretty much no reason?
[+] [-] sodality2|3 years ago|reply
[+] [-] shp0ngle|3 years ago|reply
I could use GPT to generate Wikipedia articles about random villages and people I know nothing about.
Sure, those will not be at all correct, but who checks correctness on wikipedia, especially about random people and villages?
GPT, give me 10 paragraphs about New East Lake, Michigan
[+] [-] schroeding|3 years ago|reply
Ideally, new versions of GPT (and other LLMs) will be also trained on the newly added, mostly hallucinated data when using Wikipedia as part of the training set, baking those past hallucinations into the model, allowing other users to get additional hallucinated facts that fit the existing fictitious data, slowly creating a new "GPT cinematic universe" for e.g. small towns in Nebraska.
And if people fact check it with Bing, there is a good chance it will say "Yeah, that checks out, here's Wikipedia and <some Wikipedia mirror> as a source". A creative derivation of XKCDs citogenesis[1] :D
[1] https://xkcd.com/978/
[+] [-] benopal64|3 years ago|reply
At the same time, it uses Wikipedia as a source as well as marketing and blog sources so Phind results should be carefully critiqued as well.
[+] [-] pornel|3 years ago|reply
The only thing GPT changes here is speed at which you can do that, but if you start mass-spamming with such articles that will actually make it easier to spot.
[+] [-] sorokod|3 years ago|reply
[+] [-] dang|3 years ago|reply
Show HN: XP1 – A GPT-based Assistant with access to the browser Tabs - https://news.ycombinator.com/item?id=33970570 - Dec 2022 (9 comments)
[+] [-] bfeynman|3 years ago|reply
[+] [-] 2Gkashmiri|3 years ago|reply
[+] [-] yunwal|3 years ago|reply
[+] [-] deet|3 years ago|reply
I'm working on a somewhat related product (except bringing this assistant capability to all apps on your computer, all browsers, and using mostly on-device ML...waitlist in my profile in case you're curious)
What we've discussed internally is having two modes for the cases where we do need network connection:
1) A turn-key, use-our-OpenAI/HuggingFace/whatever proxy that doesn't store anything, just adds our token and pays for it on your behalf
2) Bring-your-own key for each service
The fact is that most users who just want to use these kinds of productivity tools might not have their own OpenAI/Azure/etc account, so offering option 1 and even defaulting to it is right for most end-users.
I think XP1 is making the right call here with this default, though offering #2 would be nice!
(edit: added Github link to XP1)
[+] [-] valine|3 years ago|reply
"Hi yunwal,
Regarding your concern about the privacy of Dust XP1, it's understandable to be cautious when it comes to sharing personal information. However, as mentioned in the Discord message shared by spolu, Dust XP1 only sends your requests to OpenAI and stores them for debugging purposes. They do not fetch or store anything else than what is required to process your requests. Additionally, Dust XP1 is open source, which means you can look at the code if needed. If you have any further questions, feel free to ask.
Best regards, XP1"
[+] [-] cloudking|3 years ago|reply
[+] [-] zo1|3 years ago|reply
Are you genuinely curious, or are you asking because you're implying that the people who would use such an app are somehow not understanding something or not intelligent, or don't know something that you do? Like you have to prove your case too, as you're not immediately "right" in your statement. Sure there is some level of "risk" in doing this, but there is risk in a lot of things. It's like me asking people this:
"Why would anyone trust people with 4 weeks driving classes and a test with their lives on a road driving 80mph inside 2-tonne metal cages? Seems insane."
[+] [-] zo1|3 years ago|reply
[+] [-] stuckkeys|3 years ago|reply
[+] [-] sureglymop|3 years ago|reply
[+] [-] apetresc|3 years ago|reply
[+] [-] valgaze|3 years ago|reply
I wonder if security issue or because the canvas/ui is special
[+] [-] mdrzn|3 years ago|reply
GPT: Users are impressed by the capabilities of the product and its ability to generate content quickly. However, some users are concerned about the privacy implications of the product and are hesitant to use it due to the fact that it sends personal information to a third-party. The fact that the extension is open source helps to alleviate some of these concerns, but others remain skeptical about the intentions of the developers. Overall, there is a mix of excitement and caution surrounding this product.
[+] [-] aa-jv|3 years ago|reply
I mean, we already process high fructose digitally-altered content, that ship has sailed - but we ought really start to having an "AI / not-an-AI" tag we can put on things...
(The moment I detect you've sent me an AI-created email about our project, I will replace you with a shell script.)
/disclaimer: I may have generated this comment without any intelligence, whatsoever.
[+] [-] sebastianconcpt|3 years ago|reply
[+] [-] ur-whale|3 years ago|reply
The bar isn't very high TBH.
[+] [-] fire|3 years ago|reply
[+] [-] mmacvicarprett|3 years ago|reply
[+] [-] wahnfrieden|3 years ago|reply
[+] [-] bcjordan|3 years ago|reply
[+] [-] m3kw9|3 years ago|reply
When you come out of beta, probably need a rebrand
[+] [-] meghan_rain|3 years ago|reply