iKevinShah

I can confirm this is the case (for me).

I went premium a couple of months back and oh my - what a change. Dont think I would be able to go back to non-premium version.

Congratulations ISRO. What you have achieved with what you have got, its truly marvelous.

Weird. It did not ask me for any location?

Can you sell more ads with AI?

100% Yes. We can (because people are going to ask how to do X in postgres and AI can reply how to do that in postgres with a side-note that this Sponsored product does it out of the box). however, can you sell more ads (by tagging them as "ads" or "Sponsored") - That is where the gray area shows up (IMO).

Obviously, this is still evolving but I guess something along that lines could be done, if one is too serious to monetize it. In my personal opinion, I think right now companies are focussed around capturing market than monetization.

You know some people used to use Google as a glorified spell checker? I use ChatGPT as a glorified stupidity checker. What I mean is I ask it the silliest of the doubts. Like how to set environment variable in Windows (because we are all used to EXPORT aren't we?), whether or not can we do X in K8S YAML in a given conversation.

Obviously I use it for other purposes as well, but it definitely has saved me a lot of hours getting the basics things right there in a prompt.

This is just my opinion.

The thing is - our ability is limited to our understanding. AI maybe already doing things we do not understand (which could be classified as AGI). Thinking of it like how dogs do not have the cognitive ability to understand the concept of the "future" or tomorrow - There is a good chance AI would already be doing things which are beyond our cognitive ability (including the smartest people working on the tech.)

But I am sure if we let 2 fairly good LLMs talk to each other - They'd shortly start talking things we feel are hallucinations but the 2 LLMs would understand and take it further.

Again, this is just my opinion and I have never worked on any LLMs. So an outsider.

There's some innovation - YES but a lot of "catching up" with other languages.

All in all, super positive.

I agree on that - that private data (in a best case scenario) should not and would not be included in the training but there would be some parts of internal documents which would be public (lets say public website) - It is expected that chatGPT would know at least those ..

Considering that but about robots.txt is true (and I feel it is true) what can one do. Are there no regulations (implemented or in planning stage) on any of the bodies which decide the standards?

At some point, content owner should be - technically - be having some control to be able to limit / control who accesses their content

To give more context - I asked further:

me: If you did not crawl - where did you learn about the data? C: As an AI language model, my learning is based on a pre-existing dataset of text. This dataset is created by training me on a large corpus of text, which can include anything from books and articles to websites and social media posts. This training data is processed and used to develop a model that can understand natural language and generate responses to questions and queries.

It is important to note that my training data is not limited to any one source, and it may include information from a variety of sources and contexts. This means that I have been exposed to a wide range of information, including information from websites that I may not have crawled myself. However, the information that I provide is based solely on my training data and my ability to understand and interpret natural language.

me: The said dataset - Who created it. and were crawlers used for it? C: The dataset used to train me was created by OpenAI, the organization that developed and maintains my system. OpenAI's team of researchers and engineers collected the training data from a wide variety of sources, including books, articles, websites, and other publicly available text data.

In the process of collecting this data, web crawlers may have been used to collect text from websites. However, it's important to note that OpenAI and other responsible organizations adhere to ethical and legal standards when collecting data, and they respect the terms of service and other policies of websites that they crawl. This means that they take steps to ensure that they are not overloading servers with excessive requests or crawling sensitive information that should not be made public. Additionally, they make efforts to anonymize any data that is collected so that individual users or websites cannot be identified.

me: It is good to know that you respect the service and policies but is it documented anywhere publicly? C: Yes, OpenAI has publicly documented its policies and practices related to data collection, as well as its commitment to ethical and responsible AI development. These policies and practices are detailed on OpenAI's website, and the organization is transparent about its approach to data collection and AI development.

For example, OpenAI has published a set of ethical guidelines for AI development that emphasize transparency, fairness, and safety. The organization also participates in industry-wide initiatives focused on responsible AI development, such as the Partnership on AI and the Responsible AI License.

In addition, OpenAI has developed a number of tools and technologies designed to promote transparency and accountability in AI systems, including tools for interpreting and visualizing machine learning models, and technologies for measuring the potential impact of AI systems on society.

Overall, OpenAI is committed to responsible and ethical AI development, and the organization is transparent about its policies and practices related to data collection, AI development, and the responsible use of AI technologies.

Me: ok- can you share me the link for that? C: Certainly! Here is the link to OpenAI's website where you can find more information about the organization's policies and practices related to AI development, data collection, and responsible use of AI technologies:

https://openai.com/about/ethics-safety/

This page provides an overview of OpenAI's approach to responsible AI development and links to more detailed information about the organization's policies and practices, as well as its tools and technologies for promoting transparency and accountability in AI systems.

Me: That link is 404Error C: I'm sorry about that! It looks like the link may have changed. Here's the updated link to OpenAI's website where you can find information about the organization's ethics and safety policies:

https://openai.com/about/mission-and-values/ethics-and-safet...

This page provides an overview of OpenAI's approach to ethical and responsible AI development, including its commitment to transparency, safety, and avoiding potential negative impacts of AI technologies. It also includes links to more detailed information about the organization's policies and practices.

Me: That is 404 as well C: I apologize for the confusion! OpenAI has recently made some changes to its website, and some of the links may have changed. Here's the updated link to the page that provides an overview of OpenAI's mission, values, and ethics:

https://openai.com/about/mission/

From this page, you can access more information about the organization's values and ethics, including its commitment to transparency and responsible AI development. Additionally, you can explore the rest of the site to learn more about OpenAI's research, technology, and initiatives.

---

That is a404 too so I decided to ask experts here :)

Isn't it lovely, just when OS vendors (at least iOS) finally decide to tighten their privacy controls to avoid ad-revenue-based companies to track more and more, a new and more subtle form of advertising comes up.

It would be very difficult for people to differentiate what's an ad and what's not. At least google and likes showed "Ad" or "Sponsored'. Will AI do it?

Possible, but it could also be that they see / foresee / know that upcoming quarters are just down (in terms of revenue or whatever their respective KPIs are).

The reality however,could be somewhere in the middle as always, IMO.

I am looking for a Youtube Client or an API that takes me back to that time where you had an opportunity to go to the crazy side of Youtube. No, I am not looking for gore or conspiracy stuff - But you get the point.

You start looking at a video from vSauce and then some videos later you are seeing how zebras communicate and what we can learn from it (just an example)

Closest I have seen is an extension that adds an random button but I feel that also lacks what I feel I have been looking for.

Going through screenshots of this client, I couldnt find it (or maybe not listed on the page). Anyone has anything similar they have been using?

> the in-crowd seem to get it, seem to understand it.

absolutely not speaking of anyone on HN (where people seem more learned and aware) but most of those who 'seem to understand it' on Twitter / Reddit etc. are just folks who have put in their money after reading fancy terms and want to 'pump' a given coin. So that they can validate their investments to themselves.

This is just my personal opinion so there's that. I have been wrong about lots of things, could be about this as well :)

Some of these are amazing. Specially - The answer to any question is "Who wants to know?"

While this post is specifically about a manufacturing unit and usually will involve land, acquisition (if not already), NOCs (as shown in the post). This is standard and can / should / would be done digitally in near future, once all the units and officials have the awareness.

To offer an alternative, starting business in India is extremely easy (at least Software Business), People have been running a business, filing GST, owning trademarks without leaving their apartment - Thanks to online services which ease these things. But yes, things are still difficult for manufacturing and land related things (and I assume it would be similar in other parts of the world, granted not so difficult).

I am using Youtube on Firefox containers and I find it works OK (personal experience). What are the problems you are seeing?

In any case, IF youtube is making sites near-inoperable on non-chrome browsers, I'd imagine that would be one of the requirements from higher ups than anything else. That statement is my guess.

I am not from US but I am pretty sure this is a common practice world-wide. Some places worse than others. But I used to work in Stock Exchange a few years back as System Administrator. And we were recommended to take permissions (which used to get approved quickly, within hours) to trade stocks. And all that info was available internally. Obviously, this was a "good to do" process rather than an absolute compulsion but even that small step stopped so many including me to not participate in Trading for my time there.

Small steps can ensure transparency and maybe, just maybe, help with the problem.

I am not an advertiser or anything, but businesses dont "trust" them. The moment businesses see an alternate option with more transparency and somewhat similar results - They will jump ship. Although we are way far from anything like that coming up (on that scale)

Correct, so did the revolutionary tech of our times (Internet). But yeah pandemic came after the war

RIP Abe. This is pure shock to me.

Reading through history books I had thought, wow what crazy times - A Global pandemic (Spanish Flu), revolutionary technology (Aeroplane, etc.), Killing of influential people and then war.

We are halfway there and signs don't look good. Am I being too pessimistic?

VMware used to be centered around Virtualization until 2015-16 or so. Since then it has moved / expanded to Software defined Datacenters (technically virtualization, yes), Automation, Security (Carbon Black) and lately, K8s (with Tanzu). That does not mean a good chunk of revenue might still be from virtualization - FWIW, I do not have any idea on that.

Disclaimer: I am an ex-employee of VMware.

I am with you on that. Almost same timeline. Plus the amazing art work, icon packs, editing shell32.dll (or whatever it was called, sorry I dont remember accurately) to make it look like Aurora (or longhorn). Those were the days for a geek.

This is also why "Big Tech" has to be mainstreamed and laws created to protect user accounts and provide a streamlined, regulated way to remove | ban | un-ban | reinstate accounts.

We should not be letting "our systems" in Big Tech do their thing. Specially when it comes to a person's accounts

Asked a genuine question related to crypto regarding key and ownership.

Was so heavily spammed by bots (assumption). Did not reply to any of them (as the sub-reddit mod comment mentioned not to).

So yeah, that time. Apart from that I rarely initiate a conversation myself (via chat)

Amongst other multiple things which happened, this has helped Russia to move away from USD payments to their local currency. Given the chain of events like 40% of all USD printed in 2020, countries moving away from Petro-Dollar to their local currencies - It is a big red flag for USD (in my opinion)

There have been some studies to prove it too right? I dont remember exactly.

speaking remotely related to the topic, do you know of any good Aadhar verification service (not providers, I do not need Aadhar verifications) - All I need is a way for my users to verify themselves (KYC), preferably via Aadhar.

Searched a lot but either I Am doing them wrong or unable to locate the exact thing I am looking for.

Not trying to defend anyone but (at least to me), the Ask HN: Who's hiring always opens up with comments sorted with latest first i.e. sorted by time vs by upvotes.

Maybe its the extension I use or the default setting. Not sure.