Hacker News new | past | comments | ask | show | jobs | submit | curiousmindz's comments login

It is surprisingly easy to use to obtain a type-safe data storage solution.

And everything is Open Source : https://github.com/evoluhq/evolu

Their future business model seems to be selling hardware running the server code with end-to-end encrypted sync and backup.


The analogy with Chess does not work: I can go on YouTube to watch how a pro player beats a specific boss, then use that to massively shorten how long I need to beat that boss.

Watching a lot of grandmasters play Chess will minimally help me beat a Chess AI that was better than me (excluding the beginner level).

I think that someone could have fun playing a Diablo-like RPG because they enjoy feeling powerful while they mow down a lot of enemies. And someone someone could enjoy a Soulslike game for the precision they need to apply to beat a boss.

Maybe it is somewhat similar to the difference between an arcade/fun racing game and a professional track racing game.

I wouldn't consider one to be "better" than the other. They simply have different objectives.


I just tried with Bing AI (in "precise" mode), it ran a search, then answered:

> There are many soccer players whose names contain a Z. Some of them include Zlatan Ibrahimović, Zinedine Zidane, Zico, Zvonimir Boban, and Zé Roberto ¹. Would you like to know more about any specific player?

Source: Conversation with Bing, 3/31/2023 ...

I also tried: "Can you name 14 soccer players whose names contain a Z?" (At 15+, it answers "I’m sorry, but I don’t have 15 names of soccer players whose names contain a Z. However, I can provide you with a few more names")

> Sure! Here are 14 soccer players whose names contain a Z: Zlatan Ibrahimović, Zinedine Zidane, Zico, Zvonimir Boban, Zé Roberto, Zbigniew Boniek, Zakaria Aboukhlal, Zlatko Zahovič, Zubayr Amiri, Zico, Zé Luís, Zećira Mušović, Zsolt Lőw and Zah Rahan Krangar. Is there anything else you would like to know?


I would think that "lossless" implicit conversion are ok. Right?

For example, implicit conversion from a 32bit signed integer into a 64bit signed integer.


Note that this answer is from "old Bing". It has nothing to do with the GPT-enhanced new Bing:

https://oslo.town/@matt/109864320071232564

The main hints to spot new Bing are: The logo and the feedback buttons.


Right, I meant to suggest that this was an old data sampling algorithm. My point is that if this is already the low quality they were serving before, it is hard to see how adding a hallucinating algorithm in to the mix is going to help anything.


Old bing returns 0, when I asked that same question.

Did you try that same query, and what results did you get?


I expect this deal to be a must for Microsoft. OpenAI is probably very happy to raise the stakes as much as possible. So we will see how many billions Microsoft ends up paying for this.

Still, is there a world in which we look back 10 years from now and think that we were overvaluing the impact of AI?

(For example, this did happen with tablets, when people thought that the iPad would replace "computers"...)


Nah -- this sounds like Google buying YouTube or Android for billions while they were in their infancy but had proven tech.

People did say at the time Google overpaid but they were some of the wisest investments Google ever made.

I hope Microsoft don't buy them and OpenAI just becomes another FANG.


Or like when Microsoft invested $240M into Facebook back in 2007, which is one of the all time greatest corporate investments. Even after the massive correction, they still have a 22x return on the investment.

https://www.vox.com/2017/10/23/16412108/facebook-microsoft-2...

I wonder if they have cashed out their investment?


EMC acquired VMware at $500 million and VMW later IPOed at $20 billion. So 40x in only a few years.


It's like YouTube and Android I would think, but similarly, they didn't have a road forward independently.

YouTube was burning a fortune on hosting costs and being sued out of existence when Google bought them. Android didn't have a monetisation path at the time, because the Play Store did not yet exist.

I suspect the same is true of OpenAI currently. They've got some great technology, but are spending a lot of money servicing free queries right now, and don't really have a route to selling their product to the world and building revenue yet.


I remember hearing that said about Facebook buying Instagram, too. In hindsight, one of the best decisions they made.


Google bought Deepmind for 2% of openai's current valuation before openai existed.


The google acquisition is a great comparison. Years from now it will look like a steal


No it's not. YouTube had a working product with a working business model.

OpenAI has neither.


FANGO, then?


Replace the F from Facebook with the M from Meta and now we can have "MANGO" which is an acronym that would absolutely catch.


The problem is the N.

Netflix does matter to you if you are working anywhere near software in the Silicon Valley, but is just not in the same tier as the rest of them. The opposite for the missing Microsoft.

That's why the rest of the world uses GAFAM and not FAANG.


Made me chuckle, thanks.


It's a racial slur where I live.


It's a fruit where I live.


For what group?


Gypsy/roma


Interesting. What’s the connection?


They are darker skinned than the rest of the population and the word itself is like a generic name for one of them. I guess it is some form of mutation of the Turkish word mangal which is something like barbeque or charcoal


Thanks. Very interesting.


Tablets replaced computers for the most part. They are just a good bit smaller than we expected and have the capability to do phone calls.

Mobile is a much bigger market than Desktop these days.


I think this is an insightful take. My first tablet was 7”. Most phones are 6” now. The extra size of a 10” tablet does not buy much extra functionality and we all basically have “phablets” now. And in the end, these big smartphones did end up taking up 80% of the tasks I used to do on my laptop and I don’t hesitate to leave it at home for a trip unless I know I’ll need to do a heavy creative task.


This is a pretty bad take. The mobile market is much larger precisely because they AREN'T computers. They are mobile companions. But you don't do the same things on a computer and on a mobile phone.

Who edits their movies on a phone? Who codes on a phone? Who writes their PhD thesis on a phone? You will be hard pressed to find professionals who do these things. Because a phone is not a computer.


The main usage of computers even before mobile phones was to browse the web, read and write emails and play games. Web and mail is mostly done on phones now. Not sure about games.

The use cases you mention are much smaller.

Steve Jobs had the right analogy: Tablets are cars, desktop computers are trucks. Few people use trucks. Most use cars.


And yet SUV/Pickup is the most popular category of vehicles in the USA


There is absolutely no one I know who uses a tablet as their primary work computer. No one. That analogy instantly breaks down because of this. As if everyone drives to work primarily using their trucks.

The even more sad thing is that the iPad hardware is absolutely capable to be the primary computer for people. It's simply Apples refusal to allow a real OS to run on it that keeps holding it back.


Young people, the poor, many people in developing countries tend to all be mobile only. I don't have hard figures but i would estimate the number of people who do all their "computing" on a phone or tablet numbers in the billions.


Right. a phone/tablet is still better then nothing.


It's not so much about having a real OS than about the input. Mouse & keyboard is just so much better.


Ipad has Mouse & keyboard


As a secondary option. Compare with Surface (Pro), which has the opposite "issue".


I find tablets are good for one thing--watching movies on the go. Desktops/Laptops do a ton more than that for me.

I disagree that tablets replaced computers. I've seen no evidence of that in my life. Maybe I'm an anomaly though?


Parent comment is making a joke - "small tablets" that can make calls are mobile phones.


10B is what this article says

https://www.semafor.com/article/01/09/2023/microsoft-eyes-10...

Also mentions a profit distribution, where MS would get the majority of profit until its investment is paid back


I thought they would have been bought out by Microsoft. It would be a good play to lockout others to use chatGPT and GPT3 and it would actually work well with bing to have something that Google would eventually have to copy (but it would only give them a slightly larger moat for Google to cross).


There's an inherent advantage to let them continue running in experimental startup mode vs bureaucratic red-tape enterprise mode.


> Still, is there a world in which we look back 10 years from now and think that we were overvaluing the impact of AI?

AI? Probably no.

LLM-style AI? Yeah, I expect the tablet or blockchain story. A solution in search of a problem, with some very cool niche applications. In this case, Copilot.


Even with the models we have right now, if you built the right app on top of them, they'd be multi-billion dollar businesses that upset incumbents.

Imagine an IDE where you make assertions about the generated code, and it takes those and does a random walk through the latent space until it finds a point that satisfies those assertions. Instead of editing the modified code, you debug by making more assertions or describing the process more accurately.

Imagine art software where you describe what you want, then iteratively add refinements through more description and rough sketch-ups, and then get the final result neatly broken down into semantically consistent layers for a final pass in photoshop.

This stuff is all possible now, and if we see the same or better improvement in models in the next 10 years as we saw in the last 10 years the future versions will be amazing.


What you describe is it what the models can do today, but what they might be able to do with more work. It is possible conceptually now, but getting it to work on a product or MVP level - still risk there.


> is there a world in which we look back 10 years from now and think that we were overvaluing the impact of AI?

As a natural language model , we are overvaluing it. Yes , it is a better Google index, with fuzzy querying , but it s limited and bland as time goes by, Kinda like my VR goggles. After an initial wave of enthusiasm, its output will become so commonplace and bland that it will lose its value.

As a programming tool, it's probably just the beginning of a new era in which we talk to the computer and it spits out executable files.


My interpretation of the situation is based on the fact that the new models and ChatGPT are overloaded and demand is through the roof. So I assume that OpenAI just said "we may need a LOT more servers" and then looked at how much it will cost and then looked at Microsoft.


Another example of Microsoft purchasing what’s “trendy” and “ cool” to be relevant. They just buy hot tech and do nothing with it.


To be fair, sometimes that is all that it takes.

LinkedIn is after all still effectively a monopoly.

And it's not just Microsoft. Whatsapp is another "do nothing" example that comes to mind where the work was done on the backend, but the app is functionally just as awful as it was when it became the de-facto messaging app for most of the world.


This definitely happened before, but they are doing fine with GitHub.


They've done pretty well with Github?


In C#, you can write (pseudo-code): if (AVX2) { ... } else if (SSE) { ... } else ...

Then, when you run the program, the JIT will pick the first supported option and eliminate the other ones.


The most important "goalpost" is: Every major cross-platform AAA game gets released simultaneously on Windows, Xbox and PlayStation. When macOS gets added to the list in a consistant manner, people will consider it a "major" gaming platform.

Having access to a lot of mobile games doesn't matter for hardcore gamers.


This is a good example of changing the goal posts.

Your claim means that the Nintendo switch is not a gaming platform.

A AAA game is not denoted by how many platforms it releases on the first day.

Your other comment about mobile games is just another form of gatekeeping. Again the Switch is mobile gaming and would not meet your criteria.


Yes.

And I see that its id is just before this one. So that's a solution to find its parent.


Indeed. I didn't think about this.

I wonder how it managed to be N°2 in this Weekly Top 10 list for last week:

https://github.com/headllines/hackernews-weekly/issues/137


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: