Johngibb

I am actually asking this question in good faith: are we certain that there's no way to write a useful AI agent that's perfectly defended against injection just like SQL injection is a solved problem?

Is there potentially a way to implement out-of-band signaling in the LLM world, just as we have in telephones (i.e. to prevent phreaking) and SQL (i.e. to prevent SQL injection)? Is there any active research in this area?

We've built ways to demarcate memory as executable or not to effectively transform something in-band (RAM storing instructions and data) to out of band. Could we not do the same with LLMs?

We've got a start by separating the system prompt and the user prompt. Is there another step further we could go that would treat the "unsafe" data differently than the safe data, in a very similar way that we do with SQL queries?

If this isn't an active area of research, I'd bet there's a lot of money to be made waiting to see who gets into it first and starts making successful demos…

This reads like an infomercial... like someone was paid to write it.

If we're going to grant that a machine can have infinite ram, surely we can grant that a spec of C can have infinite stack allocated arrays... :)

Can I have one please?

I think your criticism is well founded.

That said, the author did put work into something, document it, and share it freely with the community - and for that reason, I'd rather not see someone hurt their feelings calling their work an 'abomination.'

I just think with a slightly different tone you could have made the same point in a way that would show the OP some brutal honesty but without discouraging them.

Please, be constructive instead of just dismissive. A nasty tone doesn't help anyone nor does it encourage trying new things.

I bet the variation in the size of people's fingers is greater than the difference in the size of touch targets between original and mini iPads... :)

Deprecated, but not removed yet. It "may be removed in a relatively distant future"

That's true, and I think assigning malice to this situation is unfounded. But maybe this is a problem worth solving?

Come on, don't reject it so flippantly. Sure, for the case of a woman getting married and taking a new last name, I doubt it's that big of a deal - you can change your name for future commits, but your old name will exist for historical commits. However, there _are_ cases where you might not want your former name around (transgender, or even something like privacy / witness protection). Right now, these folk are being sort of excluded (however inadvertently) and it's worth discussing ways to fix that.

That stood out to me too... is there an inside joke? What's the white have to do with it?

I know you'd miss the syncing, but why not let me just cc something@thread.is instead of having to gain access to my google account? It would be usable to people on exchange as well that way...

Yea that pesky tablet revolution wasn't a thing either, and neither was the GUI actually. I'm still using lynx.

(No offense to lynx users.)

Snark aside, it seems like high dpi will inevitably become standard in the next few years.

I didn't know it had been confirmed yet, can you add a link?

That doesn't mean that people don't care. I certainly wouldn't able to remember the birthday of all my closest friends, but I do care and am glad to be reminded. On the other hand, there are of course a ton of bday wishes from people who probably don't really care, but is that really a bad thing?

Why the snark? They're just providing another piece of data in an open discussion that may encourage more people to try the app. What's wrong with that?

If your argument is that the comment didn't add much to the discussion, I'd reply that yours added even less.

Is there any way to use it for say an iPhone app interacting with web services authenticated as a user?

Why shouldn't you be able to walk down a dark alley in NYC at night? It's not your fault if something happens. With that attitude, we are just tolerating crime and accepting it. If more people walk around at night, the crimes will gain more exposure, be more aggressively stopped, and things will get safer.

Yep, that'd do it!

Are you sure about that? I am almost positive that you're wrong, and @@identity is per connection. Otherwise how woul it know which table to return an identity for?

I thought that the difference had to do with what's returned if a trigger does an insert or something like that...

Someone capable of burning their cars changing a light bulb probably shouldn't be driving :)

You still paid for the device generating revenue directly to Amazon. The ads are just supplementing a discount on the product. Google is not making money off of the Android devices they don't sell, although it is changing as they start building and selling their own hardware.

Exactly. It's not a bad thing, it's a pretty fundamental basis of the Internet and the reason we get so much for free. At the end of the day it is still a win for consumers. I'm glad it works that way, since I'd rather view ads then pay a monthly subscription to Google (or would I? At least most people would).

Googles not making any revenue off you directly, yet they're paying engineers to work on it. They're making money somewhere - it's off of the ads you you see while you likely use google's services.

Please note that I don't think this is a bad thing, and I love and use Google's products myself very happily. But there is a difference between Google who is collecting revenue from advertisers, and Amazon/Apple who are making their money primarily from consumers.

Agreed. I get the point that new cars are intricate, crammed and complicated but a light bulb is a user serviceable part that is really not much harder than changing a lamp at home. Would you hire an electrician for that because you didn't want to blow your home's electrical system? ;)

The difference is with Amazon you're the customer, and the device and content are the products. With android, _you_ are the product and the advertisers are the customers. This distinction means that Apple/Amazon's interests are more aligned with consumers than Google's.

Wow, I hadn't heard about that Apache situation. That's not ok....

Peeing in a park where there could has been children can put you on the list, with the rationale being that while urinating in public you're also potentially exposing yourself to children. It's definitely outrageous that it's on the same scale, but it's not like peeing on a dark alleyway at 3 am will do it.

In my mind the reason for this is often increasing government transparency and encouraging citizens to be more critical of the government by exposing them to the gruesome realities that most of us don't see often. I think that the hypothesis here is that violent acts or murders committed for the camera is fairly rare, which seems fairly likely based on my observations. I'm not sure though and would be interested to hear from someone with more information.

I'd be nice if you could just _hide_ apps not in the group, not kill them... But I guess that would mean they still show up in command-tab.

It sounds like you're forcefully killing processes - can you at least kill them more gracefully? Basically "kill" vs "kill -9".