jpc0

Review the "Menu Tree" from win 11 and win 95.

I could use like 3-4 keyboard navigation items and have my app open in win95. In win11 I must use my mouse and it is slow as balls and I have a ryzen 7 + GTX2080ti this isn't entry level hardware.

If the start menu was still as usable as it was then I agree I an many others would have no reason to complain but it isn't and the "better" alternative is only better about 50% of the time so in general what I end up doing is pinning everything to the task bar or putting it on the desktop and try my best to just do the rest in the terminal.

> In modern WIndows, from 7 onward, I can hit the meta key and type the first letters of the app I want to open, hit enter and boom, it's opened.

I mean in theory I can also do that on my Win 11 machine... In practice if I actually performed those exact steps I will probably have edge open up with a web search of the letters I typed.

The amount of times I actually have to use the now even less user friendly way of finding an app in the start menu regardless is infuriating, give me both, a star menu that is deterministic and a search that works...

Just because I want the older stuff does not mean I have to give up some of the newer stuff.

> If you are going to release them, which I would not be in favor of, you ban them from all electronic devices.

I want to ask two questions here.

If you believe the prison system can change people and make them better, consider how you would live your current life without access to all electronic devices. Do you still think a flat out ban is reasonable?

If you don't think the prison system can bring about actual change then what do you believe the alternative is?

I think my question boils down to this.

Would you be willing to spend a portion of your salary for the rest of your working life to support a pedophile? That is exactly what would happen if they were cut off from all electronic devices or imprisoned for life.

cough FFMPEG, cryptography…

So no actually we very much do, because sometimes it is worth it.

My bigger argument that is if I cease living the atoms that correspond to my body no longer has consciousness.

So is your argument that whenever a session ends or I interrupt a session that consciousness ceases for the LLM and it has died?

Then how do you correlate that with a consciousness not being able to be returned one dead? You can try to make the argument that consciousness is the firing of individual nuerons in a fixed system but we have never been able to model that and some pretty popular theories tend to believe that is a by product of consciousness and not the cause of it, once again not exactly possible to argue for or against.

If AI is conscious then what about it is conscious? Because turn to turn it might be served from completely different GPUs and I can just change something in the context it is fed and it will have completely different output.

It is in the end a set of mathematical operations that if not queried will do nothing.

That is not true for any other animal on earth so whether you consider humans as superior to animals or not I would like the make the argument that something should at the very least be alive to be considered conscious, ignoring any scholarly definition of consciousness.

Pretty much if you consider an LLM conscious then my pocket calculator doing a mathematical calculation should be considered conscious by the same argument since it is a simpler version of an LLM.

People include licenses because if there isn't any license copyright law applies and you may not create any copy of said code. You as a third party have no use of the code without a license

MIT does not wave the right to attribution so no even under MIT it is illegal to reattribue work.

Authorship and the underlying code are seperate rights under law.

This seems like one of those “reality has a surprising amount of detail” situations.

Surely getting something to autonomously without fail extend an arm and plug in for the lifespan of these vehicles vs just park in this allocated spot you would park in anyway is an obvious tradeoff.

> Today's software is still the same software that ran perfectly well half a dozen years ago.

This statement is quite honestly not true at all. Just take the two largest OS from 6 years ago and compare resource usage between them and you will find you are incorrect, never mind the software running on it.

Not sure if it’s a setting but my mac definitely asks me if I want to reopen windows after a forced reboot.

I'm not entirely sure I would put that on BMD. AMD support on linux when it comes to actual compute capabilities has always been hit or miss.

Only recently has AMD even become viable for LLM inference on consumer chips and that is the same compute codepaths Resolve would depend on.

So effectively AMD is the issue, AMD on linux is great, AMD on linux for a workstation was kind of hit or miss.

If you allowed that in your contract when doing the commissioning that's on you.

I wouldn't be surprised that if you asked an AI to weite said contract it would add a clause regarding copyright ownership of all codr and will put the onus on the developer to prove ownership of all of it.

Effectively you could sue them if you ever get sued.

When it comes to copyright and licensing it's complicated and it's best to write the code by hand.

As in all cases it depends on jurisdiction. For example where I am performers have a right to not be recorded so you may in fact not make such recording, you didn’t not necessarily violate copyright but you violated related rights.

And likewise if you distribute any sort of copy of the recording you made you are violating at least one if not more copyrights.

By that very definition you did not create it.

Yes it’s the same as using a stock drum pattern in a drum machine, it is not copyrightable because no human was involved in any part of it.

If you have an idea and want rights to it then do it the old fashion way and pay a developer to do a commissioned work and you can have your copyright, heres the catch, that will cost a hell of a lot more than 100usd a month

There has been more than I project where I literally didn’t even look at the code.

I prompted what amounts to verbose “I want X” and then did QA. I’m perfectly happy with an LLM being credited with that code and there being no copyright existing for that code.

For some people that is their life’s work and they want to clutch pearls. Their sole contribution was a half baked idea and they shipped QA out to their “users” but they want to be credited with any rights.

There is definitely a continuum in LLM usage for code, do I agree with an AI blindly stamping every commit, not really.

Do I see LLM generated code as equivalent to me digging a hole with a shovel, it depends. Sometimes there was very little shovelling, other times there was no me involved and you may as well credit the entire hole to the shovel.

Where this will come in is when it comes to copyright and licensing.

If your entire product is LLM generated you sure as hell have no right to place any license on there other than potentially a MIT equivalent license, even that is dubious though but from an organisational standpoint MIT probably will be more widely accepted than saying it is uncopyrightable.

My argument being I would rather know that you didn’t even look at the code, which is what this will achieve, whether I agree with it or not at the very least it will make it easier to sift through the garbage.

My argument there is likely there was too much surface area in the environmental to start with.

If your webserver bundled the kitchen sink but you never used it the easiest way to make it more secure is to remove the kitchen sink from production code/codepaths.

There may very well be legitimate edge cases where there is some novel issue found but in some of these cases the AI had arbitrary web access when all the task required was very specific web access, we’ve been able to parse urls for a very long time and it is rather trivial to just deny a toolcall if it is outside of the expected domain.

But that’s the hard way that requires time and diligence to do, the easy way is give it access to curl and ask it to not do anything bad while setting up its only feedback to be to solve the problem at hand.

We are really in an age where there are many exploits being found and patched, if an AI made use of a novel exploit then great, write up a report, patch/report the bug and apologise.

But using a case of clear engineering failure, and yes even if the failure is despite your best efforts, for marketing really does not seem like you have any intent to correct the issue.

And we can loop all the way back to regulation of AI, if the industry refuses to be better then governmental will do it instead and their solution will very likely be inferior in all ways.

My argument isn’t against those that actually put in the effort and got held accountable, it’s against the “we gave our agent bash and internet and it hacked xyz”.

Bash and internet in that example might be highly abstracted but it’s still bash and internet.

Just look at the replies in this very comment thread, it’s pretty much “We tried nothing and we’re all out of ideas”

In the only other discipline you mentioned, engineering, there would be reviews and any negligence would result in direct action against the engineers that signed off.

For some reason when it comes to building AI harnesses the default response is an ad piece and people shilling how smart and sophisticated the model is.

Imagine a dam collapsing and the engineering firm pumping how smart and tricky water is.

If it’s hard be more diligent, move fast and break things doesn’t really apply in all cases.

These things are not human, have no agency and cannot be held accountable.

We don’t need to restrict them from doing things, we need to default to allowing them to do things.

“My agent did XYZ because I allowed it to” is the only valid argument that can be made, and not not every agentic harnass is just a shell toolcall, every one I have built has a specific defined usecase and toolcalls that allows it to execute that usecase and no other usecase, because that is good practice.

Does that make it less capable, hell yes because I am held accountable for it’s actions by my stakeholders and the same should be true of others.

IT IS NOT ALIVE. This things are computer programs running in compute on a computer, you are responsible for their actions just like you would be responsible for the actions taken by a script run in a cron job.

The AI can literally only do what it has available in the agentic harness. I don’t ever get this argument about the agent did XYZ and we didn’t know or expect that. You gave it the ability to do that and you should be held liable, if your children play with knives that you gave them and they end up hurting themselves or others then you are responsible. You were the responsible party at all times.

I’m not for or against regulation but really don’t tell me the agent did xyz when you gave it the ability to do so, these things are not alive.

I hope to see more of this across the industry.

I definitely make use of AI but in my experience I almost always could have done it better myself, the places where I threw AI at the problem I didn't care about the results being good, only good enough.

When we see memory and compute requirements for version x+1 of software decrease instead of increase I will happily say AI is the oracle people proclaim it to be.

In what situation do you need to do that is what the previous commenter qas getting at.

If you want a graphical browser just open it locally...

Capex != Opex

Your are measuring two very different things.

And you are only considering electricity bills for the GPU. Higher TDP also means more heat which means more cooling.

It's not really easy to make an off hand comment about costs. A 30-40% decreaae in electricity usage and heat output for a fleet of GPUs definitely makes a massive difference to your opex bottom line.

Group delay is a poor argument.

Unless you also have a pretty decent monitoring system the group delay of the speakers isn't going to be consistent so the filters before them wouldn't matter all that much...

Even in that case I would have a hard time believing that any human in a blind test would be able to perceive a group delay of even 360deg above 2k...

You are talking about sub milliseconds differces in the time frequency content arrives at the ears, just tiling your head slightly will have a greater impact...

> A lot of capacity is coming online in the next 5 years

Is this true though? I don't really have time to do the research and have no dog in the race but I'm sceptical...

But then again I'm not there one making our profiting from the claims that there is billions being invested into infra...

> I just want a damn API key, I keep it a secret and revoke if necessary and don't need 10000 layers of auth bullshit tangled up in every layer of every platform

Then implement that on your app... You are just generating a random key and storing a hash + salt.

Auth is hard only applies to auth for many users. For your own auth this is dead simple and made even simpler if you use a half decent framework...

If you are really worried about the implementation being insecure throw one of the many moderately frontier models at it, they are really not bad at finding issues in an auth system that simple.

Home networks are almost exclusively secure by default on any reasonable hardware.

The bigger issues is not remembering hostnames vs IP addresses.

Unless you have explicitly changed it what is the hostname of your mobile device? How about your PC?

The reality is with an even mildly competent DNS+DHCP implementation that is all you would need...

And mDNS otherwise but it seems only Apple ever bothered with that being default.

Enable sanitizers on test suites and fuzzers.

Enable warnings and WError

Use clang tidy and other static analyzers

Actually use a modern compiler and enable the safety features they ship with

Most of these things have solutions that would take years of work in an existing project so it isn't done

And it takes significantly more effort to write good modern C++ code than Rust code

So Rust wins

But I don't like writing Rust code, I do enjoy writing modern C++ code, the tradeoff is modern C++ can be a tooling nightmare... Try shipping a modern stdlib on an old platform, it is truly infuriating, I don't want to be a build systems expert but I need to be to use a safer alternative.

> What made open source great, is the fact that if you find a problem, you can patch it. It's what motivated me, anyway.

What exactly is different now?

> it's under development and very likely will be forever.

So is Sqlite. Last time I checked they are still actively developing Sqlite.

Do you mean you can't just grab a current release and hold on to that? Well it's pre-alpha... That's the point...

    1. Free Redistribution
    2. Source Code
    3. Derived Works
    4. Integrity of The Author’s Source Code
    5. No Discrimination Against Persons or Groups
    6. No Discrimination Against Fields of Endeavor
    7. Distribution of License
    8. License Must Not Be Specific to a Product
    9. License Must Not Restrict Other Software
    10. License Must Be Technology-Neutral

Open source has nothing to do with the right to contribute upstream. It's about you being able to use the software how you like and make changes to it and redistribute it.