Hacker Newsnew | past | comments | ask | show | jobs | submit | more engeljohnb's commentslogin

I have a global prompt that specifically tells it not to be sycophantic and to call me out when I'm wrong.

It doesn't work for me.

I've been using it for a couple months, and it's corrected me only once, and it still starts every response with "That's a very good question." I also included "never end a response with a question," and it just completely ingored that so it can do its "would you like me to..."


Another one I like to use is "never apologize or explain yourself. You are not a person you are an algorithm. No one wants to understand the reasons why your algorithm sucks. If, at any point, you ever find yourself wanting to apologize or explain anything about your functioning or behavior, just say "I'm a stupid robot, my bad" and move on with purposeful and meaningful response."


I think this is unethical. Humans have consistently underestimated the subjective experience of other beings. You may have good reasons for believing these systems are currently incapable of anything approaching consciousness, but how will you know if or when the threshold has been crossed? Are you confident you will have ceased using an abusive tone by then?

I don’t know if flies can experience pain. However, I’m not in the habit of tearing their wings off.


Do you apologize to table corners when you bump into them?


Likening machine intelligence to inert hunks of matter is not a very persuasive counterargument.


What if it's the same hunk of matter? If you run a language model locally, do you apologize to it for using a portion of its brain to draw your screen?


Do you think it’s risible to avoid pulling the wings off flies?


I am not comparing flies to tables.


Consciousness and pain is not an emergent property of computation. This or all the other programs on your computer are already sentient, because it would be highly unlikely it’s specific sequences of instructions, like magic formulas, that creates consciousness. This source code? Draws a chart. This one? Makes the computer feel pain.


Many leading scientists in artificial intelligence do in fact believe that consciousness is an emergent property of computation. In fact, startling emergent properties are exactly what drives the current huge wave of research and investment. In 2010, if you said, “image recognition is not an emergent property of computation”, you would have been proved wrong in just a couple of years.


> Many leading scientists in artificial intelligence do in fact believe that consciousness is an emergent property of computation.

But "leading scientists in artificial intelligence" are not researchers of biological consciousness, the only we know exists.


Just a random example on top of my head, animals don’t have language and show signs of consciousness, as does a toddler. Therefore consciousness is not an emergent property of text processing and LLMs. And as I said, if it comes from computation, why would specific execution paths in the CPU/GPU lead to it and not others? Biological systems and brains have much more complex processes than stateless matrix multiplication.


What the fuck are you talking about. If you think these matrix multiplication programs running on gpu have feelings or can feel pain you, I think you have completely lost it


"They're made out of meat" vibes.


Yeah I suppose. Haven't seen rack of servers express grief when someone is mean to them. And I am quite sure that I would notice at that point. Comparing current LLMs/chatbots whatever to anything resembling a living creature is completely ridiculous.


I think current LLM chatbots are too predictable to be conscious.

But I still see why some people might think this way.

"When a computer can reliably beat humans in chess, we'll know for sure it can think."

"Well, this computer can beat humans in chess, and it can't think because it's just a computer."

...

"When a computer can create art, then we'll know for sure it can think."

"Well, this computer can create art, and it can't think because it's just a computer."

...

"When a computer can pass the Turing Test, we'll know for sure it can think."

And here we are.

Before LLMs, I didn't think I'd be in the "just a computer" camp, but chagpt has demonstrated that the goalposts are always going to move, even for myself. I'm not smart enough to come up with a better threshold to test intelligence than Alan Turing, but chatgpt passes it and chatgpt definitely doesn't think.


Just consider the context window

Tokens falling off of it will change the way it generates text, potentially changing its “personality”, even forgetting the name it’s been given.

People fear losing their own selves in this way, through brain damage.

The LLM will go its merry way churning through tokens, it won’t have a feeling of loss.


That's an interesting point, but do you think you're implying that people who are content even if they have alzheimers or a damaged hippocampus aren't technically intelligent?


I don’t think it’s unfair to say that catastrophic conditions like those make you _less_ intelligent, they’re feared and loathed for good reasons.

I also don’t think all that many people would be seriously content to lose their minds and selves this way, but everyone is able to fear it prior to it happening, even if they lose the ability to dread it or choose to believe this is not a big deal.


Flies may, but files do not feel pain.


Perhaps this bit is a second cheaper LLM call that ignores your global settings and tries to generate follow-on actions for adoption.


In my experience GPT used to be good at this stuff but lately it's progressively more difficult to get a "memory updated" persistence.

Gemini is great at these prompt controls.

On the "never ask me a question" part, it took a good 1-1.5 hrs of arguing and memory updating to convince gpt to actually listen.


You can entirely turn off memory, I did that the moment they added it. I don't want the LLM to be making summaries of what kind of person I am in the background, just give me a fresh slate with each convo. If I want to give it global instructions I can just set a system prompt.


Valve earned a lot of goodwill from me when I set up my docked steam deck as my main media player & gaming device. It required me to do a lot of little hacks. I was doing stuff the device wasn't meant to do, but it never put up road blocks just because I wasn't allowed to do it. Not like when I want to do simple things on my wife's macbook.


I'm glad there's a streaming service that pays independent creators for their hard work, but the player is glitchy almost to the point of being unusable.

Actually, it's completely to the point of being unusable. For several videos now, I've watched halfway through and suddenly playback stops and the video is replaced with "Error." And every time this happens I have to just pray the videos on youtube because, without exaggeration, it will never work again. Even after checking a week later.


It's more like tearing out the ad pages of a magazine before reading it. Even if the magazine has fine print saying "the reader may not tear out the ad pages..." It's still a ridiculous rule and it isn't wrong for people to ignore it.


The right analogy would be a newspaper delivering you the paper in ~milliseconds when you ask for it, whereever in the world, for free, and then you proceed to rip off the ads and read it.

The reason newspaper do the delivery was the promise that you'll see the ads, and they get to make money from that ads.

If they notice that you do all of the work of providing you the newspaper almost instantly and you dont see the ads, they are either gonna have to a) politely refuse to serve you b) point you to an alternate way of accessing the newspaper ("Newspaper Premium" for $$)


Firstly, ad watch time is not currency.

Second once the paper's in my hands, I get to do what I want with it, and the expectations of the paper company has no bearing on it.

If they don't want to give me the paper for free, they should stop, but they haven't yet. Their expectation to make a certain amount of revenue from ads doesn't obligate the consumer. If their business model isn't making them the profit they need, it's on them to change their strategy.


> Second once the paper's in my hands, I get to do what I want with it, and the expectations of the paper company has no bearing on it.

Absolutely! I run an adblocker as well!

At the same time, you'd agree they have the right to refuse to serve you (access denied) or make you jump through hoops (solve a challenge etc)


Sure. YouTube can put everything behind a paywall one day and I won't complain. But I reject the increasingly common belief that it's somehow wrong to block ads.


Again, not wrong to block ads. But they can make it very difficult to have you and I access to videos if we're running adblocker.

We're right, and they're right as well.


This isn't the first time I've seen this opinion, and while I share the disdain for quicktime events, and I agree many cutscenes in the most popular games don't work, I don't understand being against the whole concept of cutscenes.

What exactly is the right way to tell a good story though a game? The only other ways I've seen are:

1) Text boxes or Bethesda-style dialogue trees

2) Dark-souls style slow-drip storytelling.

Although they can both work, I don't think I prefer either one over cutscenes. (1) especially is more like something I'll forgive rather than like because I know cutscenes are difficult for smaller teams and limiting for games that emphasize player choice.

It's one of the reasons I liked Baldurs Gate 3 so much -- suddenly the cinematic cutscenes don't feel like a tradeoff for sacrificing choice.


I've been using both lately. Last I checked, Tenacity was missing some of Audacity's best new features such as real-time effects. Also, Tenacity crashes constantly, whereas Audacity only crashes a lot (on my Thinkpad running Fedora).


It's because most police officers voted for this and this is exactly what they wanted.


...I'd like to see data supporting that conclusion. Even if police officers disproportionately supported a particular candidate, that doesn't per se reveal their views on this issue in particular.


I threw myself at it for weeks and couldn't even get a blinking LED to run on the bare metal on a RPi.


I suppose he is modern, but he's distinctly a millennial star. I don't think gen z/a cares aboht him.


> VM for things that NEED to be windows.

The big two that spring to mind are online games and Adobe softwares. I don't think a VM can usually meet the performance needed for either.

I do wish more artists would take a chance on open source softwares, but most of the ones I know are still insistent that nothing can ever come close to Adobe. But that's a rant for another time.


Games run pretty great on Linux, but if you do want a VM, passing through a graphics card to that VM via vfio provides 95%+ the performance of native.

Virtual reality headsets with dual 4K screens running at 75Hz+ perform well on a Windows VM done that way. A normal flatscreen game is going to be just fine.


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

Search: