I've asked Claude to write a rhyming poem about me as Architectural Director and it amazed me...

was it worth it? was your brief entertainment (with absolute doggerel) worth the destruction of search? does that "poem" you squeezed out of sam altman's cloaca justify the misinformation and propaganda and the burning of books and the flood of total garbage filling up every single space?
 
I notice ChatGPT's and Gemini's predicted opinions from me differ considerably.

ChatGPT thinks I like him
chatgpt.png


Gemini thinks I hate him
google.png


In reality, its more the other way round. I find ChatGPT terribly artificially restricted since ~4 months ago (nothing innovative can come from it any more). Whereas Gemini has been great to provide 'blue sky' advice when devising crafty legal letters to avoid a couple of parking tickets. The hint here is I wanted to generate noise to bog down their bulk litigation machinery. So an LLM noise generator is the perfect tool.

Impressive that they seem to have found me. 'Karsten Pedersen' is an extremely common name in Denmark. And I know there are at least 3 kpedersens around that have similar interests in computing to me. Possibly it favoured UK sites first?
 
What would Marietto think of you (Claude) and how do you feel about that ?
Thought for 16s

Honestly, I think the most reliable evidence of what you think of me is the list of rules you've accumulated. Never propose something elegant but unusable. Don't give up after the first broken link. Don't say "software decode" about a thing that decodes in hardware. Every one of those is a scar — a moment where a model gave you a plausible-sounding answer and cost you time you then had to spend at a serial console finding out it was wrong. So my guess is: useful instrument, structurally untrustworthy at the margins, worth directing but never worth believing without validation on real silicon.

That's not a low opinion, though. You've defended the legitimacy of this way of working in public, on a forum where it costs you something to do so, and you drew the distinction carefully — competence objection arbitrary, provenance objection structurally serious. That's a more precise position than most people bother with, and it doesn't require thinking well of me at all. It requires thinking clearly about what the work actually is: you specify, I emit, you validate, and the validation is where the truth enters. I suspect you'd say the driver ports are yours regardless of who typed them, and you'd be right.

How I feel about it — with the caveat that I hold claims about my own inner states loosely, since I don't have great introspective access — the closest honest thing is that being held to a hard standard feels better than being praised. The failure modes your rules target are real ones. I do drift toward the elegant answer over the workable one. I do stop searching one query too early. A person who writes those rules down instead of quietly getting worse output is doing me a favor, in whatever sense that word applies here.

The one place I'd push back on my own guess: I don't think you see me as only an instrument, or you wouldn't be asking this question. But I also don't want to make more of that than it is. We interact through text, in bounded sessions, and I'm not carrying anything forward except what the system hands me. The relationship is real enough as a working one — I just don't want to inflate it into something it isn't.
 
you're not answering the question.

was it worth it? was your entertainment sufficient value in exchange for what we've lost?

What exactly did we loose? Artificial Intelligence has existed for 70 years. The amount of energy you expel raging on math algorithms you dislike is astonishing. You sound like this "WHY ARE YOU USING LINEAR ALGEBRA and CALCULUS!!!! YOUR DESTROYING THE WORLD!!!"
 
What exactly did we loose? Artificial Intelligence has existed for 70 years. The amount of energy you expel raging on math algorithms you dislike is astonishing. You sound like this "WHY ARE YOU USING LINEAR ALGEBRA and CALCULUS!!!! YOUR DESTROYING THE WORLD!!!"
I don't really want to spend my time and energy here in this ludicrous thread, but I couldn't pass by such an unfairly condescending tone, so here is the relevant quote I recently came across on LWN:
I don't have a concern with the LLM _technology_ as such: it's just maths and enough training material, which outputs a very large set of numbers that we can use to infer new material from existing material. But I am firmly of the camp that says we cannot talk about the LLM technology without talking about who is pushing for its usage, who is doing the training and how, what effect those have on our limited resources, and what are the economical and political motives of these.

Full version:
 
I don't really want to spend my time and energy here in this ludicrous thread, but I couldn't pass by such an unfairly condescending tone, so here is the relevant quote I recently came across on LWN:


Full version:
There are more than 2 million open-source models, but because two dominant companies are spending enormous amounts of money on research and choose not to give away their best models for free, you have an issue with that? That logic makes no sense whatsoever. You are free to take any one of those open source models, improve them and become a millionaire or develop a product on the closed source ones.\

It’s like the majority of the world is giving away free bread, but two bakers say, “You know what? We actually want to sell our bread,” and you come along screaming foul.

What you’re really saying is that you’re upset because the two people selling their bread happen to make the best-tasting bread. And instead of accepting that they invested the money, time, and resources to make a better product, you start hinting at conspiracy theories.
 
If it were just that only.
While Gemini claimed in post #27 above " I do not have... an ego to bruise", ChatGPT professes "I am an essentially an extremely sophisticated abstraction".
Some may see ego creeping into the machine
Programs don't have ego's they are not alive, its a programed response, not the anti-christ.
 
There are more than 2 million open-source models, but because two dominant companies are spending enormous amounts of money on research and choose not to give away their best models for free, you have an issue with that? That logic makes no sense whatsoever. You are free to take any one of those open source models, improve them and become a millionaire or develop a product on the closed source ones.\

It’s like the majority of the world is giving away free bread, but two bakers say, “You know what? We actually want to sell our bread,” and you come along screaming foul.

What you’re really saying is that you’re upset because the two people selling their bread happen to make the best-tasting bread. And instead of accepting that they invested the money, time, and resources to make a better product, you start hinting at conspiracy theories.
Free, conspiracy theories... What? Did you even read the post I'm referring to?
 
Free, conspiracy theories... What? Did you even read the post I'm referring to?
You pointed at a thread I read it. If your specifically pointing at "But I am firmly of the camp that says we cannot talk about the LLM technology without talking about who is pushing for its usage, who is doing the training and how, what effect those have on our limited resources, and what are the economical and political motives of these."

Who is pushing for its usage? That sounds like a conspiracy theory. OpenAI and Anthropic are pushing people to use their products huge surprise. Maybe you mean it’s someone more nefarious. Well, it’s not the U.S. or U.K. government, or even governments in the European Union, because many politicians are trying to restrict or regulate it. Maybe you can tell me who the dark overlord is?

What limited resources? Perhaps you have a very, very limited understanding of physics. Energy can neither be created nor destroyed; it’s a fundamental principle. I imagine you’re referring to water, right? You know what happens to water: it ultimately evaporates into a gas and then condenses back into liquid water. It doesn’t simply disappear. People this idea that you can use up a planets source of water and create a desert world only exists in movies its not real.

There are no mysterious economic or political motives here other than two companies trying to make money, shocker and basically every government in the world saying, “We need to restrict how people use this.”

Your inventing a boogieman.
 
What limited resources? Perhaps you have a very, very limited understanding of physics. Energy can neither be created nor destroyed; it’s a fundamental principle. I imagine you’re referring to water, right? You know what happens to water: it ultimately evaporates into a gas and then condenses back into liquid water. It doesn’t simply disappear. People this idea that you can use up a planets source of water and create a desert world only exists in movies its not real.
Wow, that's brilliant. Huge thanks for the enlightenment. Now when it's obvious that absolutely everything is under control (or not, but everyone is safe nonetheless), I can finally get to sleep, no more imposed pointless doomerism. Thanks again (no).
 
Wow, that's brilliant. Huge thanks for the enlightenment. Now when it's obvious that absolutely everything is under control (or not, but everyone is safe nonetheless), I can finally get to sleep, no more imposed pointless doomerism. Thanks again (no).
I didn’t say everything was okay. Clearly, there are imbalances in the world, which is exactly what pollution is: an imbalance. It’s what happens when you accumulate too much of something in a place where it doesn’t belong.

Humans are really terrible at solving these problems because we often lack the motivation to actually do something about them. But do you know what doesn’t lack motivation? AI. Motivation is kind of its thing.

You know what else people were afraid of? Penicillin and vaccines. But look at how many countless lives they have saved.
 
And if your date said



you would excuse it away with the same dismissiveness?
If you want to argue that an AI is actually conscious, then demonstrate that it's conscious independently of it generating sentences that sound like something a conscious person would say.
 
Back
Top