[dinfinity]

It's also extrapolating on what already exists. We are way beyond 'just some academic theories'.

One can argue all day about timelines, but AI has progressed from being fully inexistent to a level rivaling and surpassing quite some humans in quite some things in less than 100 years. Arguably, all the evidence we have points to AI being able to take over AI research at some point in the near future.

[pier25]

> all the evidence we have points to AI being able to take over AI research at some point in the near future.

Does it?

That's like looking at a bicycle or car and saying "all the evidence points out we'll be able to do interstellar travel in the future".

[dinfinity]

> That's like looking at a bicycle or car and saying "all the evidence points out we'll be able to do interstellar travel in the future".

Incorrect. The difference between interstellar travel and land based travel on earth is enormous. The difference between current AI and AGI is tiny in comparison.

You're not saying it, but people might interpret 'interstellar travel' to be faster than light or very close to it, which means breaking the laws of physics or spending prohibitive amounts of energy. AGI needs no such thing, as evidenced by human brains running on < 100 watt.

Interstellar travel at far lower speeds is indeed probably something we will be able to do, looking at what we've done in space travel in the past 100 years. Although again, the resources required to do so as dictated by the laws of physics make it incredibly expensive. Given the low benefit it is probably not going to happen soon.

Reaching AGI is cheap as fuck and far more potent in comparison, so it will happen sooner.

[pier25]

> The difference between current AI and AGI is tiny in comparison.

Splendid. You should probably tell people like Yann LeCun this. He will be happy to hear it. /s

> Interstellar travel at far lower speeds is indeed probably something we will be able to do

Speed is not even an issue. We don't even know bigger problems like the long term effects of zero gravity in the human body or what dangers we'd encounter beyond the heliosphere.

[dinfinity]

> Splendid. You should probably tell people like Yann LeCun this. He will be happy to hear it. /s

Do you have an actual counterpoint or is this edgy nonsense the extent of your capabilities?

> We don't even know bigger problems like the long term effects of zero gravity in the human body or what dangers we'd encounter beyond the heliosphere.

So you agree that your analogy was bad. Good.

[pier25]

So now that you've run out of fantastical declarations you are now recurring to ad hominem attacks. You must be fun at parties.

[suddenlybananas]

>surpassing quite some humans

I don't really think this is true, unless you'd be willing to say calculators are smarter than humans (or else you're a misanthrope who would do well to actually talk to other people).

[spongebobstoes]

idk, if you try something like o3-pro, it's definitely smarter than a lot of people I know, for most definitions of "smarter"

Even the chatgpt voice mode is an okay conversation partner, and that's v1 of s2s

variance is still very high, but there is every indication that it will get better

will it surpass cutting edge researchers soon? I don't think in the next 2 years, but in the next 10 I don't feel confident one way or the other

[dinfinity]

OK, go ahead: Write a 10 page reasonably well-researched and sourced report on the political situation in the Netherlands in the past 20 years. You have 15 minutes.

The various 'deep research' tools available today can do this. You can't. AI already surpasses you (and me) in this task. Now think about the result after asking less intellectually capable people to do this.

Before you start balking about "hallucinations", pick some country you know about and ask a similar question to Google Gemini (2.5 Flash, and enable 'Deep Research'). Check the results and reconsider your 'calculator' straw man and 'misanthrope' ad hominem.

[suddenlybananas]

Yes, and a calculator can add 104123412341235+243524352435 much faster than I can.

>Check the results and reconsider your 'calculator' straw man and 'misanthrope' ad hominem.

How is the calculator a strawman? What is the argument that I am attributing to you that you do not hold?

As for the ad-hominem: I'm glad you don't dispute your misanthropy.

[dinfinity]

> How is the calculator a strawman? What is the argument that I am attributing to you that you do not hold?

I said: "AI has progressed from being fully inexistent to a level rivaling and surpassing quite some humans in quite some things in less than 100 years"

You attacked the intentionally inane (which is the purpose of a straw man): "Calculators are better at all humans in arithmetic, so they are smarter than all humans"

In no way is what I said close to what you attacked.

> As for the ad-hominem: I'm glad you don't dispute your misanthropy.

Sure, double down on your fallacious nonsense instead of opening your mind to reason and engaging with my point in good faith.

I provided properly described evidence for my point. You're stuck in "AI is just some calculator on steroids". Do your 'deep research' assignment before responding.

[suddenlybananas]

If you can't tell the difference between a strawman and an analogy, then no wonder you're so impressed by AI.