YAAK

[YAAK @YAAK]

@farzyness Does it make sense to also include the API costs in the report? Would be interesting to see that. Although it can become irrelevant if the capital grows large enough. I'm assuming the cost of research to trade 1 share is, roughly, the same for trading 100 shares.

[YAAK @YAAK]

@googlegemma Also for "Generate SVGs" task
`./run.sh --scenario svg --topic "Technology and AI" --tasks 10`

[YAAK @YAAK]

@elonmusk @grok How much mass can be transferred from Earth to the Moon without significantly altering the Moon's orbit?

[YAAK @YAAK]

True human-level intelligence demands continuous learning that can actively override its pre-training. It relies on a critical balance: the ability to forget the noise so it doesn't overfit, while remembering enough to stay useful, much like how the human brain changes during sleep. Ultimately, it needs to abstract vast amounts of data analysis into a distinct 'feeling' or intuition.

We don't see this ability in current frontier models yet. They are only a fraction of what human intelligence is. However, that doesn't mean these tools won't automate tasks that are currently handled by humans.

Even without true intuition, these models are capable enough to automate a vast number of tasks. The market demand for routine or less creative "cognitive labor" is falling. Humans in the middle of the intelligence spectrum are being outcompeted by "low-level artificial intelligence at scale". In an economy that is already tightening, first, we will see declining incomes for the less adaptable, followed rapidly by their total unemployment.

In this assumed future, isn't the winner the one who owns the "low-level AI at scale" and the loser the one who competes with it?

[YAAK @YAAK]

Was "The Matrix" just a movie, or a preview?💊

Don't you feel like the scene in The Matrix, where Neo gets plugged in and instantly learns martial arts, is basically what we’re watching happen with LLMs right now?

We plug all the documented human data into these models, and suddenly they "know" things and are able to answer our questions.

Being able to learn everything has always been a dream. Just absorbing every book, every paper, every piece of documented history. But obviously, that’s impossible for a human brain (at least mine) and not even possible in one lifetime (at least not yet!).

So, maybe rather than trying to learn it all individually, the real dream is to build a "Mind" that can hold all that knowledge.

That leads to a hard question: "If you had access to a mind that knew everything... what would you actually do with it?"

And no, I'm not referring to "the answer to the ultimate question of life, the universe, and everything" I am genuinely curious what you would actually do with it.

We talk a lot about the technology, but not enough about the purpose.

What would be your first request to "The Construct"? "Lots of guns" or "how to fold a protein 🧬"?

#AI #TheMatrix #curiosity #future #technology

[YAAK @YAAK]

Verifying myself: I am yaak on Keybase.io. KY7b-HT-yRx8aNvNVF_dkiNSJ4XzChkqizKI / https://t.co/5pi4YH35xd