Viewing profile — sixfiveotwo

> I think a memory address is a number that CPU considers to be a memory address I meant to say that, indeed, there must be some concept of CPU for a memory address to have a meani…

How would you define what a memory address is without first defining in which context it has a meaning?

I'm sorry if you feel that way. I am in no way trying to judge you; rather, I'm trying to get closer to the truth in that matter, and your input is valuable, as it points out a dis…

> Yeah like several hundred "Chess IM/GMs react to ChatGPT playing chess" videos on youtube. If I were to take that sentence literally, I would ask for at least 199 other examples,…

Very strange, I cannot spot any specifically saying that ChatGPT cheated or played an illegal move. Can you help?

That's simple logic. Quoting you again: > Machines are good at applying rules, so when they fail to apply rules correctly, it means they have incorrect, incomplete, or totally abse…

I think the article briefly touch on that topic at some point: > For one, gpt-3.5-turbo-instruct rarely suggests illegal moves, even in the late game. This requires “understanding”…

> Whereas the LLM makes "moves" that clearly indicate no ability to play chess: moving pieces to squares well outside their legal moveset, moving pieces that aren't on the board, e…

> Machines are good at applying rules, so when they fail to apply rules correctly, it means they have incorrect, incomplete, or totally absent models. That's assuming that, somehow…

It's a good point. But this math analogy is not quite appropriate: there's abstract math and arithmetic. A good math practitioner (LLM or human) can be bad at arithmetic, yet good …

Quite interesting, thank you. However, in this specific instance, even if the text cannot be changed, couldn't the error itself in the server be processed and signaled differently,…

thank you, that looks awesome.

Sorry, I understand it was a bit intrusively direct. To bring some context, I toyed a little with neural networks a few years ago and wondered myself about this topic of training a…

> I spend much longer trying to figure out how to get 1-trit training to work and I never could. What did you try? What were the research directions at the time?

Indeed, you can get a lot more from dependent types than Damas-Hindley-Milner inference, yet does it mean that you should use the former everywhere?

Yes indeed, I realized that it was way more complicated than what I initially imagined. When I first read the article, the sequence of subgroups that were described evoked that ima…

Clearly that first intuition doesn't work. The Hamiltonian cycle for decimal numbers is perhaps an equivalent of grey code? And if it exists, is there a connection with the Rubik's…

My intuition when reading the first lines of this article was that, just like when searching exhaustively for the correct combination on a padlock, one would cycle through each sub…

Perhaps the problem could be different. Wouldn't the energy gathered from renewable sources otherwise be used by nature? At which point will the amount we capture be large enough t…

> This is a very good example of how you can cause real world harm with by trying to game the system for yourself. Isn't that the rule that Uber itself already imposes on its custo…

Well, maybe...

If you have a look at the underlying network traffic, you'll see IP packets carrying TCP data, ie. The protocol field in the IP packet header will be set to TCP; this could be assi…

Thank you for bringing this to my attention. I will try to remember that Let me coin a new term to help me in that task: the "swarm gallop", which would be that technique applied b…

They just hate being manipulated.