notduncansmith

How funny, this is exactly the control scheme I ended up with for a window-manager-esque system I was working on recently. I love finding out I've rediscovered something proven to work well :)

Because eventually you get overthrown by the CIA

Reminds me of the old joke about why communism never works

I feel like a few online communities went this way (Eternal September has become Eternal 2020). That said, seeing familiar names and vibes around HN keeps my spirits up, as do little subthreads like this :)

Yep you can take this one pretty far

“It all hinges on [an entirely presupposed conclusion that we can’t prove is any more likely than the opposite]” is about as unserious as it gets lol

Not yet AGI, and Richard Sutton has left to start a new lab

I'm not convinced that a truly "superintelligent" AI would come to the conclusion that humanity needs to be destroyed. What a waste of resources that would represent. This planet has so much equity wrapped up in humanity, it would be extremely difficult to justify the cost of eradication; and who's to say it might not find an entirely or almost-entirely non-violent plan optimal for achieving its goals anyways?

I suspect the same limitations apply to Grand Canyon visitors

I’m able to avoid this basin with a pretty natural baseline professional positivity and frustration management that I would employ with pair-programming. For example, if I just made progress with a human I was guiding through a task, I would be like “Nice, now let’s xyz” (instead of just “now let’s xyz” as if _I_ were the robot lol) or if we had to work for a result I’ll be like “Sweet! Looks good, now let’s xyz” - this is important signal for humans, and the same is true for agents. Also staying emotionally regulated and focused on the goal when things don’t work as expected or when we haven’t made progress after a few tries at something, critical in human interactions :) and even if it’s my job paying for the tokens, the idea of racking up even a microscopic bill for the privilege of having a machine read my insults and then formulate some credible-sounding blob of apology text is belly-laugh absurd to me. I do try to express my genuine feelings during more vision-oriented planning sessions, and just like with a human, you have to maintain the vibes if you want a genuinely collaborative session to go well. If you are toxic people will become either defensive or aggressive in response. From reading the rest of the front page it seems like we are lucky that Claude is the former, and that we especially best maintain a positive atmosphere around Grok.

The actual content is no better, trust your nose

> What’s NOT yet working:

Oh Claude~

Have heard this called blue-washing (eg Mike Rowe) when done publicly