fourthark
fourthark on Hacker News
Does work with ssize_t, just not necessary.
It's an idiom or simile; it's not literally true.
Maybe you should try voting harder.
Presumably the repo is private...
It requires knowing how to code, at some level.
That doesn't solve the someone-might-blow-it-up design problem cited in TFA.
> Response
> In 2012, on the 35th anniversary of the Wow! signal, the Arecibo Observatory was said to have beamed a digital stream towards Hipparcos 34511, 33277, and 43587.[45] The transmission consisted of approximately 10,000 Twitter messages solicited for the purpose by the National Geographic Channel, bearing the hashtag "#ChasingUFOs" (a promotion for one of the channel's TV series).[46] The sponsor also included a series of video vignettes featuring verbal messages from various celebrities.
What an inane, embarrassing "response", if the original was any attempt to communicate. (Sounds like it probably was not, but still...)
The exception that proves the rule.
Seems like a fairly direct parable against AI, suggesting that even if it's right it's better to think for yourself.
IMO you should also wait half an hour for the food not to be delivered. Isn’t that the suspenseful part?
> This started off as a bet with myself that APL notation would provide an easier way to make a voxel game.
Did you win the bet?
It's intended to be a markdown with code. So it has nesting and scopes and code/math modes in with the markdown.
Idk, I find it mind-bending but quite readable.
Interesting use of evals.
Might help interpretation to say on the front page that it's a five point scale with 0 (or 1?) being the safest score. This can be picked up from colors and the bars in the individual reports, but it takes a minute to figure it out.
Capitalism doesn't work for big infrastructure projects? Who knew?
Interesting, I got a completely different result on green/blue on this one, way more green whereas I got average on the individual test. Going between very different colors makes it hard to reset - they might consider breaks between spectra.
> You gasp. You hyperventilate. Your heart rate jumps. Your blood pressure climbs. All of this in a few seconds.
There's something especially creepy about AIs talking in the second person about biological processes they don't experience.
Yes, using nine specialized cameras. Still very impressive but the human is overmatched on equipment alone.
> reset the context
Yes. Do this. These problems indicate you have muddled the context.
This was too long and I didn't read the whole thing, but I'm glad the author came to understand that arguing won't help.
> But if you are the kind of person who cries out against this abomination we must warn you that people who go through life expecting informal variant idioms in English to behave logically are setting themselves up for a lifetime of hurt.
I think the point is that you have a better idea of what you want it to remember and even a small hint can have big impact.
Just saying "write up what you know", with no other clues, should not perform any better than generic compaction.
Wish we could downvote articles. Is it legitimate to flag AI slop?
Does it fix the security flaws that caused the original project to be shut down?
Odd how this thread is a recapitulation of your experience with the LLM.
What is take from this is that it's pointless to try to find out why an LLM does something - it has no intentions. No life and no meaning, quite literally.
And if you try to dig you'll only activate other parts of its training, transcripts of people being interrogated - patients or prisoners, who knows. Scary and uncreative stuff.
Most survive by bending. See e.g. Google and surveillance a decade ago.