Hacker Newsnew | past | comments | ask | show | jobs | submit | Zee2's commentslogin

Alignment “appearing” better as model capabilities increase scares the shit out of me, tbh.


Conversely: in humans, intelligence is inversely correlated with crime.

It doesn't go to zero, however!


If you're smart enough you just use the laws as written to get what you want, or change them.


Yep


> Conversely: in humans, intelligence is inversely correlated with crime.

If you're measuring the intelligence of criminals who have been caught, why would you expect it to be otherwise?

IOW, you're recording the intelligence of a specific subset of criminals - those dumb enough to be caught!

If you expand your samples to all criminals you'd probably get a different number.


It very much depends on the crime. The truly awful stuff is committed by intelligent people.


> Conversely: in humans, intelligence is inversely correlated with crime.

Inversely correlated with crime that's caught and successfully prosecuted, you mean, because that's what makes up the stats on crime. I think people too often forget that we consider most criminals "dumb" because those who are caught are mostly dumb. Smart "criminals" either don't get caught or have made their unethical actions legal.


Is that actually well defined given the very low sample size at the top?

To the best of my knowledge, none of the individuals believed to have an IQ >200 have committed an actual crime.

The closest I found is William James Sidis's arrest for participating in a socialist march.


IQs more than about 140-150 don't really mean much. They typically come from mathematical extrapolation that tries to account for age (this young child performs very well on the test, just think what they can do when they're an adult). Adult scores usually show this not to be the case


yeah anthropic tries to address this through mechanistic interpretation but not sure they are progressing as fast in that domain as their model development


They’re a bit behind the curve. Prices are dropping.


The article is from February.


What about Gitea? Hmm…


only thing i found after a relatively quick sleuth

https://github.com/go-gitea/gitea/issues/4175


I have to say the same, but even as someone who isn’t really “relied upon”. The best asset for my own independent well-being has always been knowing which way the wind blows and sailing in that direction.

I have to imagine if there was some internal Polymarket-esque platform I’d be a rich man... (facetiously speaking) Unfortunately knowing the way the wind blows is not as much of an asset to those in charge.


The kerning on this makes me itchy. Everything seems oddly spaced.


"Everything expanding at the same rate" sounds vaguely similar to the truth that what we feel as gravity (standing on earth) is us and everything around us accelerating upwards from the center of the gravity well - and what we feel as "pressure" on our feet is from the earth "holding us up" (in crude terms). So, it sounds crazy but it's not too distant from the truth.


This is super cool. Would love to see a Z80 simulator set up with these examples to play with!


100% Please do this! I wish the same


https://3e.org/private/z80ulmweb/

It's just one-shot AI slop - literally, the prompt was 'make a web based version of [github url of this project]' and it spat this out. It appears to work fine.

I'll keep it up for a couple of months and then it'll be auto-deleted, no sense in keeping it around longer than that.


You know, I'm no hydraulic press expert, but I'm pretty sure that isn't a hydraulic press.


If you read the release, it explicitly does not include the likenesses of human actors. Only animated and illustrated characters are included. (Although, that does cover animated/illustrated versions of characters that are typically portrayed by human actors...)

This is almost certainly due to the photographic/human likenesses of actors being under an entirely separate license and royalty contract than pure IP from Disney.


Interesting; what about say... ironman? Humanoid, has someone inside. Darth Vader, C3PO, or Chewbacca? Or say the Mandalorian?


The ping-ponging is certainly a Gen1 problem. (My Gen1 does this.) Gen1 was essentially an off-the-shelf Mobileye unit, and the performance was, as expected, not good.

Gen2 autonomy stack is completely unrelated to Gen1, and from what I hear is a completely different level of reliability.

(also - this presentation covered yet another, unrelated, gen3 autonomy stack, which shares none of the hardware or models with the existing gen2 stack, either.)


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: