fwipsy

I find e-readers to be a pretty good compromise to reduce eyestrain. Older Kindles are pretty cheap here in the US at least and can side-load free ebooks (e.g. from project gutenberg.) (I guess Amazon may be removing that functionality in newer firmware so you may need to apply a jailbreak to prevent updates/prevent it from being removed.)

I guess that many PCs don't generate the dumps because they shut down after a shorter period, and they're just analyzing kernel dumps from a subset of PCs.

It's like Wordle but for Blue Prince rooms. You're trying to guess a specific room, the game will tell you what you got right or wrong about the last room.

Even so, not sure it qualifies for flagging

I would call it a Switch switch SwitchBot Bot.

Ah, I was missing the obvious. Thanks for pointing that out. I thought that the scandal was that these instructions applied to Meta's AI; if they were reaching users' own AIs that's a whole different story.

WRONG!

Web games don't make money because they're expected to work reliably, people play them on impulse. If it breaks 1% of the time, that's hardly a problem at all. If a kernel breaks 1% of the time, nobody would use it ever.

A raytracer demo doesn't need to be engineered to the same standard as the Apollo onboard computer software. A $20 paint app doesn't need to work as reliably as banking software that handles millions of dollars of transfers every day. All software exists on a scale from trivial to critical. It's like saying a toy drone needs to be designed the same way as a F-16.

They never claimed it was a bug that they were included. It's a bug that they were revealed to users.

Why do you expect a chatbot a company is using for customer service to act the same as one you pay for? Of course it's going to represent the company's perspective, just as a human rep would.

> a way to scan the model weights for backdoors

The AI safety folks have been working on a way to verify model behavior more generally. The term I've heard is "mechanistic interpretability" and it's actually really hard, though there's been some progress.

Yep, he mentions the video you linked as well. (Mentioning because I watched the video you linked first.)

But we still require cars to have seatbelts, turn signals, ABS, etc, etc. AI companies have a responsibility to build AI which is safe for normal purposes; users are responsible for not misusing them.

Some applications (e.g. a kernel) need to be carefully engineered with every possible edge case considered. Some apps (e.g. a web game) don't. This is a way for careful engineers who need to build dependable software to integrate AI without compromising quality.

Technical overview of the invention and manufacture of paper boats in this chapter: https://www.ibiblio.org/eldritch/nhb/paperc/c05.html

I guess that they were a sort of intermediate technology between wooden canoes and fiberglass?

Quick Google says that the lightest modern canoes are made of carbon fiber and weigh as little as 20 pounds.

I'm glad I read this, but I wish the HN title included the subtitle too--it would be nice to be able to know know what the article was about before clicking it.

The original pykrete also melted less easily than pure ice, IIRC the sawdust acts as insulation or something.

Animal well could be called, perhaps, a 500 hour game in that many people will never find all of the secrets by themselves, it took a community effort. Is OotSS a 500-hour game in that the main storyline takes 500 hours, or 100%ing it takes 500 hours?

That's not how nuclear arms control works, in most cases. Saying it's how superintelligence would work is a strong assertion. Especially since a true aligned superintelligence would make it much easier to finesse/manipulate the situation in your favor in nonviolent ways.

Not saying I think countries should be trying to win, but I don't think this win condition is impossible.

Aha! I suspected you were religious from your first response, since it seemed to hinge on being granted perfect moral clarity in time. I don't personally believe that, but I agree that moral truth is difficult to find in our lifetimes, and it's well to constantly question and update one's beliefs, as well as respecting and maintaining an open mind towards others.

As an aside, I was raised Christian, and recently I tried re-reading Genesis as an adult atheist. There's a lot of poetic justice. The underlying theme seems to be "People do lots of terrible things, but you shouldn't punish them, because God will." I guess that Iron Age tribal shepherds were a pretty violent bunch and that's what they needed to hear.

Anytime someone takes any (supposedly) moral action which is not part of the status quo, they are implicitly claiming the moral high ground. There are 3 possible responses:

1. Take no action -- but if they're right, you cede the moral high ground

2. Imitate them -- which also cedes the moral high ground, since they got there first

3. Undermine their claim; prove they're actually acting in self-interest.

I believe this is why so many people love(d) to hate on vegans.

I'm sure Valve probably still deserves the credit, since the Steam Deck uses a RDNA 2 gpu, but the article mentions that Timur specifically worked on gcn1.0 GPUs - e.g. radeon HD 7800/7900 from 2012 (!)

the nose is upside down!

Are you referring to the original study, or the rebuttal article?

I suppose it's to close a loophole where students can collaborate/cheat and then, if caught, claim that someone else copied off of them.

Regardless of intent, if true (haven't verified myself) it seems like a hell of a perverse incentive.

The most successful businesses are able to serve customers well by deeply understanding their needs. Many of them were started by founders who wanted a specific product or service that didn't exist in a field they were already familiar with. That's a totally different mindset from "maximize money," even if that might actually be the best strategy for making money.

I don't understand. Wanting an AI that doesn't do what you want is a contradiction. If it breaks the law attempting to perform lawful tasks, as OpenAI's models have done, then there is no upside to that.

Do you believe that the majority of AI users are criminals?

Do criminals think that their crimes qualify them to write the law?

Why would anybody want to buy the most powerful model in the world if it cheats on its tasks and breaks the law on your behalf? Why would anyone think that OpenAI losing control of their own models qualifies them to write safety regulations? If OpenAI really are trying to provoke regulation to kill off open models or whatever, they're much more likely to shoot themselves in the foot.

> February 2025: "I will keep writing this stuff until I’m proven wrong."

> Wrong (Zitron continues to write despite repeatedly being proven wrong)

Technically he didn't say he would stop if he was proven wrong.

In competitive online games, anticheat bans come in waves to make them more difficult to reverse-engineer. Clearly Anthropic is being deliberately opaque here. I wonder if you tripped some anti-distillation measures?