mckirk

"THERE IS ABSOLUTELY NO CAUSE FOR ALARM"

Sorry for being off-topic, but 'rouge agents' was too adorable to leave unmentioned.

_Every_ agent? I surely hope not. But it would be an interesting... artisocial experiment?

Just don't be confused if they then follow the commands side-effect free.

The fact that Orban is called Viktor as his first name meant your first sentence confused me greatly for a second.

I mean, it's understandable; having to endure a lockdown _with_ Doordash was really rough on our civilization.

Damnit, I am pretty sure I had a few-year-streak going until just now. Welp, off to the grind again, I suppose.

Nitpicky reply questioning the adherence of OP's comment to HN guidelines.

Along these lines: I really like the 'Climate Reanalyzer' project by the Climate Change Institute at the University of Maine [1]. There's so much good stuff there if you click around a bit; you can create custom plots for the surface temperature of different regions for example[2], which quickly shows you that Western Europe has actually warmed a lot more than the global average, and we're closer to +2°C already in that region.

[1] https://climatereanalyzer.org/clim/sst_daily/?dm_id=world2 [2]: https://climatereanalyzer.org/research_tools/monthly_tseries...

If writing goes the way music seems to be going with Angine de Poitrine gaining a huge following as a kind of allergic reaction of people against the 'AI sameness'... then we could be in for a wild ride.

On the other hand, music is primarily an art form and writing (nowadays) is primarily utilitarian I would contend, so maybe the analogy doesn't quite hold up.

I have to admit, the movements and interactions looked so uncannily natural that my intuitive suspicion was that this might be another instance of a 'fake it till you make it' demo, and the robot was actually controlled by a person. Though if this is real, that's of course some of the highest praise they could hope for.

I have to admit that this is also what keeps me coming back to LinkedIn. My brain is dangerously easy to motivate by dangling a virtual leaderboard in front of it.

I think what that research found is that _auto-generated_ agent instructions made results slightly worse, but human-written ones made them slightly better, presumably because anything the model could auto-generate, it could also find out in-context.

But especially for conventions that would be difficult to pick up on in-context, these instruction files absolutely make sense. (Though it might be worth it to split them into multiple sub-files the model only reads when it needs that specific workflow.)

This is the first time I've heard the term 'apecode', and I will make sure to use it at every opportunity.

This is only done at the DNS level, so using a different DNS (such as Quad9) solves that issue. For background info, I can recommend [1, 2].

[1] https://www.youtube.com/watch?v=Uxmu25mUZgg [2]: https://cuiiliste.de/

That's the 'built by the lowest bidder' feature. Probably pretty realistic in a lot of places.

Note that this is the Flash variant, which is only 31B parameters in total.

And yet, in terms of coding performance (at least as measured by SWE-Bench Verified), it seems to be roughly on par with o3/GPT-5 mini, which would be pretty impressive if it translated to real-world usage, for something you can realistically run at home.

For me, these books are in the rare category of 'wait I didn't know it was allowed to come up with a story _this good_'. I envy all those that have yet to read it for the first time.

I'm not sure whether that was intended, but 'operating at scale' actually made me laugh out loud :D

"Do you or a loved one suffer from an abundance of brain cells? Speak to your doctor today about whether The Jersey Shore might be right for you!"

"A cable!"

"How do you know?"

"I'm holding it!"

Unfortunately proving anything about a concrete imperative implementation is orders of magnitude more complex than working with an abstraction, because you have to deal with pesky 'reality' and truly take care of every possible edge-case, so it only makes sense for the most critical applications. And sometimes there just isn't a framework to do even that, depending on your use case, and you'd have to sit down a PhD student for a while to build it. And even then you're still working with an abstraction of some kind, since you have to assume some kind of CPU architecture etc.

It really is more difficult to work with 'concrete implementations' to a degree that's fairly unintuitive if you haven't seen it first-hand.

While I fully agree with your sentiment, I'd like to take the opportunity to share a favorite fun-fact of mine: the frogs in the not-jumping-out experiment had their brains removed beforehand. Which might make the analogy more apt, actually, considering how much under siege our attention is these days.

I generally do this via a `throw UnsupportedValueError(value)`, where the exception constructor only accepts a `never`. That way I have both a compile time check as well as an error at runtime, if anything weird happens and there's an unexpected value.

This reads cool and all, but I also can't help help but feel like it might not have been as much of a 'gotcha' as the text makes it out to be. Who knows what kind of information the Russians got from this episode. The closer the NATO response is to what would actually happen in a combat scenario, the more valuable such a provocation is to them, I suspect.

You either give them the option to search the web for facts or you ask them things where the utility/validity of the answer is defined by you (e.g. 'summarize the following text...') instead of the external world.

My favorite website to see all the relevant climate trends:

https://climatereanalyzer.org/clim/seaice_daily/?nhsh=nh

According to that graph we're not currently at the absolute record low (2020 and 2016 were lower apparently), but only because so many of the recent years were record-low years.

What would be your intuition as to which 'quality' of the LLMs this tournament then actually measures? Could we still use it as a proxy for a kind of intelligence, since they need to compensate for the fact that they are not really built to do well in a game like poker?

Sorry to be completely off-topic, but: I'm really reluctant to click on anything with these 'share IDs' and usually remove them from any link I share with anyone. I don't want to make it even easier for the platforms to build networks of associated accounts.

The ancient tongue of the IO Nomads...