Tldr: Poland shot down Russian drones that entered polish airspace. Not the first time they've entered, but first time they've been shot down by Poland.
I wouldn't be surprised if it is deliberate by Russia.
Gray zone warfare in part does small little practically deniable actions, to create a new normal and establish small precedents that can be escalated into larger precedents. Slowly boil the lobster alive - create messaging that conflict in Poland is usual and nothing to wake up about.
The Netherlands also helped to shoot down some drones. A first it seems. Not only F35 fighters were launched, also at least two tanker airplanes were deployed to resupply the F35’s. Source: https://nos.nl/l/2581928
> When researchers attempt(opens a new tab) to recover [something like] a coherent computational representation of an Othello game board they instead find [bags of heuristics]
Humans don't exactly have a full representation of board space in their head either. Notably, chess masters and amateurs can memorize completely random board positions as well as the other. I'd think neither could memorize 64 chess pieces in random positions on a board.
That's not what "coherent computational representation" means in this context. It means being able to reliably apply the rules of Othello / chess / etc to the current state of the board. Any competent amateur can do this without studying thousands of board positions - in fact you can do it just from the written rules, without ever having seen a game - they have a causal, non-heuristic understanding of the rules. LLMs have much more trouble: they don't learn how knights move, they learn how white knights move when they're in position d5, then in position g4, etc etc, a "bag of heuristics."
Notably this is also true for MuZero, though at that scale the heuristics become "dense" enough that an apparent causal understanding seems to emerge. But it is quite brittle: my favorite example involves the arcade game Breakout, where MuZero can attain superhuman performance on Level 1 and still be unable to do Level 2. Healthy human children are not like this - they figure out "the trick" in Level 1 and quickly generalize.
For whatever its worth, I bet the chess master would be able to instantly identify that it is a random/invalid board position, aka an invalid world state. I think the experiment you are alluding to gave both groups a very limited amount of time to look at the board. Given enough time, both groups would definitely be able to memorize 64 pieces on a board.
Sorry, I meant that masters could identify smaller sets of pieces as invalid instantly, but that both masters and amateurs would be able to memorize 64 piece board with enough time.
I really like the phone/desktop convergence concept. Mostly I think because I want the freedom / open experience of my desktop on my phone though, I think.
But I think most folks interested enough in the concept are also rich enough to afford a phone and a laptop, and if you want a keyboard for your phone you might as well just use a laptop.
I still think conceptually it's the right direction for tech that our devices should be so flexible, but it's hard enough in practice that it's not generally done.
I feel the same way, but while there are definitely actual hardware limitations preventing phones from being identical to computers, the problem is mostly a choice. Why aren’t ipads with keyboard cases able to be used exactly like laptops, for example? I think companies seized on the combined accessibility and restrictiveness of smartphones to justify design choices which are more about profit. Restricting the app library makes apple a great amount of money. Ads are hard to block across a mobile device, why else if not for more money? I think the circumstances of smartphone development gave them the opportunity to make these choices and we’ve gotten locked in since.
> Why aren’t ipads with keyboard cases able to be used exactly like laptops
Small screen - cannot fit many controls or code. Small keys - cannot type fast. No touchpad - cannot do precise clicks, therefore cannot have many controls on the screen. Try imagining something like editing lots of small notes in a music editor with your fingers...
I can hit 40-60 WPM on a BlackBerry keyboard, but a chicklet keyboard is too much for honest-to-god software developers?
The small screen is equally ludicrous. The desktops of a few decades ago had lower resolution on physically smaller displays, and I consider a large, crisp display a must-have for longer sessions - not a hard requirement for smaller, quicker tasks
Not having a trackpad is one reason the iPad supports USB mice too, and giving some users a trackpad would result in the same complaint: "This is terrible, can I use a real mouse please?". More to the point, parent is complaining about keyboard cases with trackpads, which are mediocre in part precisely because Apple has constructed a software ecosystem that is hostile to powerful, desktop-style programs
I think the convergence concept still makes sense in big corporations where most of your work happens on a VM in the cloud, while you just use your device as a thin client. Especially in places they don't even let you use a thirdparty browser >.>.
Earlier this year, I was actually tried to replace my bulky 16" MBP with a Pixel 9 for work. Android's desktop mode just wasn't there.. Maybe I will try it again next year...
All I really need was a browser and a drop down terminal anyway.
There are at least dozens of us doing this. My $5k bloated corporate laptop sits in my office 24/7. The 25% of time I’m traveling is with a $300 Chromebook with Linux Mini, a Bluetooth mouse, and logged into to a Windows VM.
Now that everything corporate is forced into the cloud, using a VM doesn’t carry all the extra downsides it used to.
and the bonus is that, when the workday is done, I have a machine I actually own and can use without breaking policy.
Huawei as well. Used to have a P30 Pro. It felt like a true downgrade when I bought a Pixel 8 Pro two years ago and it had no desktop mode and a worse camera to boot.
the problem with keyboards like this and the ones on the surface is that they have no connective hinge and rigidity. with my UMPC at least, I like to hold it by the base while looking at the screen. I really wish there would be a clampable keyboard that used nice membranes like the GPD but had a phone clamp on top like a selfie stick and a single swivel-hinge like those fujitsu convertibles
> But I think most folks interested enough in the concept are also rich enough to afford a phone and a laptop, and if you want a keyboard for your phone you might as well just use a laptop.
Laptops are bulky; phone and keyboard can fit in one's pocket. I also dislike the idea of carrying around a device that's not under my control. It's not about wanting my phone to behave like a laptop because I can't afford a laptop. It's about getting to have control over my phone the same way I have control over the laptop.
For example, when I try to screenshot and the OS says I'm not allowed to by the app, on my own device, I die a little inside. The very idea that an OS would obey an app over the user is really messed up. It's really wrong. It's like a guest saying their guest sets the rules in your own house.
Also the weird, arbitrary limitations. On Android you can split screen and show 2 apps vertically at limited, specific heights. On the Pinephone with i3/sway, you can divide the screen with as many windows as you want, in whatever orientations you want, with as many workspaces as you want. You can set the scaling to whatever you want, have interfaces be as big or small as you want. Limits aren't arbitrary.
> I still think conceptually it's the right direction for tech that our devices should be so flexible, but it's hard enough in practice that it's not generally done.
The difficulty isn't in getting desktop stuff to work on the phone. The difficulty is getting phone stuff to work on the phone.
Lack of types is one thing that turned me away from Elixir when I was trying to learn it.
I didn't know how to think about the types so I wanted some way to annotate them to help think through it, but went through it. And then the compiler complained at me I was passing in the wrong type to a function. I mean yes thanks? But also give me a way to figure that out BEFORE I try running the code.
True that's a good point - if publishers were OK with micro purchases for their articles, we'd see some publishers try that out. Nothing's stopping the NYT and similar from trying a "pay as you go model".
The fact that publishers haven't experimented with that implies they're not interested, which dooms any project like this from the start.
They're not interested and it's not for technical reasons. It's for business reasons:
• Advertisers want subscribers because that's a proxy for wealth and often, locality.
• Only quite rich people are willing to pay for an ad-free newspaper. The Spectator is one example of such a thing in the UK (subscription only, no ads).
• A lot of subscriptions are driven by a desire for opinion and opinionated takes, often by a single star writer, not news and certainly not neutrally written news.
Extremely slanted opinion sells like hotcakes and subsidizes all the rest, but the market for drive-by micropayments for opinion is very small. This opinion-subscription-bias amongst readers is why Substack works and also the Guardian (the Guardian is 90% just opinion pretending to be unbiased news).
I do not think I have owned a single device where the headphone jack was the first item to have issues or fail. Even unused debris would trigger switches changing sound sources. I am happy to be done with wired headphones being yanked off my head.
Good point in the post about confidence - most people equate confidence with accuracy - and since AIs always sound confident, they always sound correct
Except that's not what "confidence man" means. It means that you gain their confidence/trust, then betray it.
A con man often uses the illusion of confidence to gain trust, though that's not the only way. The reverse also works: gain their trust by seeming unconfident and incapable, and thus easily taken advantage of.
The number of times I've caught chatgpt passing off something borked with perfect confidence is growing but what's truly annoying is when you point it out and you get that ever so cheerful "oh I'm so sorry teehee" response from it. It's dumb stuff too like a formula it's simplified based on a assumption that was never prompted.
Yep. Last night I was asking ChatGPT (4o) to help me generate a simple HTML canvas that users could draw on. Multiple times, it spoke confidently of its not even kind of working solution (copying the text from the chat below):
- "Final FIXED & WORKING drawing.html" (it wasn't working at all)
- "Full, Clean, Working Version (save as drawing.html)" (not working at all)
- "Tested and works perfectly with: Chrome / Safari / Firefox" (not working at all)
- "Working Drawing Canvas (Vanilla HTML/JS — Save this as index.html)" (not working at all)
- "It Just Works™" (not working at all)
The last one was so obnoxious I moved over to Claude (3.5 Sonnet) and it knocked it out in 3-5 prompts.
IME, it's better to just delete erroneous responses and fix prompts until it works.
They are much better at fractally subdividing and interpreting inputs like a believer of a religion, than at deconstructing and iteratively improving things like an engineert. It's waste of token count trying to have such discussions with an LLM.
Those are not my prompts. Those were the headings it put above the code it generated in its responses.
Even if my prompt was low-quality, it doesn't matter. It's confidently stating that what it produced was both tested and working. I personally understand that's not true, but of all the safety guards they should be putting in place, not lying should be near the top of the list.
Agree with sibling, security theater largely. I suspect the logic of banning is to stop recordings of conversations, whereas Bluetooth is just a protocol for sending data. Eliminate collection sensors and mediums for transmit are fine.
I did decide to purchase a Pebble Time Steel and a new battery alongside the Core 2 Duo. I hope that with Eric back in charge, the old Pebbles will be allowed to use the new app and hopefully get modern apps.
By that logic a one party system is the most superior system, since by definition everyone is on the same page.
We got Trump in part because people felt unable to fully express their opinion - they felt it was either the status quo person or the anti status quo person, with no nuance in between.
And there are still divisions - the freedom caucus, the progressive "squad", the swing politicians. Those politicians should be in parties that reflect them rather than Frankenstein's monsters of parties.
Coalitions are made to enable things like voting on government budgets before funding runs out .... But that problem does not seem solved in the US
Free mobile games paid by ads?
reply