An excuse to say "apple detectives"? Choice of words drew me in, and I'm happy it did. This is quirky news; it's making a bit of geekery interesting to distracted geeks, like me.
The subject is interesting and I am not doubting that. The story is interesting as well.
But the headline is just weird, especially for an outlet like that. Why do we need to resort to goofy theatrics to attract people to science (interesting in itself) is the problem I have. Same reason why I detest people who genuinely think Kip Thorne's most famous work is Interstellar.
There's definitely something to be said about not trying to spin stories into something more. And, I'm usually on the other side of the barricade in these discussions. But, when I'm reading about apples, it's me being goofy, so it's nice when the author is tailoring for that. I would absolutely hate it if the same was done when writing about something I care about in a "real" way, for the lack of a better term.
Until LLM context sizes explode by two orders of magnitude, I cannot envision significant agent programming without leaning heavily on spec-driven workflows.
It's also worth noting that SDD is such a wide variety of approaches that the term on its own says very little. For example, SpecKit and SpecDD are both very capable SDD frameworks, yet they have only minimal overlap: SpecDD describes system components (with emphasis on boundaries), while SpecKit is a fairly advanced process for changing specs.
SpecKit and Superpowers do have significant overlap, in that they can orchestrate work, diverge into parallel streams and reconverge, etc. But, SpecKit is about making spec changes as safe and explicit as possible.
OpenSpec is a very lightweight framework by comparison. SpecDD is lightweight too, imo.
I have such fatigue from listening to the rhetoric and whining from US farmers when enough of their goods are dangerous for consumers and illegal in Canada and the EU.
It's all bad faith from the US trying to run over any market they don't control so they can weaponize control over food supply of another nation later.
I don't mind countries setting their own rules for the food they want to consume, and for sure the EU can be overly bureaucratic.
On the other hand, the US is the only country I've been to where I have purchased milk in a completely sealed plastic container, and it was rancid when I opened it. Upstate New York is proud of their local and organic produce, but they are selling rancid milk in stores like that's a normal thing. That was a shock as a visiting Australian.
I remember a delightful trip to Canada, where I ordered a hamburger, and they'd only let me have it well-done. I asked why, and the waitress says "The beef comes from the US", with a grimace...
Keep in mind, social media and western online dialogue is extremely US centric. If every country was a house, the US is where everyone meets to party. So every spec of dust spawns endless content for everyone to dig into. Nevermind that people who have the most time to spend on social media, dictate the narratives that are popular.
The reality is that the US better if you have money (like white collar salary man level) and (much) worse if you are an odds-and-ends gig economy type worker (like an influencer).
From the vantage point of a ~75% income bracket home, moving to Europe is almost purely downsides (conventionally, some people give up everything for their dream to live in a cold dank cave), whereas being in a <50% income bracket home, Europe seems like a utopia.
You can't make that generalization. What you describe will be different city to city, not to mention country to country. Further, privacy and safety regulations (which are EU-wide) will not be available in US, independent of income. Though that's city or state dependent too, I guess. It's just too hard to make these offhand comparisons, unless we make them more concrete.
I agree about social media distorting things. When I visited US, I was surprised that it's not GTA-like violence everywhere, haha. I feel silly sharing that. But, the biggest surprise was how friendly and warm strangers were. Memes didn't hint at that at all.
Yeah, I'm curious about which ones are a problem. I could see there being some incompatibility, and the details are more interesting than sweeping statements.
Some regulations would have to be normalized and agreed upon between the countries for trade open up. Can't have different quality standards and ways of evaluating and declaring them.
Programmers keep thinking law is if/then, it's not, it's a set of instructions to judges, which may contain obvious errors or conflict with other instructions, which is why we allow humans to interpret them instead of computers.
Are you defending PPWR? Not in spirit but actual implementation?
It will never get so-far as the judge because the EU has already admitted the law cant be followed and arent going to be taking people to court over it.
One I have actually dealt with was VATMOSS. Especially when first introduced it had very low ceilings for registration and actually deterred small businesses from trading across borders.
I also think GDPR is too strict for small businesses and non-profits and not strict enough to deal with big businesses that trade data.
Having health with VATMOSS too my experience is that it was trivial to implement. Maybe your country fucked up the rollout? Here in Sweden I had zero issues.
Its not the country, its the implementation cost for small businesses. In particular the ceiling for registration was so low that even micro-businesses with minimal cross border sales had to comply.
Its would have been trivial for a big business, but it was not for small businesses.
Maybe just calibrated poorly. Small enough and IMO the only important rule is no sharing with others. That should always be strictly enforced. But why worry about how some small timer handles my personal data or if I can make various requests of him? The stakes are too small to matter.
You're on a tech-focused Silicon Valley based news forum. Most people here think if you're not carte blanche allowing your Ai companies unfettered hyperscale economy-threatening death spiral infrastructure investments for a nebulous end goal that benefits a small minority with undertones of civilizational collapse and mass unemployment then you're a over-regulatory nanny-state that is crushing innovation.
Welcome to Canada where the regulations are in fact provincial.
Canadian provinces have a harder time trading with each other than countries in the EU, although thanks to the sales tax and package transit changes the EU is becoming competitive in this area.
...Those cookie banner things for a start!! heh. ;)
Mostly just wouldn't really work because Ottawa would have to somehow represent the provinces to the EU and the provinces and Ottawa don't work together in a way that would be compatible, I don't think anyone in Canada would want to change how Ottawa works with them. We may also end up in the same position again as we have with the Americans, nobody but us likes our supply management system[1]. GDPR is also something I think Canadians would struggle to get behind, our PIPEDA framework is quite good and I think most folks approve of it (except Quebec, who have their own framework). Taking the Euro would be a problem, etc etc, I think I could probably build quite a big list. btw, I respect the EU regulation, and that Europeans quite like it, I was just saying I don't think it would be practical for us to re-work the whole country to accommodate them, that's all.
LLMs are trained to obey instructions, and they try their best to game the reinforcement learning by including reports of how they're obeying your instructions. Therefore, not talking about followed instructions is a sort of conflict for an LLM.
I have found that asking the agent why it did X or Y is an essential part of iterating on its harness. It was non-obvious to me, probably because I'm used to having to reverse-engineer why a system does something, but that's not usually necessary with LLMs, unless the harness is complicated and you have to hunt for the instruction it tells you about.
It would make sense to have this integrate with a self-learning routine for an agent: e.g. at night it looks through what it did and writes NPC-Forge recipes. Tomorrow it can answer queries (which he turned added to NPC-Forge) without an LLM. Of course this implies a branching where a query is either processed by NPC-Forge or an LLM, depending on some measure of confidence that NPC-Forge can answer it well.
reply