Computing is a very broad topic. Even Linus has no skills or knowledge about countless topics that would be mundane to you.
It doesn't matter really, what matters is our ability to stare into the void of what we don't know and having learned how to approach the topics we know nothing about.
Sadly we, the "good guys", created a dangerous precedent in the balkans when Kosovo unilaterally split from Serbia, under foreign (NATO) occupation moreover.
International law does not promote nor support unilateral secessions. If a region or autonomous republic wants to secede it should only do so in accordance to the host country laws. E.g. the Quebec and Scotland referendums were made in accordance to the host countries of Canada and UK.
But then we created that dangerous case where now every region can secede from their host one unilaterally, even if it's occupied by foreign forces. And in practice, the "legality" of it, really depends on international recognition and the undergoing narratives.
International laws have always been pleasantries, as there's no real ways to enforce them, but there were powerful incentives for everybody to play by the rules.
It's hardly a precedent, probably half of the countries worldwide have been formed by seceding from some other country against its will. U.S. would be in this half.
It's the first country to do so under foreign military presence since UN inception.
The only precedents of unilateral secession were Slovenia and Croatia from Yugoslavia and Bangladesh from Pakistan but none did so under foreign military presence.
All of the Arab countries have basically seceded from Ottoman empire under an occupation of this or that European country.
"Unilaterally" is not easy to define. Sometimes there is a long and violent struggle for independence and the metropole eventually gives in and signs some paper, sometimes it is stubborn and doesn't sign anything - the difference is not that important in my opinion.
LLMs have been marketed for years, with great meadia fanfare, as being almost magical, something that can do the job of software engineers. Every week, the hype is driven further.
This matters. When people get told everyday that XYZ is magic, some will believe so, and use it as if it is magic.
I'm not sure I completely agree, I don't think it's that black and white, it's a similar analogy to Guns and gun violence.
Without the prevalence of guns there is simply less gun violence, but you could argue that it's also a human problem.
Giving people who have no business using an LLM to submit slop bug bounties is a problem of the tools accessibility. But also a human problem of course.
Edit: I should mention, I don't have a solution to the problem although I do like the other posters suggestion of a "deposit" scheme to submit a bug. I think that would incentives higher quality submissions.
This is not a technology, but ethics and respect problem.
From the same article:
> Not all AI-generated bug reports are nonsense. It’s not possible to determine the exact share, but Daniel Stenberg knows of more than a hundred good AI assisted reports that led to corrections.
Meaning: developers and researchers who use the tool as it's meant to work, as a tool, are leveraging it to improve curl. But they are not skipping the part of understanding the content of their reports, testing it, and only then submitting it.
E.g. We don't blame cars, the tool, for driving into a gathering of people that can kill a dozen of them, we blame the driver. The purpose is transport, the same way LLMs for coding are a tool for assisting coding tasks.
We do actually keep cars out of areas with lots of people here. And the media headlines always refer to a "car" driving into people without mentioning the person behind the steering wheel. Whether that's the better than addressing the root issue is another question though.
We also don't allow car use without a license.
In the end what matters if allowing something is a net positive or not. Of course you can have more precise rules than just a blanket ban but when deciding and enforcing those rules is not free that also needs to be considered in the cost benefit analysis. Unless you can propose how projects can allow "good" contributions without spending more time on weeding out bad ones, a blanket ban makes sense.
> I suspect these frameworks/patterns just fill up the context with unecessary junk.
That's exactly the point. Agents have their own context.
Thus, you try to leverage them by combining ad-hoc instructions for repetitive tasks (such as reviewing code or running a test checklist) and not polluting your conversation/context.
Ah do you mean sub-agents? I do understand that if I summon a sub-agent and give it e.g. code reviewing instructions, it will not fill up the context of the main conversation. But my point is that giving the sub-agent the instruction "review this code as if you were a staff engineer" (literally those words) should cover most use cases (but I can't prove this, unfortunately).
I do think you're right that you should be cautious about writing too convoluted sub-agents.
I'd rather use more of them that are brief and specialized, than try to over-correct on having a single agent try to "remember" too many rules. Not really because the description itself will eat too much context, but because having the sub-agent work for too long will accumulate too much context and dilute your initial instructions anyway.
The number of people defending prediction markets here is mind boggling.
Any moderately intelligent people should realize why insider trading, banning athletes from betting, etc measures have been put in place. One should understand why without those (and even with) those there's perverse incentives to act in destructive ways.
Yet people here would be trying to discuss philosophy, semantics and tell you this is good because an insider betting on an attack on Venezuela 4 hours before it happened increases the accuracy of the prediction and the information being public, ignoring the elephant in the room of having the perverse incentives to influence destructive events. Just think about it: there might be people with incentives of attacking Greenland because they bet on it. This is madness.
This is the worst degeneracy of gambling and dangerous incentives combined, and it's all for nothing else but money. Just look at whose behind these projects: bs crypto adjacent fintechs and gambling companies.
I know we live in numb times where people have thrown in the towel of any hope for a better world, but ffs.
It doesn't matter really, what matters is our ability to stare into the void of what we don't know and having learned how to approach the topics we know nothing about.
I'm sure you've done that countless times.
reply