This project creates a "compact, machine-optimized format designed for efficient AI parsing rather than human readability" called "Structured Knowledge Format (SKF)".
It's not obvious to me that this is a good idea. LLMs are trained on human-readable text.
The author notes that non-reasoning LLMs struggle with these SKFs. Maybe that's a hint that human readable summaries would perform better? Just a guess.
I think it's really a thing about reasoning model. Non-reasoning model struggles at math too. It's more like a protocol between two math genius, they could communicate with really abstract stuff
What you describe is more accurately called the "prosperity Gospel", not evangelical Christianity. Mainstream evangelical Christianity doesn't believe anything like what you describe.
What I describe is what I've seen in many evangelical churches over decades and in three different countries, first hand. Evangelicals like to think their flavor is immune from all that ailes other branches of Christianity. Yet they too look down on the sick and the poor, sometimes more than older and more traditional strains of the religion.
Non-prosperity gospel churches don’t say it out loud, but the implications are easy to draw. Massive ideological and cultural structures aren’t logical proofs, there are many contradictions.
What a horrible thing to say. I can't speak for "goons" other than myself, but I have no hidden agenda when I flag the multitude of one-sided propaganda stories flooding HN about how horrible President Trump and DOGE are.
I find the resulting discussions to be hyperbolic, FUD-invoking, divisive and one-sided - as evidenced by your insults to half of U.S. voters - offering little to no discourse of value.
I recently watched a 2 hour congressional committee session, with 5 minute talking points per member. BOTH sides of the aisle used their entire 5 minutes to spout one-sided rhetoric and talking points obviously designed for re-election rather than anything resembling debate or conversation.
I have no idea which side "started it", but where we've landed isn't useful.
Why would you even suspect this is a troll account? These are clearly genuinely held opinions, stated plainly and without the normal wild rhetoric I typically hear in comments in such threads, yet you read it as propaganda.
This is why I flag all articles on DOGE/etc, because genuine conversation is assumed to be in bad faith.
Expecting someone to read an article having an obvious propaganda hit-piece title like "DOGE as a National Cyberattack" is silly.
Would you read an article titled "technology is the mark of the beast" and take your time to debate its merits?
I personally hold the belief that DOGE and president Trump are acting in good-faith to keep his campaign promises as best as they're able, in a messy and tumultuous environment.
At the same time, I have a lot of empathy for the great number of people that are afraid and hurting right now for a multitude of reasons. People are facing food/job/business insecurity, genuine threats to various core ideological beliefs, an environment of fear and uncertainty for many affected people, threats to the desired direction of our laws and societal moral compass, etc. I hurt for those affected, and I do what I can within my spheres of influence to help.
I don't see why we can't have an honest conversation with each other without assuming that the other is operating in bad-faith. I think BOTH sides should stop using propaganda, and start LISTENING to each other, that eventually we might determine paths forward together without cancelling each other.
Why is it silly? Is it reasonable to hold the opinion that DOGE should not have been given access to these systems (note: this doesn't mean that the opposite view isn't also reasonable)? If it's a reasonable position to hold, then getting access to these systems can be reasonably construed as an attack, can it not?
I don't really think this argument merits a comparison to "technology is the mark of the beast" or that the only people that can be opposed to DOGE suffers from "personality derangement" or "glorifies bureaucratic power"
> Is it reasonable to hold the opinion that DOGE should not have been given access to these systems
"We audited ourselves" typically doesn't fly, so no, I'd say not a reasonable position. Someone external has to do it, and DOGE is the one tasked by the president to do so.
Audit are already conducted by outsiders, but the objection to DOGE is less the concept of auditing but how they’re doing it by bypassing all kinds of policies. Normally auditors would be qualified, have passed background checks, and agree to follow the same security and privacy policies.
The outrage is because they’re taking a lot of risk and clearly treating it as a political exercise when it shouldn’t be.
>I don't see why we can't have an honest conversation with each other without assuming that the other is operating in bad-faith.
>I think BOTH sides should stop using propaganda
Well you proved it right here. You're "both sides"-ing this when the responsibiliry and power at the moment is horribly disproprtionate. It isn't at all. We can throw all the links we want, but I've yet to see any "liberal propaganda" posted in response to suggest that Democrats are "playing dirty".
If we can't even talk about objective facts like "Musk retaliated on Judges who gave him court order", then we can't talk much. We're not in the same reality and facts like that aren't even denied by Musk. You're defending someone who is outright saying "I want to take down the courts". He isn't even defending himself.
Same with ICE raids. People are upset because they built their house on sand and have to start again. Businesses are upset because they can't get around labour laws
I find it funny that you're getting downvoted though. Maybe in a few years it'll all blow over
Wow. You don't need to be very right leaning to feel the complete opposite. I'm simply amazed someone could feel that way, as nearly all media is very left-leaning (to my perspective).
And there's the core of issue. If you use vague terms like "left" and "right", then different people in the discussion will be using different definitions. You're using them to mean socialism vs capitalism, whereas others mean Democrats vs Republicans. Some are even using liberal vs conservative. Occasionally, I've seen it as authoritarian vs libertarian, even though that should be an orthogonal axis. If you're going to commit to the logical sin of the false dichotomy, at least say what you mean.
It strikes me as a strange that not one comment in this thread supports RTO, so I will weigh in with my unpopular opinion - I really wish all our employees would work from the office 3+ days per week.
I like the energy we get when we work in the same space. I like being able to look people in the eye when discussing challenging or emotional topics. I like being able to brainstorm together at will, and use the whiteboards. I like seeing our office space we pay for being used by more than just 2 people. I enjoy our staff lunches and getting to know each other socially. Most people have a <10m commute in our small town, so travel time isn't a big deal.
Half our company is remote, and the other half work from home most days. But I'd prefer we all be local and in the office ideally. There, I said it.
Why do you postulate that "most people don't have" this need? I also use AI non-stop throughout my day for similar uses.
This feels identical to when I was an early "smart phone" user w/my palm pilot. People would condescend saying they didn't understand why I was "on it all the time". A decade or two later, I'm the one trying to get others to put down their phones during meetings.
My take? Those who aren't using AI continually currently are simply later adopters of AI. Give it a few years - or at most a decade - and the idea of NOT asking 100+ AI queries per day (or per hour) will seem positively quaint.
>Those who aren't using AI continually currently are simply later adopters of AI. Give it a few years - or at most a decade - and the idea of NOT asking 100+ AI queries per day (or per hour) will seem positively quaint.
I don't think you're wrong, I just think a future in which it's all but physically and socially impossible to have a single thought or communication not mediated by software is fucking terrifying.
It's not obvious to me that this is a good idea. LLMs are trained on human-readable text.
The author notes that non-reasoning LLMs struggle with these SKFs. Maybe that's a hint that human readable summaries would perform better? Just a guess.
Or perhaps a vector store?