yesco

It's funny you mention this, because I've been thinking lately that all the focus on code quality benchmarks for LLMs seems to miss something. In my experience, LLMs aren't actually all that good at prompting other LLMs, and that's exactly the skill that matters for proper subagent usage.

The corpus of code available to train LLMs on is rich in both volume and quality. The same can't be said for LLM prompts. Prompts only came into existence alongside LLMs themselves, so most of the prompts out there are actually LLM generated, and training on them causes every model to overfit to the same patterns.

LLMs can give clear and concise directives to other LLMs, but only for basic tasks. Beyond that, they frequently overstuff their prompts with too much prose and too much direction, and worse, they often fill them with subtle contradictions.

Of course, there's a spectrum here. Some models turn out to be better at this than others, and I suspect this is what differentiates Fable-type models from the rest, and why vendors have started keeping their models' reasoning confidential.

I think this is one of those areas where the translation from research to the public ends up too precise on the details, beyond the cognitive load most people are willing to commit to it day to day.

In the same spirit of upāya from Buddhism, I like to compress this type of topic into a simpler model, even if imperfect.

Here's how I model cancer, and how I judge whether something is likely to give me cancer, without trying (and failing) to memorize a million risk factors individually:

You are a collective of cooperating cells. When cells rebel, the order that holds your body together collapses, and you get cancer. Cells generally don't want to rebel. They're content as long as they get their energy, their paycheck.

But what about activities that cause frequent cell death? A sunburn, smoke in your lungs, alcohol in your bloodstream, radiation (essentially atomic shrapnel flying through your tissue). Anything that causes inflammation, especially chronically. When cells die before their expiration date, the survivors have to keep dividing to replace them, and they start to get pretty mad about it. Maybe even rebellious.

With every round of division, they are in essence "evolving" away from their cooperative nature to cope with a hostile environment. A cell doesn't care whether the collective lives or dies, and it doesn't have the capacity to reason about that in the first place.

So the question becomes: are you keeping your cells safe? Are your activities hurting them? If they're not happy, they'll rebel, and you'll die.

This is where the model earns its keep. Take obesity. It's on every risk list, but excess fat isn't what makes cells rebel. The real culprits are the conditions obesity creates: chronic inflammation, more cells that need to be maintained and replaced, a body that is generally harder to live in.

Weight loss is on the list because it's the easiest way to fix those conditions, not because thinness is protective in itself. Once you see that, you don't need the list. Anything that makes your cells' lives harder, day after day, is raising your odds, whether or not anyone has published a paper on it yet.

The math is real, but a model like this tells you which variables you actually control.

Tech leaders demand nations of the world give them a moat or else

Because they aren't and never have been! This has been scientifically proven from the astrological data according to my sources.

Somewhat tangential, but this reminds me of when I took a certain Microbiology midterm in college. I hadn't put much effort into that class leading up to it, as I had some tough CS classes that consumed my focus that semester (also was admittedly not a great student in general). So when I finally went to take the midterm, after cramming like mad before the exam, I quickly realized I basically didn't know the answer to most of the questions, even what I crammed was only a small portion of the material.

The exam was huge, at least over 10 pages, and even when we technically ran out of time, the professor was kind enough to move the remaining exam takers to the neighboring lecture hall to continue taking it. I recall I spent a total of 2 hours on that exam.

Now mind you it was mostly short answer or multiple choice questions. The multiple choice questions were pretty sharp too, lots of traps and false but sounds right answers mixed in. But if it had been purely essay questions, I would have been screwed.

However with such a huge corpus of information in front of me, I ended up basically learning all the material on the spot. I just kept doing multiple passes through it, each time I noticed one of my answers contradicted one of the others, I would make adjustments to harmonize, which indirectly refined my understanding.

In the end I got B+ in the exam (which was curved to an A), and walked out understanding the material better than I did walking in.

Reflecting in the experience years later, I've wondered if a hypothetical LLM which was ignorant of microbiology could do the same thing if fed that exam. In some respects the traps they placed in the multiple choice questions actually were what helped me refine my understanding the most. Made me appreciate information theory more.

Yeah I walked into this with my pitchfork ready but isn't this stuff pretty... reasonable?

McDonalds is just a restaurant, they predict what menu items you like and how likely you will come back, is that really a problem? What is the concern here? I don't use their app but presumably for those that do, isn't this exactly the type of data that would simply influence whether the app offers a coupon or something? Or how well a franchise is doing? Maybe also what to keep on the menu or how much to stock?

What exactly is the bar here I wonder? McDonalds has security cameras, it also has menu kiosks with cameras (I think?). The alternate reality evil tech-like McDonalds could have theoretically used facial recognition to categorize all footage of any given customer, then used this footage to estimate their friends, spouse, BMI, age, gender, ethnic group, attractivness, disability, etc. They could then sell it to third party data brokers for extra cash.

That would certainly be the kind of dystopian surveillance to get me swinging my pitchfork around, but this? Having assumed the worst I'm now walking away realizing McDonalds might not be so bad after all.

I reject your characterization of my comment. I explicitly called myself an outlier and said I didn't want to get too specific, so I'm not sure where you're getting "clever" from. I wasn't claiming credit for my circumstances. I was identifying the actual variable that separated my outcome from peers in similar circumstances, because that's useful information for anyone who does have that option available.

And plenty of people do. I know people who could live at home rent-free and chose apartments anyway because they wanted independence sooner. That's a legitimate preference, but it's still a tradeoff, and pretending the tradeoff doesn't exist because some people don't get the choice at all helps nobody. "Not everyone can do X" is true of literally every piece of financial advice ever given. It doesn't make X bad advice for the people who can.

I purchased a house within commuting distance of Boston in my mid 20s, back in 2022. Didn't need PMI, the mortgage terms weren't unreasonable to me (fixed 5% interest), and the monthly payments for utilities plus the loan are still well within my means. It's even got an attached garage.

I don't want to get too specific here for privacy reasons, but I believe the main difference between myself and my peers is that I chose to live with my parents and save for a house instead of moving out and getting an apartment right away during/after college. With almost zero real expenses outside my student loans, and the median software engineer salary for the region, I was able to save enough for a down payment after just a couple years. I did this because I disliked the idea of having no equity and paying rent to offset someone else's mortgage instead of saving for my own. My parents really liked that reasoning.

In many respects I'm fundamentally an outlier, yet once I bought mine, my peers with much lower incomes started doing the same after I explained the financials. When they actually sat down and calculated the mortgage payments, they realized it wasn't that bad, as long as they got something on the smaller side, which is still bigger than an apartment anyway.

To be clear, housing costs were crazy and still are. But I sense "crazy" is pretty relative when talking to people online from other countries. Housing in the US is expensive, especially compared to various convenient periods within the last 100 years. But even now, it's not the unrealistic back-breaking dream it seems to be when I talk to Europeans about it, and I suspect that's why so many Americans on social media overestimate the costs.

My perspective until now was that the Wikimedia foundation was already supposed to be a union-like organization. Would it make sense for Linux maintainers to form a union within the Linux foundation? The vibes feel similar to me.

Yeah I was expecting some giant text dump based on the complaints in the comments here, yet all I see is a pretty normal README? It's not even that large.

If we are splitting hairs some sections could have been left out or broken up into a dedicated doc, but this is still vastly better than a README that explains too little. At minimum I expect a README to give me guidance on what this is and how to get started with it and having stuff like a file layout helps with exactly that.

Yes it's truly a shame when the people responsible for critical infrastructure only hire the cheap inexperienced software engineers to build it.

Much like how relying on a resident nurse instead of a cardiologist when you are experiencing a heart attack can end your life pretty badly as well.

I see no reason not to be empathetic. The frustration is fair, but it's aimed at the wrong layer. These people were guided into this spot by bootcamps and curricula that start at React and never go down the stack.

My experience was the reverse. I learned HTML and CSS first, then Rails in college to serve templated pages. I understood the client/server boundary fine as a concept, what I couldn't see was where it actually sat in a web context. I sort of knew JavaScript ran in the browser, but then I'd see ERB templates stamping values directly into script tags, so the server was writing the JavaScript that ran on the client, and my mental model fell apart. Where does my code actually execute? Why does this variable exist here but not there? Why does the page have data the network tab never fetched? Nobody ever sat me down and explained the request/response lifecycle as its own thing. I had to assemble it from fragments over years. This was around 2017 for context.

How you learn something shapes how you keep learning. If your mental model is misaligned, everything downstream is friction. The thing that finally made it click for me was reading the actual HTTP RFCs, which is apparently a weird thing to do, because HTTP itself is absent from nearly every guide and curriculum. Tutorials teach you the framework, maybe the language, and just assume the protocol underneath. These days I make newbies read the MDN docs like a book and skim the HTTP wiki page, learn the history of the protocol. It's short! It's not even a book! That gives you a firm foundation. But if your foundation starts at React, drilling down is like digging past bedrock. People don't know where to start, and Googling only shows them wrong answers because they don't yet know how to ask the question.

You can agree or disagree with the consequences, but the voting rights act never had any explicit provisions about districting, this was something conjured entirely by the courts. It was even framed as a temporary measure at the time of the original ruling.

So not exactly bewildering, I personally saw it as closer to inevitable. The Supreme Court never had the power to legislate, it can only interpret, and a shaky interpretation always has an expiration date no matter how popular it is.

Friends who give ultimatums like this are usually toxic and worth ditching. Your friend would be better off cutting you off now, regardless of what they decide about the job, than continuing to associate with someone who'd emotionally manipulate them over a career choice. Healthy relationships simply don't look like this, and dressing it up as principle doesn't change what it actually is.

The fact that this feels like a normal thing to say to a friend tells on you a bit. Get out more, spend time with people who don't already share your priors, and the certainty starts to sand down on its own. Threatening your friendships over someone else's career is not the moral high ground, it's just an ugly way to treat people. Humility is understanding you can be wrong about things even when you're certain you're correct.

I honestly agree with you in many respects, I'm simply spinning in some nuance to a topic I keep seeing.

The snake oil salesmen is productive precisely because the actual effects of the snake oil they are selling is unknown to the consumer they are introducing it to. There isn't easy answers to this, it's just a fact of life that we can try our best mitigate.

And apparently fish oil actually does help your brain. Weird world we live in.

So I think the focus on "experts" is actually a consequence of declining institutional credentialism. You didn't trust them for claiming to be experts, you trusted the institutions who called them experts and said you should trust them for that reason. But expertise implies competence not trust. Not everyone operates with good intentions even with the right credentials, including many institutions themselves.

This is why I believe we should only listen to amateur opinions on everything, experts simply lack historical credibility. For example I've recently purchased a healing crystal (half off) for only $5000 dollars! It cleared up the imbalanced energies my street guru told me about right away.

I would never have been made aware about the consequences of imbalanced energies in the first place if I had asked an expert instead. They probably wouldn't even suggest an immediate solution to the problem like my reliable street guru always does! Something to consider.

Spain had the largest empire in the Western Hemisphere. Extracted silver, enslaved entire populations, and lost it when we kicked their teeth in during 1898. That's imperialism. Paying someone hundreds of millions to let you park planes on their runway is not. And "which neighbor do they need defending from" is a question that tells on itself. If you still think wars are about neighboring countries you haven't been paying attention to anything happening in the world right now.

"Granted to them for free"? The US has been paying Spain for base access since 1953. Hundreds of millions per renewal cycle in military aid, economic assistance, and direct spending. It was never free and it was never a favor. Spain negotiated compensation every time.

"Who does Spain need defending from?" Nobody, because of the security architecture my tax dollars built. That's not evidence the bases are a favor to us. That's evidence they worked. You're welcome. And if they can't be used when it matters, I won't lose any sleep if they get closed.

Glad we are on the same page, because yes, as you pointed out, it literally says here in plaintext that it was NATO Allies that activated it, not the United States.

The United States has never activated article 5. Get your facts straight before attempting to use an LLM to reply to me.

The coalition for Afghanistan was voluntary. This isn't even that, it's just flying our planes over Spain's airspace.

Even as a joint contributor I see no reason for the US to pay for bases it's never going to be allowed to use.

I want to say upfront that I'm absolutely not trying to say Spain should or even needs to join this silly war.

But the US not being allowed to use the bases it pays and maintains for Spain makes it questionable why it does so in the first place. Iran is in fact a threat relevant to NATO considering most of it is/was within ballistic missile range. It's also a simple fact that Iran's manufacturing base has been supporting Russia's war machine, which has been a key contributing factor in the Ukrainian stalemate. There is some genuine strategic overlap.

Restricting air space on top of that, makes me, originally a more sympathetic American NATO supporter, question the dynamics here. Why should the US help Spain when it's in need in a future conflict?

I don't want Isreal dragging us into wars for it's personal benefit. But this whole conflict has really got me realizing I don't want Europe dragging us into any wars either. The only transactional benefit to those air bases is that they power American global logistics. If this becomes a pattern then I think NATO will likely become nothing more than a nuclear umbrella, even after Trump leaves office. And only as a hedge against nuclear proliferation.

People take for granted that Biden was technically the most Pro-NATO president we have ever had, and likely ever will.

This dynamic could also be argued as a cause of the War of 1812.

Ah, I finally understand NFTs now

Salespeople are the easiest to sell to. Con artists are the easiest to swindle. The people who believe they're immune to being tricked are always the ones who get tricked the most.

I get maintainers have their own issues to deal with, and respect that they are trying to keep the project clean. At work I have had many times where I spent more of my day reviewing MRs than actually writing code, and sometimes my cold blunt replies can unintentionally rub people the wrong way.

Still, I feel like they were pretty rude to this guy for no real reason. I don't think I'd want to work with them.

Agreed on the slacktivism point. Physical presence means something that bots and polls can't fake. My issue isn't with protesting itself, it's that the assumed impact often seems out of proportion with what's actually being achieved. A crowd showing up doesn't automatically translate to minds changed or policy moved. And crowd sizes can be just as ambiguous as poll numbers when it comes to representing broader sentiment. If the tactics alienate more people than they persuade, visibility alone isn't doing much.

Assuming critics are just reflexively resistant is a convenient way to avoid asking whether the criticism has merit. "They'd get it if they were more curious" is unfalsifiable.

Everyone already knows dissent exists. Polls, social media, elections make that clear. The question is whether street protests add anything to that awareness, and whether the way they're conducted generates curiosity or just irritation. For a lot of people it's the latter, and waving that off doesn't make the problem disappear.

You're describing how protests energize people who already agree. I'm asking how they persuade people who don't. The honks are from your side. The people you need are either tuning out or getting annoyed. Visibility used to equal influence when everyone watched the same three channels. That's not the world we live in anymore.

I was primarily discussing written language in my post, as that's easier to speculate on.

That said, if most people turn into hermits and start living in pods around this period, then I think you would be in the right direction.

If we focus only on the impact on linguistics, I predict things will go something like this:

As LLM use normalizes for essay writing (email, documentation, social media, etc), a pattern emerges where everyone uses an LLM as an editor. People only create rough drafts and then have their "editor" make it coherent.

Interestingly, people might start using said editor prompts to express themselves, causing an increased range in distinct writing styles. Despite this, vocabulary and semantics as a whole become more uniform. Spelling errors and typos become increasingly rare.

In parallel, people start using LLMs to summarize content in a style they prefer.

Both sides of this gradually converge. Content gets explicitly written in a way that is optimized for consumption by an LLM, perhaps a return to something like the semantic web. Authors write content in a way that encourages a summarizing LLM to summarize as the author intends for certain explicit areas.

Human languages start to evolve in a direction that could be considered more coherent than before, and perhaps less ambiguous. Language is the primary interface an LLM uses with humans, so even if LLM use becomes baseline for many things, if information is not being communicated effectively then an LLM would be failing at its job. I'm personifying LLMs a bit here but I just mean it in a game theory / incentive structure way.