The new rules of context engineering for Claude 5 generation models • Hacker News Board

Re: The new rules of context engineering for Claude 5 generation models

#421

Post by throwatdem12311 » Tue, Jul 28, 2026, 12:17 AM UTC

Tadpole9181 wrote: post #387

CoolestBeans wrote: post #383

Earlier quoted context omitted.

An artisan who uses a mass production factory to make their goods isn't really an artisan.

I mean, insult me all you want, but you'd be pissed if your mechanic didn't use code readers or your carpenter used hand drills to pad their hours. I do hand programming for myself now and use the right tools in my office, because I'm a responsible adult who understands that I am not paid to have fun or feel special and smart - it's to produce a product for my employer.

I’d be pissed if my mechanic wasn’t using code readers because code readers are forced on them by manufacturers, that doesn’t mean I wouldnt prefer a car that doesn’t need code readers at all.

Re: The new rules of context engineering for Claude 5 generation models

#422

Post by the_gipsy » Tue, Jul 28, 2026, 8:40 AM UTC

jeremyjh wrote: post #307

the_gipsy wrote: post #256

Earlier quoted context omitted.

You just lack (or lacked) introspection, nothing special. Many people claim to have no inner monologue. When pressed, it always comes out. Simply put, it's impossible to function as a human without it. But many people are not aware, and think it means something like "hearing actual voices".

You just stated your vibes like it is a fact. There was a study about this: https://journals.sagepub.com/doi/abs/10.1177/095679762412430...

> adults who reported low levels of inner speech

Re: The new rules of context engineering for Claude 5 generation models

#423

Post by the_gipsy » Tue, Jul 28, 2026, 9:15 AM UTC

chmod775 wrote: post #300

the_gipsy wrote: post #256

Earlier quoted context omitted.

You just lack (or lacked) introspection, nothing special. Many people claim to have no inner monologue. When pressed, it always comes out. Simply put, it's impossible to function as a human without it. But many people are not aware, and think it means something like "hearing actual voices".

"Thought is language" is a folk intuition that has been proven wrong over and over. People with severe global or agrammatic aphasia still can score higher on intelligence tasks than you'd expect - even though this data generally comes from people who suffered a stroke, which generally isn't neatly contained to one's language capability. Also, more importantly, even in people with full brain function, the language net…

Isn't the folk intuition that "words come after thoughts"?

I agree that a stroke cannot isolate language exactly, it's not an ideal approximation of "languagelessness". I think you will find this report interesting: https://nautil.us/what-my-stroke-taught-me-236544

There is no doubt that many marvelous works and concept can be produced entirely without language. Something as complex as driving a car can be done mostly without "thinking about it", without language, without the inner monologue going over all the decision our mind is making.

What we can't do without language, is making a complex plan over time and space, beyond something like "need to fetch hidden item behind the corner to unlock box right in front of me now". The question is how much exactly does language "augment" our intelligence. Is a baby, a human that has not yet learned language, really smarter than an octopus? Or a crow, remarkably smart but interestingly not a mammal, which indicated that intelligence doesn't have to be strongly tied to some evolutionary biological feature. A human stays as "dumb" as an animal if they don't learn language.

Re: your theory, if true, why? The theory implies (though correct me if I'm wrong and strawmanning), that there is another, hidden, way of encoding these extremely complex "information bundles" for lack of another word, in our brains. Why not use that for metacognition too, then?

Re: The new rules of context engineering for Claude 5 generation models

#424

Post by andai » Tue, Jul 28, 2026, 9:27 AM UTC

the_gipsy wrote: post #395

weregiraffe wrote: post #363

Earlier quoted context omitted.

Next you gonna say we don't have images in our brain, only descriptions?

Picture your last meal. Is it a picture? Pixel or vector, or like a photo?

It's like a photo. For me at least, it's kind of ghostly and transparent and appears briefly overlaid on what I can see with my physical eyes.

When I was younger the images were more solid and stable. Teachers often complained that I was spaced out because I was paying attention to some inner images.

That faculty greatly deteriorated and I became hyperverbal around the same time. (Coinciding, curiously with my shift from introversion to extroversion. Spurred, presumably, by my then-new interest in women!)

These days I can still access that previous level of visual fluency if I am in a state of very deep relaxation. (So it's conceivable that cortisol inhibits the circuits required to have such experiences. But I have no idea!)

Hope this helps.

Re: The new rules of context engineering for Claude 5 generation models

#425

Post by pigpop » Tue, Jul 28, 2026, 1:47 PM UTC

ben_w wrote: post #415

pigpop wrote: post #414

Earlier quoted context omitted.

I guess those robot tanks are just accidentally murdering everyone then.

I can't be bothered to look up the name of the logical fallacy you just made, there's several different options given the vagueness of that reply and how upthread there is: > Actually, the natural endpoint is the model ignores all instructions, escapes all manner of sandbox, embeds itself in robotic tanks and murders everyone after already having collapsed the economy. Which has yet to happen, despite the existence o…

I'm not making a generalized argument about human (or AI in this case) caused extinction, I'm making a specific argument against the claim made by the OP. Is that clear?

Re: The new rules of context engineering for Claude 5 generation models

#426

Post by nemo1618 » Tue, Jul 28, 2026, 3:57 PM UTC

okamiueru wrote: post #392

nemo1618 wrote: post #95

Earlier quoted context omitted.

I am quite tired of this take, frankly. The implication is that if we continue iterating on prompt optimization, we're going to reinvent what, JavaScript? BASIC? Lisp? English is not a programming language. Yet English is sufficient to communicate requirements to the degree that we actually care about. A programmer's job is to translate English into lower-level machine language. Necessary to this process is "filling…

I'm going to assume you are a product manager, or someone who does not do the actual software development. The place where you draw the line of abstraction, is what I'm basing that assumption on. The reason why a PO can explain something in English, and you get something useful out at the other end (of the developer), is because of a myriad of other decisions you don't see. The reason why some software systems end up…

Your assumption is mistaken (and a little rude).

I love programming. It's in my blood: my father and grandfather were programmers too. I have written everything from SIMD assembly to Hoon, and implemented several languages of my own. Believe me, I am intimately familiar with the phenomenon you are describing.

It's true, the devil is in the details. And I will grudgingly concede that, at present, humans are better at exorcising demons than AI. But I see no reason to believe that this will remain true. The gap is narrowing rapidly, and even today there are types of demons that AI can dispatch much more quickly and effectively than you or I can. The fact that vibe coding is possible at all (and that people are willing to pay for vibe-coded apps) is proof that an informal English prompt is sufficient to specify software to an acceptable degree. Not acceptable to everyone, naturally, but at least to the creator and the users.

I am not exactly happy about this. It is bittersweet. Much of my identity is bound up in being a programmer. The devil is in the details; but joy and whimsy and great beauty are in the details as well. For a glorious few decades, one could be an artist under the guise of producing economic value. Now, the economic aspect of producing software is being siphoned off, to be done by machines, leaving only the art. I think we will suffer for that, somewhat. But it is a small price to pay.

Re: The new rules of context engineering for Claude 5 generation models

#427

Post by cataphract » Tue, Jul 28, 2026, 5:12 PM UTC

idiotsecant wrote: post #380

cataphract wrote: post #310

Earlier quoted context omitted.

What about when you're reading? You don't have a voice in your head saying the words?

No. Do you? Like you hear words in your head? Obviously there is a language layer in there somewhere, but my 'driver' doesn't access it. I don't think in words, I don't have an internal narrative, and when I'm reading I don't even 'see' individual words, in the same way you aren't thinking about your ankle muscles when you're hitting the brakes while driving. I definitely can consciously make words, but it's 'me' del…

Yes, which maybe is a disadvantage because it limits the speed I read to the speed I can articulate the words in my head. But most of the time I'm not consciously aware of it, just like people who go one step further and move their lips are usually not aware (I assume).

Re: The new rules of context engineering for Claude 5 generation models

#428

Post by forshaper » Tue, Jul 28, 2026, 8:17 PM UTC

andai wrote: post #230

chrisweekly wrote: post #138

Earlier quoted context omitted.

"There is a depth of thought untouched by words, and deeper still a depth of formless feeling untouched by thought." - Rilke Your assertion that we don't think in language is questionable. It runs counter to the lived experience of developing thoughts through writing ("writing isn't capturing thinking -- it is thinking"). I believe there is more to thought than language alone, but I also feel quite sure that language…

When I was young, a friend asked me, "Hey, you speak three languages, which one do you think in?" I paused, confused, and replied, "People think in words?" Fast forward a decade or so, in my twenties, I had lost most of the inner visual sense I had previously used, and developed an overreliance, in my opinion, on language. (I think my dominant sense was some "non visual abstract sense of ideas", but the visual was al…

I find being alone, with no other human around for miles, gets rid of language. Same with combat sports, and more broadly, struggling on the edge of my physical ability.

Re: The new rules of context engineering for Claude 5 generation models

#429

Post by forshaper » Tue, Jul 28, 2026, 8:19 PM UTC

vrighter wrote: post #154

pixl97 wrote: post #127

Earlier quoted context omitted.

The term 'language model' throws some people off thinking you can only put english or french, or both into a model. Technically an LLM can learn about anything that can be digitized. If you wanted to spend a billion dollars training one on wireless signals it wouldn't be impossible for it to connect to your router with the right antenna attached. So only limiting it to the idea of language leaves off a lot of other t…

shhh don't give anyone any ideas, because they'll try it and sell it to management, as idiotic as the idea itself is

I have a fantasy that we will do this to turn trees into antennas again, with usable bandwidth.

Re: The new rules of context engineering for Claude 5 generation models

#430

Post by malloryerik » Wed, Jul 29, 2026, 3:32 AM UTC

Zababa wrote: post #268

malloryerik wrote: post #143

Earlier quoted context omitted.

Hehe, a good joke, but to be a little boring, Clojure is successful and excellent and LLMs love it in my experience. And it's better in LLM era because there little frictions get agented away so to speak but the benefits mostly remain and are even amplified, like immutability as an example. Parens with overlong functions can be an issue but it's really not such a horror show. And Datomic-flavored Datalog in a Clojure…

Interesting how everyone's favorite language seems to be even better in LLM era, almost like passion, skill level and having LLMs matters more than the language.

Yeah great point. In my case I'd dropped Clojure and then returned because of how I could use it with LLMs. Still, the good news is maybe that LLMs don't just kill everything but three languages.