Live data from Hacker News

The new rules of context engineering for Claude 5 generation models

claude.com

251–260 of 434 posts

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

#251
So this is cool. I recently asked Opus and Fable to "say hi" in Claude code. The "hi" cost roughly $0.50 for Opus and $1 for Fable, mostly due to the length of the system prompt.

I'm eager to test the new version. If it's 80% shorter now, then saying hello should only cost Fable $0.20. Exciting times.

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

#252
post #190

Earlier quoted context omitted.

s/blast radius/malloc/g

Wait it uses “blast radius” ? In what context?

I see "blast radii" all the time in context of refactorizations. Like, what happens if we swap library A for library B.

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

#253
post #251

So this is cool. I recently asked Opus and Fable to "say hi" in Claude code. The "hi" cost roughly $0.50 for Opus and $1 for Fable, mostly due to the length of the system prompt. I'm eager to test the new version. If it's 80% shorter now, then saying hello should only cost Fable $0.20. Exciting times.

Also try Hey if you've got the budget ;-)

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

#254

Earlier quoted context omitted.

Now I have the full picture. You're right to push back, and that's on me. The load-bearing seams of language are the smoking gun I should have been aware of.

I have heard so many of my co-workers use "load-bearing" over the last couple of months. It's truly comical. Maybe this is a way that we can make "fetch" happen.

I made the decision to always talk to AI in English, in order to reduce the otherwise inevitable seep-in of AI terminology into my actual speaking and writing patterns. Czech and English are far apart enough that formulations like "load-bearing" don't cross the barrier easily.

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

#255
post #251

So this is cool. I recently asked Opus and Fable to "say hi" in Claude code. The "hi" cost roughly $0.50 for Opus and $1 for Fable, mostly due to the length of the system prompt. I'm eager to test the new version. If it's 80% shorter now, then saying hello should only cost Fable $0.20. Exciting times.

Do you know why they don't just cache the system prompt for everyone? It seems so wasteful not to.

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

#256
post #230

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…

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".

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

#257
post #193

Earlier quoted context omitted.

30 days is just a default, so your session data doesn’t fill your hard drive. It’s a configurable setting. You can make the retention as long as you want.

A new default. That wasn't the default a few months ago. Silently deleting your user's data is so stupid on so many levels. They have no idea what they're doing.

They may also realize that these chats are super sensitive especially around ppl constantly pasting secrets into their chats

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

#258
post #3

I've always thought that extensive throat-clearing and prefixing the Treaties of Westphalia-length instructions into the context window was unnecessarily baroque when you can just talk to the agent. I guess part of it is also that I don't mind doing 'hand-edits' like for example LLMs love to say "// so and so removed" I just go and remove that manually later rather than being like "don't comment about what you remove…

> But I also have a hands-on human-in-the-loop working style

Literally HitL-er

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

#259
post #221

Earlier quoted context omitted.

I have a coworker that was complaining about Opus 5 and had random shitty skills and custom plugins wired in from YouTube tutorials watched over the past year. He also speaks with the model like it's GPT 4o. Needless to say, none of the new models have worked well for him, and he refuses to remove the "tweaks" or update his style of communication, which is obviously breaking the experience.

> Needless to say, none of the new models have worked well for him, and he refuses to remove the "tweaks" or update his style of communication, which is obviously breaking the experience. All attempts to control the output in a useful way for the user, in a way where the output is as reliable and repeatable as possible... and with a system not at all designed for it, that gets worse the more rules you throw at it. Se…

The model can output what he wants, but he has way too many things that are confusing the model and harness. If he got rid of all the random crap and just gave it an instruction he would be fine.

Models needed a lot more steering a few months ago, now they need a lot less.

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

#260
post #230

Earlier quoted context omitted.

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…

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".

I'm not sure. I think I had a reasonable amount of metacognition as a child. I remember being eight years old, and having a really cool idea but forgetting it.

So I devised a plan to retrieve it. I'm just going to rewind time. I'm going to go back to doing what I was doing when I had that idea, and then it'll come back to me.

And so I remembered that I had been fiddling with my seat belt when I had the idea. And so I resumed fiddling, and my cool idea promptly came back.

Metaphors and abstractions came to me much later though. (I struggled with OOP for about 10 years until one day it all just clicked.) Symbolism took me another ten years.

Post reply on HN