Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The new rules of context engineering for Claude 5 generation models

claude.com

Post reply on HN
Print view View original

371–380 of 434 posts

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

#371

Post by TeMPOraL »

ben_w wrote: post #364
lanstin wrote: post #318

Earlier quoted context omitted.

Have you ever had a professor or mentor walk you through some experiences as a way to help you understand some complex concepts? I guess language is used in that but the ideas are conveyed by the process not the language. And I rather disagree that mathematics is language, when I did maths there was a distinct difference from understanding a thing and then writing it down. And modalities that don’t include “where is…

> And I rather disagree that mathematics is language, when I did maths there was a distinct difference from understanding a thing and then writing it down. It is generally the case that there's a difference between "understanding a thing" and "writing it down", as demonstrated by every student who studies for the exam, the Chinese Room thought experiment, and Business Bullshit Bingo. For example, I can copy the next…

> as demonstrated by every (...) the Chinese Room thought experiment

Wait, did I miss the Chinese Room suddenly becoming sensible, or relevant? Last I checked it was a failure to accept that the system of "human + room" can in fact understand Chinese, even if the components individually don't.

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

#372

Post by TeMPOraL »

porridgeraisin wrote: post #314
TeMPOraL wrote: post #213

Earlier quoted context omitted.

> For one thing, many animals that lack language can still navigate a very complicated natural world So can a cruise missile. Also I think there's like separate part of the brain for that > using concepts of phenomena like gravity, distance, speed, the threat level of another animal, etc. without needing a linguistic expression of those things.* FWIW, AFAIK we haven't shown the ability to think in concept exists anyw…

Ok, but it is clear the parent meant language as in words like english or tamil. If you expand language to include anything that can convey idea then the argument is meaningless and its a null agreement.

It's not a null argument, because LLMs have long moved past "language as in words like english or tamil". Tokens are not units of such language, at least not since visual and audio tokens became first-class objects and there's no actual distinction between them inside the model. That sameness of representation is what it means for a model to be "multimodal".

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

#373

Post by vhiremath4 »

ThoAppelsin wrote: post #353
paulddraper wrote: post #322

Earlier quoted context omitted.

> Why do I need a system prompt at all? That's like asking why you need employee onboarding. You could have Stephen Freaking Hawking and he still wouldn't know what you specifically want. > Why do I need another black box AIs to review the code of the black box AI why can’t these things get code right the first time. That's like asking why you need code reviews. Thinking about it from an antagonistic perspective is u…

I don’t understand why this one is all the way down here despite being the only reply that answers the questions asked. And the answers are right: We all do our work based on the context. We would process the same request differently under different circumstances. System prompts (and user-made AGENTS.md on top of that) are simply the very didactic and direct way to provide that context to LLMs. I guess it would be mo…

My guess is people are upset that this technology is getting pushed on them and through the industry with the promise (and shown side effect) of replacing them permanently. The failure modes of adopting this technology (early) then corroborates their anger (slop code, employees being lazy/deferring their AI bugs on them, unrealistic mania in the industry, the obvious grift, etc.). And this is all off the heel of large (and continuing) layoffs (regardless of your belief in why they have/are happening).

For people who are very pro these tools and trying to have a rational/calm conversation about practical use of AI, this response is likely very annoying. For people who are very anti these tools and trying to protect their way of life, the pro (or even tempered) reaction to wanting to use these tools effectively likely comes off as callous/idiotic/dangerous.

It's a heated technology and movement in general.

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

#374

Post by throwatdem12311 »

SirHackalot wrote: post #348
throwatdem12311 wrote: post #303

This kind of stuff just makes me think nobody has any clue how these things work. Why do I need a system prompt at all? Why do I need another black box AIs to review the code of the black box AI why can’t these things get code right the first time. Why is the best “coding model” in the world still making up APIs that don’t exist and do seemingly random unreleased changes that it wasn’t prompted for. Why do these mode…

> becoming disillusioned > becoming? It's all arcane, superstitious nonsense. Nobody actually knows how to work with these models is right. We've replaced software engineering with prompt astrology and Al whispering. The peak comedy of it all is watching people like Karpathy publish "skills" that read like psychoanalysis, just offering basic verbal instructions with a completely straight face...

You’re right. As the only staff engineer at my company every time I see yet another slop PR from an offshore developer that is just a “one shot” from Claude I just want to end it all.

I’m one engineer that needs to maintain a half a million line codebase (and growing!) and review all of these PRs that are generated at the speed of slop by people in another country that do not give a single f*ck. There’s one of me and 3 of them. Before AI this was manageable. After Claude Code was given to these guys to go hog wild it’s just become completely impossible to keep up. The irony is that we’re delivering slower because the projects are way bigger, complexity has exploded and keeps getting worse, and it takes way longer to review anything because the code that is generated is just mountains of slop. But the CEO can sell us as an “AI native” company it’s a total joke.

I’m currently looking at a list of 10 PRs by a single offshore dev with an average of 50 files changed in each. Al of which cross cutting with eachother and I just can’t shake the feeling I’d rather drive a garbage truck for a living - or drive my own car off a cliff instead.

Every time I see some prompt start with something like

“You are an expert software engineer…”

Or anything in that vein I just can’t help but shake the feeling that we’ve abandoned decades of software engineering best practices in favour of what is essentially reading tea leaves.

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

#375

Post by throwatdem12311 »

Tadpole9181 wrote: post #345
throwatdem12311 wrote: post #303

This kind of stuff just makes me think nobody has any clue how these things work. Why do I need a system prompt at all? Why do I need another black box AIs to review the code of the black box AI why can’t these things get code right the first time. Why is the best “coding model” in the world still making up APIs that don’t exist and do seemingly random unreleased changes that it wasn’t prompted for. Why do these mode…

I disagree, this is all because it's understood. You need a system promot because an LLM is fundamentally a token predictor. It needs to be primed for the work it's going to do, otherwise it's next token prediction has too little to go off in the beginning and goes nuts. You use a separate AI to review the code, because it's a token predictor trained mostly on accomplishing tasks in a cost effective way - we haven't…

My point is that I understand all of that but in my view that makes them fundamentaly flawed at a conceptual level for what people are saying they should be used for.

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

#376

Post by throwatdem12311 »

bensonperry wrote: post #346
throwatdem12311 wrote: post #341

Earlier quoted context omitted.

Why is human-like behavior the standard for comparison? These things should be better than us that’s the entire point. They should not be making the same mistakes that humans make that’s the half the reason for building tools.

i mean this is the same thing as self-driving cars and all sorts of technology - humans are our benchmark, being better than a human and cheaper immediately unlocks massive value everywhere. if i can hire a human-level programmer for ~$100 USD per month, that is an incredible upgrade from that costing me ~$10k per month!

Where’s all this supposed value being generated. What software is better? What is cheaper?

Nothing.

All lies.

Everything is actually worse.

Programmers got fooled into working harder and getting paid the same, if not less because the job market is so terrible now. Congrats you played yourself.

Saying you feel more productive is a worthless measure especially when these things are designed to gas you up and make you feel good.

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

#377

Post by Tadpole9181 »

throwatdem12311 wrote: post #375
Tadpole9181 wrote: post #345

Earlier quoted context omitted.

I disagree, this is all because it's understood. You need a system promot because an LLM is fundamentally a token predictor. It needs to be primed for the work it's going to do, otherwise it's next token prediction has too little to go off in the beginning and goes nuts. You use a separate AI to review the code, because it's a token predictor trained mostly on accomplishing tasks in a cost effective way - we haven't…

My point is that I understand all of that but in my view that makes them fundamentaly flawed at a conceptual level for what people are saying they should be used for.

Why? I'm an "artisanal programmer" at heart, but for the past year I've been using these to great effect. A car that needs to be started with a hand-crank and occasionally stalls is still a car.

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

#378

Post by cindyllm »

throwatdem12311 wrote: post #376
bensonperry wrote: post #346

Earlier quoted context omitted.

i mean this is the same thing as self-driving cars and all sorts of technology - humans are our benchmark, being better than a human and cheaper immediately unlocks massive value everywhere. if i can hire a human-level programmer for ~$100 USD per month, that is an incredible upgrade from that costing me ~$10k per month!

Where’s all this supposed value being generated. What software is better? What is cheaper? Nothing. All lies. Everything is actually worse. Programmers got fooled into working harder and getting paid the same, if not less because the job market is so terrible now. Congrats you played yourself. Saying you feel more productive is a worthless measure especially when these things are designed to gas you up and make you f…

[dead]

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

#379

Post by hbarka »

> The new rules of context engineering for Claude 5 generation models We removed over 80% of Claude Code's system prompt for more advanced models.

This is incredible. It’s like Claude learned one of the central ideas in the Tao Te Ching: you remove something every day. Wisdom and wholeness do not necessarily come from accumulating more. They can come from removing.

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

#380

Post by idiotsecant »

cataphract wrote: post #310
idiotsecant wrote: post #247

Earlier quoted context omitted.

I think you're conflating different things. Many people do not have an internal 'narrator'. I am one. I don't have a voice in my head saying words, ever. I do definitely have something like a playback of other people saying things, though. Words are still in there in the form of recall, they are just not part of the executive layer in a way I have access to.

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' deliberately deciding to make them and hold them in my head. It wouldn't happen naturally.

Post reply on HN