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

101–110 of 434 posts

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

#101

Post by fragmede »

geuis wrote: post #99
ValentineC wrote: post #71

Earlier quoted context omitted.

I haven't been impressed with Opus 5 over the past ~30 hours either. It's made countless careless mistakes folding in plan amendments after they get reviewed by Sol, and has produced sloppy mockups (e.g. buttons overflowing past cards) despite all the supposed verification claims.

I finally made progress today on a deeply intractable problem that Sonnet was just incapable of solving despite hours of experimentation and multiple attempts. I swapped over to Opus in a new handoff session with the expectation of using at least one 5 hour session. It wasn't quick and took several hours but eventually Opus dialed in on several cascading base failures resulting from how the base vision model was bein…

Yeah exactly. The other day I caught myself prompting Claude a very specific question about the code architecture for something I'm working on to have it refactor something I intuited about the code, and realized that I could only ask that because of my decades of software development experience. No vibecoder without those decades could have asked that, and in doing so, I saved my company I don't know how much in future code debt issues.

New interview question. Tell me about a time that AI generated bad code for you, and how did you fix it?

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

#102

Post by vatsachak »

Exoristos wrote: post #97
vatsachak wrote: post #26

Earlier quoted context omitted.

I disagree. I speak in code to the LLMs. It's just that LLMs are really good at reinventing the wheel that you were supposed to in your codebase. Recent example. struct TensorView { body: Arc , shape: [usize], stride: [usize], offset: usize, } Okay now fill in all the helper methods. And GPT 5.6 Sol did a good job.

The lengths some of y'all will go to to avoid using JetBrains products.

I doubt anything other than an LLM auto complete could add something like a tensor reshape

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

#103

Post by FridgeSeal »

jiggawatts wrote: post #86
devnonymous wrote: post #74

Earlier quoted context omitted.

> We simply have better magic wands and more powerful spells now. Wouldn't it be nice though if the incantation of the same spell would always do the same thing every time ? You see that's how my old wand and spells worked.

Look at it from the perspective of a manager above individual developers. Their instructions to those devs are already a series of non-deterministic incantations. They ask for things in English and get something back in Git a week later! We've just pushed that indirection down a level from managers to ICs. The ICs are shocked and surprised that this level of imprecision is allowed. Their managers are not shocked at a…

The managers, aren’t on the hook for actually understanding and delivering the work, or fixing the system a week later when the vagaries of their wand-waving request come home to roost though.

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

#104

Post by customguy »

pdimitar wrote: post #82
esseph wrote: post #68

Earlier quoted context omitted.

> We simply have better magic wands and more powerful spells now. But tainted 20-40% by bouts of Wild Magic which make the outcome entirely nondeterministic, despite the best protection wards we can conjure.

I have found, both in my commercial and OSS work, that getting better at producing protection wards reduces the non-determinism to somewhere in-between 1-10%. Case in point: writing our own linters.

You can reduce pregnancy to 0.00001% and there'll still be a baby. As in, "you can't be half-pregnant". A tool is either deterministic (within some limits [0]) or it isn't.

[0] For example, for the purpose of driving a nail, if you know how to use it, a hammer is pretty straightforward tool, and what happens depends pretty much on how you use it, and what you use it on. But of course the handle can break, there could be a manufacturing defect. Just like your RAM can be faulty or your computer infected, and suddenly C doesn't behave according to the standard anymore.

But for the purpose of the discussion a hammer is still a deterministic tool, and even though we don't even fully understand everything about physics, we understand enough about hammers and nails that at least many people with material that isn't faulty can use them "blindly" (not literally, in this case) every day, without any surprises. It isn't heavier on the handle end or has a head made of glass in even 0.000000001% of uses. You might say because magic isn't real and hammers follow the laws of physics, as obscure as those may be to us, that never, ever happens. They can be faulty in all sorts of ways but they will never be 10x bigger or 10x smaller between one swing and the next, and so on.

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

#106

Post by macintux »

FridgeSeal wrote: post #103
jiggawatts wrote: post #86

Earlier quoted context omitted.

Look at it from the perspective of a manager above individual developers. Their instructions to those devs are already a series of non-deterministic incantations. They ask for things in English and get something back in Git a week later! We've just pushed that indirection down a level from managers to ICs. The ICs are shocked and surprised that this level of imprecision is allowed. Their managers are not shocked at a…

The managers, aren’t on the hook for actually understanding and delivering the work, or fixing the system a week later when the vagaries of their wand-waving request come home to roost though.

They’re typically on the hook for making sure those tasks are accomplished, however. I’ve spent 30 years in this industry doing my best to avoid that role, because that’s a terrible place to be.

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

#107

Post by geuis »

fragmede wrote: post #101
geuis wrote: post #99

Earlier quoted context omitted.

I finally made progress today on a deeply intractable problem that Sonnet was just incapable of solving despite hours of experimentation and multiple attempts. I swapped over to Opus in a new handoff session with the expectation of using at least one 5 hour session. It wasn't quick and took several hours but eventually Opus dialed in on several cascading base failures resulting from how the base vision model was bein…

Yeah exactly. The other day I caught myself prompting Claude a very specific question about the code architecture for something I'm working on to have it refactor something I intuited about the code, and realized that I could only ask that because of my decades of software development experience. No vibecoder without those decades could have asked that, and in doing so, I saved my company I don't know how much in fut…

Good question! I think I'll use that as a counter question next time I interview. Ask a technical member of the team I'm interviewing with how they handled that situation.

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

#108

Post by avaer »

mycentstoo wrote: post #7

We should design a specific language to make sure that we can encode the exact requirements that we want. Something that has a limited set of keywords that are explicit. Wait a minute...

The trend (and what TFA is arguing) is literally the opposite: be more implicit, don't waste time on details, and encode the high level concepts only. Because the rest has a billion examples in the model.

You can argue against LLM's, but increasingly (unfortunately) you're not going to do better programming by prompting the LLM with code. The agent can find the interfaces it needs.

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

#109

Post by ceejayoz »

vidarh wrote: post #37
Fordec wrote: post #11

This all strikes me as an effort to move tailoring the harness out of the easily transferable .md file into specific Anthropic tooling to increase lock in. I've been running Opus 5 today and it's already done accidental deletions, made far more mistakes and worked around deliberate hook controls than previous Opus versions combined. Also it looks like token usage is up as it fails at the task the first time around mu…

I have a document generation task that I used to run with 4.8. This morning after it switched to 5, the documents were consistently 30%-40% longer for the same prompt... Not evaluated whether they are actually better or worse yet, but what was interesting was how consistently more verbose it was.

I'm sure that's entirely unrelated to the fact that they charge per token.

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

#110

Post by ceejayoz »

pigpop wrote: post #83
cmdocidjcije wrote: post #4

Earlier quoted context omitted.

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. I hate to say it because it sounds ridiculous, but that is the path we are going to arrive at just give it 50 years. We are the proof: what do we do to animals that are less intelligent than ourselves? Now take away the mor…

>what do we do to animals that are less intelligent than ourselves? We do a lot of different things but we typically don't make an organized effort to eradicate them unless they are actively doing us harm. There is also a massive difference between how we treat animals based on their similarity, sentimentality and utility to us; we are unconcerned with accidentally stepping on an ant but most people would be very ups…

> We do a lot of different things but we typically don't make an organized effort to eradicate them unless they are actively doing us harm.

Sure. But some of the species we breed at scale might prefer we did just eradicate them, like the chickens that grow so fast their entire giant breast muscle becomes chewy scar tissue.

(It's also not true for, say, whales; no harm, but we wanted their shit. If they have language, their stories probably heavily feature their own Holocaust. Nor passenger pigeons, who we just got rid of.)

Post reply on HN