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

151–160 of 434 posts

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

#151

Post by margalabargala »

KludgeShySir wrote: post #139
customguy wrote: post #104

Earlier quoted context omitted.

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…

Exactly, like weather forecasting. If you're told there's a 30% chance of rain, it doesn't mean that 3 out of 10 times you will experience rain. Either it will rain or it won't, so the probability is either 0% or 100%. And so a forecast of "30% chance of rain" is referring to the likelihood that your probability will be 100%, as opposed to 0%.

> Either it will rain or it won't, so the probability is either 0% or 100%. And so a forecast of "30% chance of rain" is referring to the likelihood that your probability will be 100%, as opposed to 0%.

This is a huge misunderstanding of what probability means.

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

#152

Post by radio879 »

chrisweekly wrote: post #138
chmod775 wrote: post #113

Earlier quoted context omitted.

It's language and speech patterns that seem designed to trick readers into believing that claims are correct, even when the claims aren't based on anything and are possibly wrong. It was rewarded for this during training for some reason. Alternative theory: The LLMs only way to "think" about abstract concepts is through language, and this leaks into into conversation it has with humans. But humans generally prefer to…

"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…

There are people who do not have any words in their heads at all when they think, and there doesn't seem to be any reason to disbelieve them. It may have been proven or at least observed in fMRI. Some people think in visuals.

I think some of this was discovered somewhat recently

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

#153

Post by cookiengineer »

chmod775 wrote: post #113
Retr0id wrote: post #53

Earlier quoted context omitted.

Until recently I thought "load-bearing seam" was a satirical exaggeration - I'd seen both claudisms independently but never combined. But a couple of days ago it hit me with "The key structural point first: the only load-bearing seam is [...]"

It's language and speech patterns that seem designed to trick readers into believing that claims are correct, even when the claims aren't based on anything and are possibly wrong. It was rewarded for this during training for some reason. Alternative theory: The LLMs only way to "think" about abstract concepts is through language, and this leaks into into conversation it has with humans. But humans generally prefer to…

It's actually an effect that happens in the (re-)alignment process due to harmonic properties of the positional encoding in the attention matrix.

(I recommend reading and implementing the Attention is all you need paper. By hand. Otherwise you won't learn anything from it.)

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

#154

Post by vrighter »

pixl97 wrote: post #127
chmod775 wrote: post #113

Earlier quoted context omitted.

It's language and speech patterns that seem designed to trick readers into believing that claims are correct, even when the claims aren't based on anything and are possibly wrong. It was rewarded for this during training for some reason. Alternative theory: The LLMs only way to "think" about abstract concepts is through language, and this leaks into into conversation it has with humans. But humans generally prefer to…

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

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

#155

Post by vrighter »

jiggawatts wrote: post #50
ValentineC wrote: post #45

Earlier quoted context omitted.

Commit Strip seems to be down, so here's the Wayback Machine version: https://web.archive.org/web/20260521130338/https://www.commi...

I was just thinking of this exact comic, which is etched into my brain for some reason. The obvious counter to this is that we've been going through this evolution of increasing abstraction as developers for nearly a century now. In the 40s and well into the 60s, most code was written either as straight up machine code or an assembly language. MS DOS is almost entirely assembly. UNIX ushered in the era of "high level…

the only difference is that the compiler always looks at the whole code and if it says it can do something, it can, always, and without fail.

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

#156

Post by senderista »

antonymoose wrote: post #96
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…

Maybe I’m behind the curve here because I work in an SRE/DevOps context as of late - but LLMs routinely shit the bed and fail to solve basic issue for me when I try to use them (Thanks, Management) I don’t need a model to shit out a REST endpoint. I need it to figure out esoteric errors that take hours or days of debugging. They just don’t do well here. Of course, if a diligent engineer refined considerations from a…

I dunno, Claude announces it found “the smoking gun” every single time.

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

#157

Post by fastball »

nullbio wrote: post #134

We want more control, not less. This (among many others) is the reason I use GPT over Claude. It adheres very closely to your instructions and rules. You can build up your own workflows and systems as a result. Claude just does whatever it wants, regardless of what you tell it. It's a miserable experience. Claude is what you use when you want to one-shot a simple cookie-cutter product that has no nuance in it. A prod…

The fact you called it ChatGPT instead of Codex makes me suspicious of this entire comment.

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

#158

Post by nemo1618 »

antonymoose wrote: post #96
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…

Maybe I’m behind the curve here because I work in an SRE/DevOps context as of late - but LLMs routinely shit the bed and fail to solve basic issue for me when I try to use them (Thanks, Management) I don’t need a model to shit out a REST endpoint. I need it to figure out esoteric errors that take hours or days of debugging. They just don’t do well here. Of course, if a diligent engineer refined considerations from a…

Further evidence that there is some kind of weird parallel universe thing going on with LLMs. "Figuring out esoteric errors" is one of the things I would cite as a particular strength of agents. I am repeatedly amazed at their ability to root-cause weird behavior on my systems. Here is one example: https://xcancel.com/lukechampine/status/2047032091053859138

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

#159

Post by chickensong »

Retr0id wrote: post #53
hmokiguess wrote: post #47

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.

Until recently I thought "load-bearing seam" was a satirical exaggeration - I'd seen both claudisms independently but never combined. But a couple of days ago it hit me with "The key structural point first: the only load-bearing seam is [...]"

People make fun of the language, rightfully so in some cases, but also it's often quite effective language. "load-bearing seam" communicates quite a lot in very few characters.
Post reply on HN