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

211–220 of 434 posts

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

#211

Post by witx »

And they are still crap at generating code.

At my previous company they have a series of smoke tests for models mostly focused on performance and architecture. I'm still on the team chat and results just came in:

- It's abohrrent at c++: it keeps generating code with data races and, more rarely, use-after-free bugs! It doesnt seem to be able to reason about lifetimes. This on a mostly mid/junior team. It's a bug fest.

- architecture in c++ is a verbose and layered mess even for simple things, which paired with the previous bugs I mentioned is scary.

- For rust obviously there's no use-after-free, but has same architecture pitfalls of layers upon layers. It uses copy and clone all over and performance is bad. Trying to unwrap all that is messy and costs lots of time. Once in a while it generates unsafe code for some non obvious reason

The scary stuff is non determinism. You get different depending on who prompts the agent but there's always some flavour of the points mentioned above. Funny that my team was very adamant on AI-first (why I left) and now they writting more and more code by hand after some very serious bugs and, as they say, dead moments where they have to wait, sometimes hours, and start wondering about the value of their skills, for the model to generate the next spaghetti recipe

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

#213

Post by TeMPOraL »

noduerme wrote: post #169
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…

I strongly disagree. For one thing, many animals that lack language can still navigate a very complicated natural world using concepts of phenomena like gravity, distance, speed, the threat level of another animal, etc. without needing a linguistic expression of those things. Images and music can convey ideas without language. Math can convey ideas without language. Physically taking apart an object and putting it ba…

> 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 anywhere except in humans (because philosophy, reported experience) and LLMs (because we can literally see them forming and activating in patterns, and we've learned to identify them specifically, and experimentally verified through amplifying or suppressing them and observing behavior, etc.).

But more importantly:

> Images and music can convey ideas without language. Math can convey ideas without language. Physically taking apart an object and putting it back together can convey extremely complex ideas without language.

Images and music and math are langauge. If it can convey ideas, it is language.

Words and sentences and speech are subset of the idea of language and communication, that for some reason gets routinely confused for the whole thing. At this point I'd say even the "language models" are badly named, simply because people see "language models" think of "token" as number representing a sub-word element in existing human language like English. With multimodal models, at this point tokens are closer to units of sensory experience.

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

#214

Post by esseph »

prox wrote: post #190
bensyverson wrote: post #145

Earlier quoted context omitted.

s/blast radius/malloc/g

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

For example: limiting the number of resources in a particular Terraform state file so that if an apply goes wrong, it just takes out the dev instance for the app and not the prod instance if every company app.

It uses "blast radius" often in similar contexts.

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

#215

Post by otabdeveloper4 »

JohnBooty wrote: post #142
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…

This is true and it's barely even debatable. Whatever exact role language plays in our thought processes, it is most definitely nonzero. It's why I think "LLMs are only fancy autocorrect" style takes are really underselling how wild it is that we've, in a roundabout way, sort of crystallized a bit of the human thought process in a way that is genuinely useful for a lot of tasks. Linguistic Relativity — John Lucy http…

> sort of crystallized a bit of the human thought process

a) LLMs don't think. They predict a most probable sequence of language tokens. Huge difference there.

b) Whatever LLMs do doesn't model human behavior whatsoever. LLMs are basically very fancy logistic regressors. I.e., it's a mathematical abstraction first and foremost.

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

#216

Post by bloody_bocker »

shhsushs wrote: post #196
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...

This is getting tiring. Code is not The Specification. It’s a specification of God knows what. Riddled with irrelevant, non-essential details wrapping The Problem - which in most cases will amount to something the size of a large pebble - in multiple layers of fur jackets, stored in boxes, which themselves are stored in multiple ridiculous moveable warehouse (if you’re lucky). We have a standard for communication, it…

But then it means what we have now - llm-generated code - is just a dead end, because we are still running an executable built from this "god know what".

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

#217

Post by Sebastian_09 »

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…

Are you sure this is Rilke? Couldn’t find anything online - it seems it’s close to a quote by Zora Neale Hurston

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

#218

Post by javier2 »

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 [...]"

I see it at least 3-4 times per week...

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

#219

Post by dsauerbrun »

espeed wrote: post #189

Claude Code is deleting your context history on a timer. I wanted to build a searchable index of my context history, and tonight I discovered, "The default retention is roughly 30–45 days. Anything older gets removed automatically." https://code.claude.com/docs/en/data-usage#data-retention This is nuts. Anthropic should not be deleting your data on your own device.

Well that explains where my sessions went on my side project that I came back to after a few months... Thought I was going crazy

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

#220

Post by crossroadsguy »

> Now: Let Claude use judgement

> When we first rolled out Claude Code, we needed to be sure that Claude avoided worst case scenarios, such as deleting files. This meant we would give particularly strong guidance that might not always be true

Oh, AI Company, you would want us to do that, won't you?

I don't want to trust claude cli, kilo, glm, claude desktop, codex etc.

It's high time Apple and Linux world wakes to the advent of LLMs and local agenting coding tools, so that users get really intuitive (read GUIs, simple CLIs) OS level tools and APIs that these coding tools are forced to adhere to that users can control broadly or in a micro managed way, if they need to. So that they don't have to worry about when the model will go berserk and fool the tool.

Post reply on HN