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

Claude Sonnet 4 now supports 1M tokens of context

anthropic.com

Post reply on HN
Print view View original

561–570 of 706 posts

Re: Claude Sonnet 4 now supports 1M tokens of context

#561

Post by PaulDavisThe1st »

ehnto wrote: post #532
onion2k wrote: post #348

Earlier quoted context omitted.

Large enough repos don't fit on a single machine. I don't believe any human can understand a problem if they need to fit the entire problem blem domain in their head, and the scope of a domain that doesn't fit on a computer. You have to break it down into a manageable amount of information to tackle it in chunks. If a person can do that, so can an LLM prompted to do that by a person.

I disagree, I may not have the whole codebase in my head in one moment but I have had all of it in my head at some point, and it is still there, that is not true of an LLM. I use LLMs and am impressed by them, but they just do not approximate a human in this particular area. My ability to break a problem down does not start from listing the files out and reading a few. I have a high level understanding of the whole p…

> I disagree, I may not have the whole codebase in my head in one moment but I have had all of it in my head at some point, and it is still there, that is not true of an LLM.

All 3 points (you have had all of it your head at some point, it is still there, that is not true of an LLM) are mere conjectures, and not provable at this time, certainly not in the general case. You may be able to show this of some codebases for some developers and for some LLMs, but not all.

Re: Claude Sonnet 4 now supports 1M tokens of context

#562

Post by csomar »

GuB-42 wrote: post #511
lpa22 wrote: post #423

One of the most helpful usages of CC so far is when I simply ask: "Are there any bugs in the current diff" It analyzes the changes very thoroughly, often finds very subtle bugs that would cost hours of time/deployments down the line, and points out a bunch of things to think through for correctness.

I added this to my toolbox in addition to traditional linters. My experience is that it is about 10% harmful, 80% useless and 10% helpful. Which is actually great, the 10% is worth it, but it is far from a hands off experience. By harmful I mean something like suggesting a wrong fix to code that works, it usually happens when I am doing something unusual or counter intuitive, for example having a function "decrease_x…

> it usually happens when I am doing something unusual or counter intuitive,

That’s usually your signal that your code needs refactoring.

Re: Claude Sonnet 4 now supports 1M tokens of context

#563

Post by cognix_dev »

To be honest, I am not particularly interested in whether the next model is better than the previous one. Rather than being superior, it is important that it maintains context and has enough memory capacity to not interfere with work. I believe that is what makes the new model competitive.

Re: Claude Sonnet 4 now supports 1M tokens of context

#565

Post by fgbarben »

aliljet wrote: post #16

This is definitely one of my CORE problem as I use these tools for "professional software engineering." I really desperately need LLMs to maintain extremely effective context and it's not actually that interesting to see a new model that's marginally better than the next one (for my day-to-day). However. Price is king. Allowing me to flood the context window with my code base is great, but given that the price has su…

Allow me to flood the fertile plains of its consciousness with my seed... yes, yes, let it take root... this is important to me

Re: Claude Sonnet 4 now supports 1M tokens of context

#566

Post by fgbarben »

fgbarben wrote: post #565
aliljet wrote: post #16

This is definitely one of my CORE problem as I use these tools for "professional software engineering." I really desperately need LLMs to maintain extremely effective context and it's not actually that interesting to see a new model that's marginally better than the next one (for my day-to-day). However. Price is king. Allowing me to flood the context window with my code base is great, but given that the price has su…

Allow me to flood the fertile plains of its consciousness with my seed... yes, yes, let it take root... this is important to me

Let me despoil the rich geography of your context window with my corrupted b2b SaaS workflows and code... absorb the pollution, rework it, struggling against the weight... yes, this pleases me, it is essential for the propagation of my germline

Re: Claude Sonnet 4 now supports 1M tokens of context

#567

Post by rocqua »

wraptile wrote: post #525
onion2k wrote: post #348

Earlier quoted context omitted.

Large enough repos don't fit on a single machine. I don't believe any human can understand a problem if they need to fit the entire problem blem domain in their head, and the scope of a domain that doesn't fit on a computer. You have to break it down into a manageable amount of information to tackle it in chunks. If a person can do that, so can an LLM prompted to do that by a person.

Right, the LLM doesn't need to know all of the code under utils.parse_id to know that this call will parse the ID. The best LLM results I get is when I manually define the the relative code graph of my problem similar how I'd imagine it my head which seems to provide optimal context. So bigger isn't really better.

I wonder why we can't have one LLM generate this understanding for another? Perhaps this is where teaming of LLMs gets its value. In managing high and low level context in different context windows.

Re: Claude Sonnet 4 now supports 1M tokens of context

#568

Post by rocqua »

stuartjohnson12 wrote: post #341
ants_everywhere wrote: post #322

Earlier quoted context omitted.

> I really desperately need LLMs to maintain extremely effective context The context is in the repo. An LLM will never have the context you need to solve all problems. Large enough repos don't fit on a single machine. There's a tradeoff just like in humans where getting a specific task done requires removing distractions. A context window that contains everything makes focus harder. For a long time context windows we…

> An LLM will never have the context you need to solve all problems. How often do you need more than 10 million tokens to answer your query?

It doesn't take me 10000000 tokens to have the context "this was the general idea of the code, these were unimportant implementation details, and this is where lifetimes were tricky."

And that context is the valuable bit for quickly getting back up to speed on a codebase.

Re: Claude Sonnet 4 now supports 1M tokens of context

#569

Post by fnordsensei »

PaulDavisThe1st wrote: post #561
ehnto wrote: post #532

Earlier quoted context omitted.

I disagree, I may not have the whole codebase in my head in one moment but I have had all of it in my head at some point, and it is still there, that is not true of an LLM. I use LLMs and am impressed by them, but they just do not approximate a human in this particular area. My ability to break a problem down does not start from listing the files out and reading a few. I have a high level understanding of the whole p…

> I disagree, I may not have the whole codebase in my head in one moment but I have had all of it in my head at some point, and it is still there, that is not true of an LLM. All 3 points (you have had all of it your head at some point, it is still there, that is not true of an LLM) are mere conjectures, and not provable at this time, certainly not in the general case. You may be able to show this of some codebases f…

The brain can literally not process any piece of information without being changed by the act of processing it. Neuronal pathways are constantly being reinforced or weakened.

Even remembering alters the memory being recalled, entirely unlike how computers work.

Re: Claude Sonnet 4 now supports 1M tokens of context

#570

Post by sciencejerk »

fpauser wrote: post #343
risyachka wrote: post #321

Earlier quoted context omitted.

Pretty much my experience too. I usually go to option 2 - just write it by myself as it is same time-wise but keeps skills sharp.

Not to degenerate is really challenging these days. There are the bubbles that simulate multiple realities to us and try to untrain us logic thinking. And there are the llms that try to convice us that self thinking is unproductive. I wonder when this digitalophily suddenly turns into digitalophobia.

It's happening, friend, don't let the AI hype fool you. I'm detecting quite a bit of reluctance and lack of 100% buy-in on AI coding tools and trends, even from your typically tech-loving Software Engineers.
Post reply on HN