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

591–600 of 706 posts

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

#591

Post by ivape »

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…

My ability to break a problem down does not start from listing the files out and reading a few.

I does, it’s just happening at lightning speed.

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

#592

Post by cube00 »

razemio wrote: post #571
cube00 wrote: post #551

Earlier quoted context omitted.

> Tell Claude your developer finished XYZ [...] (Claude will find more problems with your developer's work than with yours). It's crazy to think LLMs are so focused on pleasing us that we have to trick them like this to get frank and fearless feedback.

I think it is something else. If you think about it, humans often write about correcting errors done by others. Refactoring code, fixing bugs and write code more efficient. I guess it triggers other paths in the model, if we write that someone else did it. It is not about pleasing but our constant desire to improve things.

If we tell it a rival LLM wrote the code it will be extra critical to tap into of its capitalist streak to crush the competition?

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

#593

Post by energy123 »

howinator wrote: post #339

I could be wrong, but I think this pricing is the first to admit that cost scales quadratically with number of tokens. It’s the first time I’ve seen nonlinear pricing from an LLM provider which implicitly mirrors the inference scaling laws I think we're all aware of.

Is this marginal pricing or if you go from 200,000 to 200,001 tokens your total costs double?

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

#594

Post by johnisgood »

fnordsensei wrote: post #569
PaulDavisThe1st wrote: post #561

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. 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.

For humans, remembering strengthens that memory, even if it is dead wrong.

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

#595

Post by mattmanser »

bamboozled wrote: post #530
nojs wrote: post #505

Earlier quoted context omitted.

In my experience jumping back like this is risky unless you explicitly tell it you made changes, otherwise they will get clobbered because it will update files based on the old context. Telling it to “re-read” xyz files before starting works though.

I always ask it to read the last 5 commits and anaylize and modified or staged files, works well...

Why do you find this better than just starting again at that point? I'm trying to understand the benefit of using this 'trick', without being able to try it as I'm away from my computer.

Couldn't you start a new context and achieve the same thing, without any of the risks of this approach?

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

#596

Post by friendzis »

onion2k wrote: post #348
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…

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.

Fitting the entire problem domain in their head is what engineers do.

Engineering is merely a search for optimal solution in this multidimensional space of problem domain(-s), requirements, limitations and optimization functions.

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

#597

Post by KptMarchewa »

FajitaNachos wrote: post #502
gdudeman wrote: post #83

A tip for those who both use Claude Code and are worried about token use (which you should be if you're stuffing 400k tokens into context even if you're on 20x Max): 1. Build context for the work you're doing. Put lots of your codebase into the context window. 2. Do work, but at each logical stopping point hit double escape to rewind to the context-filled checkpoint. You do not spend those tokens to rewind to that po…

What's the benefit to using claude code CLI directly over something like Cursor?

You don't have to deal with awfulness of vs code.

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

#598

Post by Lutger »

fnordsensei wrote: post #569
PaulDavisThe1st wrote: post #561

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. 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.

I've always find it interesting that once I take a wrong turn finding my way through the city and I'm not deliberate about remembering this was, in fact, a mistake, I am more prone to taking the same wrong turn again the next time.

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

#599

Post by croes »

jeremy_k wrote: post #224
croes wrote: post #155

Earlier quoted context omitted.

Do you only skim the results or do you audit them at some point to prevent security issues?

What kind of security issues are you thinking about? I'm generating UI components like Selects for certain data types or Charts of data.

Do these components have JS, do they have npm dependencies?

Since AI slopsquatting is a thing

https://en.wikipedia.org/wiki/Slopsquatting

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

#600

Post by vidarh »

adastra22 wrote: post #556
krainboltgreene wrote: post #537

Earlier quoted context omitted.

I have an entire life worth of context and I still remember projects I worked on 15 years ago.

Not with pixel perfect accuracy. You vaguely remember, although it may not feel like that because your brain fills in the details (hallucinates) as you recall. The comparisons are closer than you might think.

The comparison would be apt if the LLM was trained on your codebase.
Post reply on HN