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

621–630 of 706 posts

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

#621

Post by alvis »

ants_everywhere wrote: post #322
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…

> 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…

Everything in context hurts focus. It's like some people suffering from hyperthymesia. They are easily get distracted when the recall something

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

#623

Post by i_have_an_idea »

wahnfrieden wrote: post #614
i_have_an_idea wrote: post #448

While this is cool, can anything be done about the speed of inference? At least for my use, 200K context is fine, but I’d like to see a lot faster task completion. I feel like more people would be OK with the smaller context if the agent acts quickly (vs waiting 2-3 mins per prompt).

Meanwhile the key is to become proficient at using worktrees to parallelize agents instead of working serially with them

Sounds nice, in theory, but in practice I want to iterate on one, perhaps, two tasks at a time, and keep a good understanding of what the agent is doing, so that I can prevent it from going off the rails, making bad decisions and then building on them even further.

Worktrees and parallel agents do nothing to help me with that. It's just additional cognitive load.

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

#624

Post by hahn-kev »

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.

We use Code Rabbit for this in our open source project.

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

#625

Post by daveydave »

seperman wrote: post #235
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…

Very interesting. Why does Claude find more problems if we mention the code is written by another developer?

I would guess the training data (conversational as opposed to coding specific solutions) is weighted towards people finding errors in others work, more than people discussing errors in their own. If you knew there was an error in your thinking, you probably wouldn't think that way.

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

#626

Post by onion2k »

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.

If you're completely new to the problem then ... yes, it does.

You're assuming that you're working on a project that you've spent time on and learned the domain for, and then you're comparing that to an LLM being prompted to look at a codebase with the context of the files. Those things are not the same though.

A closer analogy to LLMs would be prompting it for questions when it has access (either through MCP or training) to the project's git history, documentation, notes, issue tracker, etc. When that sort of thing is commonplace, and LLMs have the context window size to take advantage of all that information, I suspect we'll be surprised how good they are even given the results we get today.

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

#627

Post by ehnto »

onion2k wrote: post #626
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…

My ability to break a problem down does not start from listing the files out and reading a few. If you're completely new to the problem then ... yes, it does. You're assuming that you're working on a project that you've spent time on and learned the domain for, and then you're comparing that to an LLM being prompted to look at a codebase with the context of the files. Those things are not the same though. A closer an…

> If you're completely new to the problem then ... yes, it does.

Of course, because I am not new to the problem, whereas an LLM is new to it every new prompt. I am not really trying to find a fair comparison because I believe humans have an unfair advantage in this instance, and am trying to make that point, rather than compare like for like abilities. I think we'll find even with all the context clues from MCPs and history etc. they might still fail to have the insight to recall the right data into the context, but that's just a feeling I have from working with Claude Code for a while. Because I instruct it to do those things, like look through git log, check the documentation etc, and it sometimes finds a path through to an insight but it's just as likely to get lost.

I alluded to it somewhere else but my experience with massive context windows so far has just been that it distracts the LLM. We are usually guiding it down a path with each new prompt and have a specific subset of information to give it, and so pumping the context full of unrelated code at the start seems to derail it from that path. That's anecdotal, though I encourage you to try messing around with it.

As always, there's a good chance I will eat my hat some day.

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

#628

Post by khalic »

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…

This is a major issue with LLMs altogether, it probably has to do with the transformer architecture. We need another breakthrough in the field for this to become reality.

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

#629

Post by ants_everywhere »

brulard wrote: post #473
ants_everywhere wrote: post #355

Earlier quoted context omitted.

I exhaust the 1 million context windows on multiple models multiple times per day. I haven't used the Llama 4 10 million context window so I don't know how it performs in practice compared to the major non-open-source offerings that have smaller context windows. But there is an induced demand effect where as the context window increases it opens up more possibilities, and those possibilities can get bottlenecked on r…

I think you misunderstand how context in current LLMs works. To get the best results you have to be very careful to provide what is needed for immediate task progression, and postpone context thats needed later in the process. If you give all the context at once, you will likely get quite degraded output quality. Thats like if you want to give a junior developer his first task, you likely won't teach him every corner…

> I think you misunderstand how context in current LLMs works.

Thanks but I don't and I'm not sure why you're jumping to this conclusion.

EDIT: Oh I think you're talking about the last bit of the comment! If you read the one before I say that feeding it the entire repo isn't a great idea. But great idea or not, people want to do it, and it illustrates that as context window increases it creates demand for even larger context windows.

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

#630

Post by cubefox »

tehlike wrote: post #8
tankenmate wrote: post #3

This is definitely good to have this as an option but at the same time having more context reduces the quality of the output because it's easier for the LLM to get "distracted". So, I wonder what will happen to the quality of code produced by tools like Claude Code if users don't properly understand the trade off being made (if they leave it in auto mode of coding right up to the auto compact).

Some reference: https://simonwillison.net/2025/Jun/29/how-to-fix-your-contex... https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-ho...

It would be interesting how this manifests in SSM/Mamba models. The way they handle their context window is different from Transformers, as the former don't use the Attention mechanism. Mamba is better at context window scaling than transformers but worse at explicit recall. Though that doesn't tell us how susceptible they are to context distractions.
Post reply on HN