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

81–90 of 706 posts

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

#81

Post by wongarsu »

TheDong wrote: post #25
jasonthorsness wrote: post #4

Earlier quoted context omitted.

What do you recommend doing instead? I've been using Claude Code a lot but am still pretty novice at the best practices around this.

Have the AI produce a plan that spans multiple files (like "01 create frontend.md", "02 create backend.md", "03 test frontend and backend running together.md"), and then create a fresh context for each step if it looks like re-using the same context is leading it to confusion. Also, commit frequently, and if the AI constantly goes down the wrong path ("I can't create X so I'll stub it out with Y, we'll fix it later")…

Changing the prompt and rerunning is something where Cursor still has a clear edge over Claude Code. It's such a powerful technique for keeping the context small because it keeps the context clear of back-and-forths and dead ends. I wish it was more universally supported

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

#82

Post by rootnod3 »

rootnod3 wrote: post #18

So, more tokens means better but at the same time more tokens means it distracts itself too much along the way. So at the same time it is an improvement but also potentially detrimental. How are those things beneficial in any capacity? What was said last week? Embrace AI or leave? All I see so far is: don't embrace and stay.

So, I see this got downvoted. Instead of just downvoting, I would prefer to have a counter-argument. Honestly. I am on the skeptic side of LLM, but would not mind being turned to the other side with some solid arguments.

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

#83

Post by gdudeman »

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 point.
  3. Tell Claude your developer finished XYZ, have it read it into context and give high level and low level feedback (Claude will find more problems with your developer's work than with yours).
If you want to have multiple chats running, use /resume and pull up the same thread. Hit double escape to the point where Claude has rich context, but has not started down a specific rabbit hole.

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

#84

Post by 77pt77 »

minimaxir wrote: post #17
mettamage wrote: post #9

Shame it's only the API. Would've loved to see it via the web interface on claude.ai itself.

Can you even fit 200+k tokens worth of context in the web interface? IMO Claude's API workbench is the worst of the three major providers.

Even if you can't, a conversation can easily get larger than that.

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

#85

Post by PickledJesus »

bachittle wrote: post #63
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).

As of now it's not integrated into Claude Code. "We’re also exploring how to bring long context to other Claude products". I'm sure they already know about this issue and are trying to think of solutions before letting users incur more costs on their monthly plans.

Seems to be for me, I came to look at HN because I saw it was the default in CC

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

#86

Post by brandall10 »

F7F7F7 wrote: post #50
TheDong wrote: post #25

Earlier quoted context omitted.

Have the AI produce a plan that spans multiple files (like "01 create frontend.md", "02 create backend.md", "03 test frontend and backend running together.md"), and then create a fresh context for each step if it looks like re-using the same context is leading it to confusion. Also, commit frequently, and if the AI constantly goes down the wrong path ("I can't create X so I'll stub it out with Y, we'll fix it later")…

Inventivatbly the files become a mess of their own. Changes and learnings from one part of the plan often dont result in adaptation to impacted plans down chain. In the end you have a mish mash of half implemented plans and now you’ve lost context too. Which leads to blowing tokens on trying to figure out what’s been implemented, what’s half baked, and what was completely ignored. Any links to anyone who’s built some…

My system is to create detailed feature files up to a few hundred lines in size that are immutable, and then have a status.md file (preferably kept to about 50 lines) that links to a current feature that is used as a way to keep track of the progress on that feature.

Additionally I have a Claude Code command with instructions referencing the status.md, how to select the next task, how to compact status.md, etc.

Every time I'm done with a unit of work from that feature - always triggered w/ ultrathink - I'll put up a PR and go through the motions of extra refactors/testing. For more complex PRs that require many extra commits to get prod ready I just let the sessions auto-compact.

After merging I'll clear the context and call the CC command to progress to the next unit of work.

This allows me to put up to around 4-5 meaningful PRs per feature if it's reasonably complex while keeping the context relatively tight. The current project I'm focused on is just over 16k LOC in swift (25k total w/ tests) and it seems to work pretty well - it rarely gets off track, does unnecessary refactors, destroys working features, etc.

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

#87

Post by rvnx »

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…

Thank you for the tips, do you know how to rollback latest changes ? Trying very hard to do it, but seems like Git is the only way ?

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

#88

Post by Etheryte »

Someone1234 wrote: post #56

Before this they supposedly had a longer context window than ChatGPT, but I have workloads that abuse the heck out of context windows (100-120K tokens). ChatGPT genuinely seems to have a 32K context window, in the sense that is legitimately remembers/can utilize everything within that window. Claude previously had "200K" context windows, but during testing it wouldn't even hit a full 32K before hitting a wall/it forg…

Strong agree, Claude is very quick to forget things like "don't do this", "never do this" or things it tried that were wrong. It will happily keep looping even in very short conversations, completely defeating the purpose of using it. It's easy to game the numbers, but it falls apart in the real world.

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

#89

Post by datadrivenangel »

cambaceres wrote: post #76
benterix wrote: post #29

Earlier quoted context omitted.

> it's not clear if the value actually exists here. Having spent a couple of weeks on Claude Code recently, I arrived to the conclusion that the net value for me from agentic AI is actually negative. I will give it another run in 6-8 months though.

For me it’s meant a huge increase in productivity, at least 3X. Since so many claim the opposite, I’m curious to what you do more specifically? I guess different roles/technologies benefit more from agents than others. I build full stack web applications in node/.net/react, more importantly (I think) is that I work on a small startup and manage 3 applications myself.

How do you structure your applications for maintainability?

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

#90

Post by SkyBelow »

anthonypasq wrote: post #69
alexchamberlain wrote: post #35

Earlier quoted context omitted.

I'm not sure how, and maybe some of the coding agents are doing this, but we need to teach the AI to use abstractions, rather than the whole code base for context. We as humans don't hold the whole codebase in our hear, and we shouldn't expect the AI to either.

the fact we cant keep the repo in our working memory is a flaw of our brains. i cant see how you could possibly make the argument that if you were somehow able to keep the entire codebase in your head that it would be a disadvantage.

Information tradeoff. Even if you could keep the entire code base in memory, if something else has to be left out of memory, then you have to consider the value of an abstraction verses whatever other information is lost. Abstractions also apply to the business domain and works the same.

You also have time tradeoffs. Like time to access memory and time to process that memory to achieve some outcome.

There is also quality. If you can keep the entire code base in memory but with some chance of confusion, while abstractions will allow less chance of confusion, then the tradeoff of abstractions might be worth it still.

Even if we assume a memory that has no limits, can access and process all information at constant speed, and no quality loss, there is still communication limitations to worry about. Energy consumption is yet another.

Post reply on HN