Claude Sonnet 4 now supports 1M tokens of context • Hacker News Board

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

#61

Post by mark_l_watson » Tue, Aug 12, 2025, 4:55 PM UTC

benterix wrote: post #29

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…

> 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.

I am sort of with you. I am down to asking Gemini Pro a couple of questions a day, use ChatGPT just a few times a week, and about once a week use gemini-cli (either a short free session, or a longer session where I provide my API key.)

That said I spend (waste?) an absurdly large amount of time each week experimenting with local models (sometimes practical applications, sometimes ‘research’).

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

#62

Post by wahnfrieden » Tue, Aug 12, 2025, 4:56 PM UTC

freedomben wrote: post #57

wahnfrieden wrote: post #52

Earlier quoted context omitted.

Did you try with using Opus exclusively?

Do you know if there's a way to force Claude code to do that exclusively? I've found a few env vars online but they don't seem to actually work

Peter Steinberger has been documenting his workflows and he relies exclusively on Opus at least until recently. (He also pays for a few Max 20x subscriptions at once to avoid rate limits.)

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

#63

Post by bachittle » Tue, Aug 12, 2025, 4:56 PM UTC

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.

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

#64

Post by fblp » Tue, Aug 12, 2025, 4:56 PM UTC

mettamage wrote: post #9

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

I assume this will mean that long chats continue to get the "prompt is too long" error?

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

#65

Post by hirako2000 » Tue, Aug 12, 2025, 4:56 PM UTC

sdesol wrote: post #42

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 I actually built this. I'm still not ready to say "use the tool yet" but you can learn more about it at https://github.com/gitsense/chat . The demo link is not up yet as I need to finalize an admin tool but you should be able to follow the npm instructions to play around with. The basic idea is, you should be able to load your entire repo or rep…

Not clear how it gets around what is, ultimately, a context limit.

I've been fiddling with some process too, would be good if you shared the how. The readme looks like yet another full fledged app.

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

#66

Post by CharlesW » Tue, Aug 12, 2025, 4:56 PM UTC

9wzYQbTYsAIc wrote: post #30

pupppet wrote: post #19

How does anyone send these models that much context without it tripping over itself? I can't get anywhere near that much before it starts losing track of instruction.

I’ve been having decent luck telling it to keep track of itself in a .plan file, not foolproof, of course, but it has some ability to “preserve context” between contexts. Right now I’m experimenting with using separate .plan files for tracking key instructions across domains like architecture and feature decisions.

> I’ve been having decent luck telling it to keep track of itself in a .plan file, not foolproof, of course, but it has some ability to “preserve context” between contexts.

This is the way. Not only have I had good luck with both a TASKS.md and TASKS-COMPLETE.md (for history), but I have an .llm/arch full of AI-assisted, for-LLM .md files (auth.md, data-access.md, etc.) that document architecture decisions made along the way. They're invaluable for effectively and efficiently crossing context chasms.

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

#67

Post by atonse » Tue, Aug 12, 2025, 4:56 PM UTC

freedomben wrote: post #57

wahnfrieden wrote: post #52

Earlier quoted context omitted.

Did you try with using Opus exclusively?

Do you know if there's a way to force Claude code to do that exclusively? I've found a few env vars online but they don't seem to actually work

You can type /config and then go to the setting to pick a model.

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

#68

Post by gdudeman » Tue, Aug 12, 2025, 4:56 PM UTC

freedomben wrote: post #57

wahnfrieden wrote: post #52

Earlier quoted context omitted.

Did you try with using Opus exclusively?

Do you know if there's a way to force Claude code to do that exclusively? I've found a few env vars online but they don't seem to actually work

Yes: type /model and then pick Opus 4.1.

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

#69

Post by anthonypasq » Tue, Aug 12, 2025, 4:56 PM UTC

alexchamberlain wrote: post #35

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'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.

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

#70

Post by artursapek » Tue, Aug 12, 2025, 4:57 PM UTC

irthomasthomas wrote: post #28

artursapek wrote: post #7

Eagerly waiting for them to do this with Opus

Imagine paying $20 a prompt?

If I can give it a detailed spec, walk away and do something else for 20 minutes, and come back to work that would have taken me 2 hours, then that's a steal.