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

371–380 of 706 posts

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

#371

Post by gdudeman »

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?

Claude is very agreeable and is an eager helper.

It gives you the benefit of the doubt if you're coding.

It also gives you the benefit of the doubt if you're looking for feedback on your developers work. If you give it a hint of distrust "my developer says they completed this, can you check and make sure, give them feedback....?" Claude will look out for you.

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

#372

Post by gdudeman »

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…

I'll note this saves a lot of wait time as well! No sitting there while a new Claude builds context from scratch.

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

#373

Post by phyzix5761 »

What I've found with LLMs is they're basically a better version of Google Search. If I need a quick "How do I do..." or if I need to find a quick answer to something its way more useful than Google and the fact that I can ask follow up questions is amazing. But for any serious deep work it has a long way to go.

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

#375

Post by urbandw311er »

flowerthoughts wrote: post #328
not_that_d wrote: post #304

My experience with the current tools so far: 1. It helps to get me going with new languages, frameworks, utilities or full green field stuff. After that I expend a lot of time parsing the code to understand what it wrote that I kind of "trust" it because it is too tedious but "it works". 2. When working with languages or frameworks that I know, I find it makes me unproductive, the amount of time I spend writing a goo…

I predict microservices will get a huge push forward. The question then becomes if we're good enough at saying "Claude, this is too big now, you have to split it in two services" or not. If LLMs maintain the code, the API boundary definitions/documentation and orchestration, it might be manageable.

Why not just cleanly separated code in a single execution environment? No need to actually run the services in separate execution environments just for the sake of an LLM being able to parse it, that’s crazy! You can just give it the files or folders it needs for the particular services within the project.

Obviously there’s still other reasons to create micro services if you wish, but this does not need to be another reason.

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

#376

Post by mnky9800n »

not_that_d wrote: post #304

My experience with the current tools so far: 1. It helps to get me going with new languages, frameworks, utilities or full green field stuff. After that I expend a lot of time parsing the code to understand what it wrote that I kind of "trust" it because it is too tedious but "it works". 2. When working with languages or frameworks that I know, I find it makes me unproductive, the amount of time I spend writing a goo…

Yea that’s right. It’s kind of annoying how useful it is for hobby projects and it is suddenly useless on anything at work. Haha. I love Claude code for some stuff (like generating a notebook to analyse some data). But it really just disconnects you from the problem you are solving without you going through everything it writes. And I’m really bullish on ai coding tools haha, for example:

https://open.substack.com/pub/mnky9800n/p/coding-agents-prov...

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

#377

Post by i_have_an_idea »

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…

This sounds like the programmer equivalent of astrology.

> Build context for the work you're doing. Put lots of your codebase into the context window.

If you don’t say that, what do you think happens as the agent works on your codebase.

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

#378

Post by qingcharles »

ericmcer wrote: post #275
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.

Agreed, daily Cursor user. Just got out of a 15m huddle with someone trying to understand what they were doing in a PR before they admitted Claude generated everything and it worked but they weren't sure why... Ended up ripping about 200 LoC out because what Claude "fixed" wasn't even broken. So never let it generate code, but the autocomplete is absolutely killer. If you understand how to code in 2+ languages you ca…

The other day I caught it changing the grammar and spelling in a bunch of static strings in a totally different part of a project, for no sane reason.

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

#379

Post by meander_water »

I like to spend a lot of time in "Ask" mode in Cursor. I guess the equivalent in Claude code is "plan" mode.

Where I have minimal knowledge about the framework or language, I ask a lot of questions about how the implementation would work, what the tradeoffs are etc. This is to minimize any misunderstanding between me and the tool. Then I ask it to write the implementation plan, and execute it one by one.

Cursor lets you have multiple tabs open so I'll have a Ask mode and Agent mode running in parallel.

This is a lot slower, and if it was a language/framework I'm familiar with I'm more likely to execute the plan myself.

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

#380

Post by insane_dreamer »

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…

I usually tell CC (or opencode, which I've been using recently) to look up the files and find the relevant code. So I'm not attaching a huge number of files to the context. But I don't actually know whether this saves tokens or not.
Post reply on HN