Wish it was on the web app as well!
Claude Sonnet 4 now supports 1M tokens of context
501–510 of 706 posts
Re: Claude Sonnet 4 now supports 1M tokens of context
#502A 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?
Re: Claude Sonnet 4 now supports 1M tokens of context
#503Earlier quoted context omitted.
If you have to review what the LLM wrote then there is no productivity gain. Leadership asks for vibe coding
I suggest you upgrade your code review skill. I find it vastly quicker in most cases to review code than write it in the first place.
Anyone can skim code and type “looks good to me”.
Re: Claude Sonnet 4 now supports 1M tokens of context
#504Earlier quoted context omitted.
Here's a paper from MIT that covers how this could be resolved in an interesting fashion: https://hanlab.mit.edu/blog/streamingllm The AI field is reusing existing CS concepts for AI that we never had hardware for, and now these people are learning how applied Software Engineering can make their theoretical models more efficient. It's kind of funny, I've seen this in tech over and over. People discover new thing, the…
The fact that this is happening is where the tremendous opportunity to make money as an experienced Software Engineer currently lies. For instance, a year or two ago, the AI people discovered "cache". Imagine how many millions the people who implemented it earned for that one.
I've been thinking the same, and its things that you don't need some crazy ML degree to know how to do... A lot of the algorithms are known... for a while now... Milk it while you can.
Re: Claude Sonnet 4 now supports 1M tokens of context
#505A 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…
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.
Re: Claude Sonnet 4 now supports 1M tokens of context
#506Claude is down.
EDIT: for the moment... it supports 0 tokens of context xD
Re: Claude Sonnet 4 now supports 1M tokens of context
#507Currently the quality seems to degrade long before the context limit is reached, as the context becomes “polluted”.
Should we expect the higher limit to also increase the practical context size proportionally?
Re: Claude Sonnet 4 now supports 1M tokens of context
#508This 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…
> The context is in the repo
Agreed but that’s a bit different from “the context is the repo”
It’s been my experience that usually just picking a couple files out to add to the context is enough - Claude seems capable of following imports and finding what it needs, in most cases.
I’m sure it depends on the task, and the structure of the codebase.
Re: Claude Sonnet 4 now supports 1M tokens of context
#509I just want a better way to invalidate old context... It's great that I can fit more context, but the main challenge is claude getting sidetracked with 10 invalid grep calls, pytest dumping a 10k token stack trace etc.... And yes the ability to go back in time via esc+esc is great but I want claude to read the error stack learn from it and purge from its context or at least let me lobotomize ot selectively... Learnin…
Vscode recently rolled out checkpoints where you can go back to a previous state of the conversation. But it's still not enough.
We honestly need to be able to see exactly what's in the context and be able to manually edit it.
Re: Claude Sonnet 4 now supports 1M tokens of context
#510Earlier quoted context omitted.
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.
I've found it better to use antonyms than negations most situations.
Same here. Always tell them the way you want it done.
For example:
Instead of "don't modify the tests"
It should be: analyze the test output and fix the bug in the source code. The test is built correctly.
Not the best but you get the idea.
The one problem with this is if you don't know how to do something properly. Like if you're just writing in your prompt "generate 90% test coverage" , you give it a lot more leeway to do whatever it wants.
And that's how you end up with the source code being modified to fit the test vice versa