Claude Sonnet 4 now supports 1M tokens of context

Post by wahnfrieden » Wed, Aug 13, 2025, 10:03 AM UTC

OutOfHere wrote: post #102

thimabi wrote: post #99

Oh, well, ChatGPT is being left in the dust… When done correctly, having one million tokens of context window is amazing for all sorts of tasks: understanding large codebases, summarizing books, finding information on many documents, etc. Existing RAG solutions fill a void up to a point, but they lack the precision that large context windows offer. I’m excited for this release and hope to see it soon on the UI as wel…

Fwiw, OpenAI does have a decent active API model family of GPT-4.1 with a 1M context. But yes, the context of the GPT-5 models is terrible in comparison, and it's altogether atrocious for the GPT-5-Chat model. The biggest issue in ChatGPT right now is a very inconsistent experience, presumably due to smaller models getting used even for paid users with complex questions.

Post by CPLX » Wed, Aug 13, 2025, 10:09 AM UTC

ivape wrote: post #591

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. I does, it’s just happening at lightning speed.

Post by wahnfrieden » Wed, Aug 13, 2025, 10:18 AM UTC

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…

Post by k9294 » Wed, Aug 13, 2025, 10:24 AM UTC

terminalshort wrote: post #494

aledalgrande wrote: post #486

I hope that they are going to put something in Claude Code to display if you're entering the expensive window. Sometime I just keep the conversation going. I wouldn't want that to burn my Max credits 2x faster.

Yeah, that 1 MM tokens is a $15 (IIRC) API call. That's gonna add up quick! My favorite hypothetical AI failure scenario is that LLM agents eventually achieve human level general intelligence, but have to burn so many tokens to do it that they actually become more expensive than a human.

Post by Ianjit » Wed, Aug 13, 2025, 10:45 AM UTC

wiremine wrote: post #130

cambaceres wrote: post #76

Earlier quoted context omitted.

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.

> 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. > For me it’s meant a huge increase in productivity, at least 3X. How do we reconcile these two comments? I think that's a core question of the industry right now. My take, as a CTO, is this: we're giving people new tools, and very little training on the techniques that…