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

461–470 of 706 posts

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

#461

Post by Aeolun »

9cb14c1ec0 wrote: post #424
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.

The more I use Claude Code, the more aware I become of its limitations. On the whole, it's a useful tool, but the bigger the codebase the less useful. I've noticed a big difference on its performance on projects with 20k lines of code versus 100k. (Yes, I know. A 100k line project is still very small in the big picture)

I think one of thr big issues with CC is that it’ll read the first occurence of something, and then think it’s found it. Never mind that there are 17 instances spread throughout the codebase.

I have to be really vigilant and tell it to search the codebase for any duplication, then resolve it, if I want it to keep going good at what it does.

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

#462

Post by boppo1 »

oceanplexian wrote: post #161
verall wrote: post #151

Earlier quoted context omitted.

> This week, I used it to write ESP32 firmware and a Linux kernel driver. I'm not meaning to be negative at all, but was this for a toy/hobby or for a commercial project? I find that LLMs do very well on small greenfield toy/hobby projects but basically fall over when brought into commercial projects that often have bespoke requirements and standards (i.e. has to cross compile on qcc, comply with autosar, in-house bu…

I work in FAANG, have been for over a decade. These tools are creating a huge amount of value, starting with Copilot but now with tools like Claude Code and Cursor. The people doing so don’t have a lot of time to comment about it on HN since we’re busy building things.

>creating a huge amount of value Do you write software, or work in accounting/finance/marketing?

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

#463

Post by Aeolun »

parineum wrote: post #176
wahnfrieden wrote: post #117

Earlier quoted context omitted.

The return for me is faster output of features, fixes, and polish for my products which increases revenue above the cost of the tool. Did you need to ask this?

Yes, I did. Not everybody has their own product that might benefit from a $200 subscription. Most of us work for someone else and, unless that person is paying for the subscription, the _value_ it adds is irrelevant unless it results in better compensation. Furthermore, the advice was given to upgrade to a $200 subscription from the $20 subscription. The difference in value that might translate into income between th…

If you have the money, and like coding your own stuff, the $200 is worth it. If you just code for the enterprise? Not so much.

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

#464

Post by ramshanker »

brulard wrote: post #412
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…

For me it was like this for like a year (using Cline + Sonnet & Gemini) until Claude Code came out and until I learned how to keep context real clean. The key breakthrough was treating AI as an architect/implementer rather than a code generator. Most recently I ask first CC to create a design document for what we are going to do. He has instructions to look into the relevant parts of the code and docs to reference th…

Same here. A small variation: I explicitly use website to manage what context it gets to see.

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

#465

Post by Aeolun »

psyclobe wrote: post #455

Isn’t Opus better? Whenever I run out of Opus tokens and get kicked down to Sonnet it’s quite a shock sometimes. But man I’m at the perfect stage in my career for these tools. I know a lot, I understand a lot, I have a lot of great ideas-but I’m getting kinda tired of hammering out code all day long. Now with Claude I am just busting ass executing in all these ideas and tests and fixes-never going back!

Haha, I think I recognize that. I’m just worried my actual skills will athrophy while I use Claude Code like I’m a manager on steroids.

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

#466

Post by dang »

bigmadshoe wrote: post #37
aliljet wrote: post #27

Earlier quoted context omitted.

How do you know that?

https://research.trychroma.com/context-rot

Discussed here:

Context Rot: How increasing input tokens impacts LLM performance - https://news.ycombinator.com/item?id=44564248 - July 2025 (59 comments)

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

#467

Post by neucoas »

lpa22 wrote: post #423

One of the most helpful usages of CC so far is when I simply ask: "Are there any bugs in the current diff" It analyzes the changes very thoroughly, often finds very subtle bugs that would cost hours of time/deployments down the line, and points out a bunch of things to think through for correctness.

I am trying this tomorrow

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

#469

Post by Aeolun »

simianwords wrote: post #184
eldenring wrote: post #179

Earlier quoted context omitted.

Serving a model efficiently at 1M context is difficult and could be much more expensive/numerically tricky. I'm guessing they were working on serving it properly, since its the same "model" in scores and such.

Thanks - still not clear what they did really. Some inference time hacks?

They already had 0.5M context window on the enteprise version.

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

#470

Post by WolfeReader »

whatever1 wrote: post #331
senko wrote: post #283

Earlier quoted context omitted.

> 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... But .. that's not the AI's fault. If people submit any PRs (including AI-generated or AI-assisted) without completely understanding them, I'd treat is as serious breach of professional conduct and (gently, for first-timers) stress tha…

If you have to review what the LLM wrote then there is no productivity gain. Leadership asks for vibe coding

I've seen AI create incorrect solutions and deceptive variable names. Reviewing the code is absolutely necessary.
Post reply on HN