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

111–120 of 706 posts

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

#111

Post by evantbyrne »

cambaceres wrote: post #76
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.

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.

The problem with these discussions is that almost nobody outside of the agency/contracting world seems to track their time. Self-reported data is already sketchy enough without layering on the issue of relying on distant memory of fine details.

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

#112

Post by GenerocUsername »

rs186 wrote: post #104
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.

3X if not 10X if you are starting a new project with Next.js, React, Tailwind CSS for a fullstack website development, that solves an everyday problem. Yeah I just witnessed that yesterday when creating a toy project. For my company's codebase, where we use internal tools and proprietary technology, solving a problem that does not exist outside the specific domain, on a codebase of over 1000 files? No way. Even locat…

Your first week of AI usage should be crawling your codebase and generating context.md docs that can then be fed back into future prompts so that AI understands your project space, packages, apis, and code philosophy.

I guarantee your internal tools are not revolutionary, they are just unrepresented in the ML model out of the box

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

#113

Post by parineum »

artursapek wrote: post #75
freedomben wrote: post #57

Earlier quoted context omitted.

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 "force" it by just paying them $200 (which is nothing compared to the value)

Value is irrelevant. What's the return on investment you get from spending $200?

Collecting value doesn't really get you anywhere if nobody is compensating you for it. Unless someone is going to either pay for it for you or give you $200/mo post-tax dollars, it's costing you money.

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

#114

Post by andrepd »

cambaceres wrote: post #76
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.

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.

Self-reports are notoriously overexcited, real results are, let's say, not so stellar.

https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...

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

#115

Post by pupppet »

olddustytrail wrote: post #98
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 think it's key to not give it contradictory instructions, which is an easy mistake to make if you forget where you started. As an example, I know of an instance where the LLM claimed it had tried a test on its laptop. This obviously isn't true so the user argued with it. But they'd originally told it that it was a Senior Software Engineer so playing that role, saying you tested locally is fine. As soon as you start…

The problem I often have is I may have instruction like-

General instruction: - Do "ABC"

If condition == whatever: - Do "XYZ" instead

I have a hard time making the AI obey the instances I wish to override my own instruction and without having full control of the input context, I can't just modify my 'General Instruction' on a case by case basis to simply avoid having to contradict myself.

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

#116

Post by throwaway314155 »

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.

/compact in Claude Code is effectively this.

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

#117

Post by wahnfrieden »

parineum wrote: post #113
artursapek wrote: post #75

Earlier quoted context omitted.

You can "force" it by just paying them $200 (which is nothing compared to the value)

Value is irrelevant. What's the return on investment you get from spending $200? Collecting value doesn't really get you anywhere if nobody is compensating you for it. Unless someone is going to either pay for it for you or give you $200/mo post-tax dollars, it's costing you money.

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?

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

#118

Post by sdesol »

handfuloflight wrote: post #107
sdesol wrote: post #42

Earlier quoted context omitted.

> 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…

Doesn't Claude Code do all of this automatically?

I haven't looked at Claud Code, so I don't know if they have analyzers or not that understands how to extract any type of data other than specific coding data that it is trained on. Based on the runtime for some tasks, I would not be surprised if it is going through all the files and asking "is this relevant"

My tool is mainly targeted at massive code bases and enterprise as I still believe the most efficient way to build accurate context is by domain experts.

Right now, I would say 95% of my code is AI generated (98% human architectured) and I am spending about $2 a day on LLM costs and the code generation part usually never runs more than 30 seconds for most tasks.

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

#120

Post by nicce »

GenerocUsername wrote: post #112
rs186 wrote: post #104

Earlier quoted context omitted.

3X if not 10X if you are starting a new project with Next.js, React, Tailwind CSS for a fullstack website development, that solves an everyday problem. Yeah I just witnessed that yesterday when creating a toy project. For my company's codebase, where we use internal tools and proprietary technology, solving a problem that does not exist outside the specific domain, on a codebase of over 1000 files? No way. Even locat…

Your first week of AI usage should be crawling your codebase and generating context.md docs that can then be fed back into future prompts so that AI understands your project space, packages, apis, and code philosophy. I guarantee your internal tools are not revolutionary, they are just unrepresented in the ML model out of the box

Even then, are you even allowed to use AI in such codebase. Is some part of the code "bought", e.g. commercial compiler generated with specific license? Is pinky promise from LLM provider enough?
Post reply on HN