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

191–200 of 706 posts

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

#191

Post by sdesol »

pacoWebConsult wrote: post #171
sdesol wrote: post #159

Earlier quoted context omitted.

Looking at the code, it does have some sort of automatic discovery. I also don't know how scalable Claude Code is. I've spent over a decade thinking about code search, so I know what the limitations are for enterprise code. One of the neat tricks that I've developed is, I would load all my backend code for my search component and then I would ask the LLM to trace a query and create a context bundle for only the files…

FWIW Claude code conversations are also durable. You can resume any past conversation in your project. They're stored as jsonl files within your `$HOME/.claude` directory. This retains the actual context (including your prompts, assistant responses, tool usages, etc) from that conversation, not just the files you're affecting as context.

Thanks for the info. I actually want to make it easy for people to review aider, plandex, claude code, etc. conversations so I will probably look at importing them.

My goal isn't to replace the other tools, but to make them work smarter and more efficiently. I also think we will in a year or two, start measuring performance based on how developers interact with LLMs (so management will want to see the conversations). Instead of looking at code generated, the question is going to be, if this person is let go, what is the impact based on how they are contributing via their conversations.

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

#193

Post by AtNightWeCode »

lherron wrote: post #53

Wow, I thought they would feel some pricing pressure from GPT5 API costs, but they are doubling down on their API being more expensive than everyone else.

GPT5 API uses more tokens for answers of the same quality as previous versions. Fell into that trap myself. I use both Claude and OpenAI right now. Will probably drop OpenAI since they are obviously not to be trusted considering the way they do changes.

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

#194

Post by spiderice »

EcommerceFlow wrote: post #26
alvis wrote: post #23

Context window after certain size doesn’t bring in much benefit but higher bill. If it still keeps forgetting instructions it would be just much easier to be ended up with long messages with higher context consumption and hence the bill I’d rather having an option to limit the context size

It does if you're working with bigger codebases. I've found copy/pasting my entire codebase + adding a works significantly better than cursor.

How does one even copy their entire codebase? Are you saying you attach all the files? Or you use some script to copy all the text to your clipboard? Or something else?

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

#195

Post by bcrosby95 »

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.

My current guess is it's how the programmer solves problems in their head. This isn't something we talk about much.

People seem to find LLMs do well with well-spec'd features. But for me, creating a good spec doesn't take any less time than creating the code. The problem for me is the translation layer that turns the model in my head into something more concrete. As such, creating a spec for the LLM doesn't save me any time over writing the code myself.

So if it's a one shot with a vague spec and that works that's cool. But if it's well spec'd to the point the LLM won't fuck it up then I may as well write it myself.

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

#196

Post by nomel »

anonz4FWNqnX wrote: post #47
aliljet wrote: post #27

Earlier quoted context omitted.

How do you know that?

I've had similar experiences. I've gone back and forth between running models locally and using the commercial models. The local models can be incredibly useful (gemma, qwen), but they need more patience and work to get them to work. One advantage to running locally[1] is that you can set the context length manually and see how well the llm uses it. I don't have an exact experience to relay, but it's not unusual for…

A good example of this was the first Gemini model that allowed 1 million tokens, but would lose track of the conversation after a couple paragraphs.

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

#197

Post by sdesol »

handfuloflight wrote: post #167
sdesol wrote: post #159

Earlier quoted context omitted.

Looking at the code, it does have some sort of automatic discovery. I also don't know how scalable Claude Code is. I've spent over a decade thinking about code search, so I know what the limitations are for enterprise code. One of the neat tricks that I've developed is, I would load all my backend code for my search component and then I would ask the LLM to trace a query and create a context bundle for only the files…

Excellent, I look forward to trying it out, at minimum to wean off dependency to Claude Code and it's likely current state of overspending on context. I agree with looking at conversations as durable assets.

> current state of overspending on context

The thing that is killing me when I hear about Claude Code and other agent tools is the amount of energy they must be using. People say they let the task run for an hour and I can't help but to think how much energy is being used and if Claude Code is being upfront with how much things will actually cost in the future.

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

#198

Post by ghjv »

markb139 wrote: post #175

I’ve tried 2 AI tools recently. Neither could produce the correct code to calculate the CPU temperature on a Raspberry Pi RP2040. The code worked, looked ok and even produced reasonable looking results - until I put a finger on the chip and thus raised the temp. The calculated temperature went down. As an aside the free version of chatGPT didn’t know about anything newer than 2023 so couldn’t tell me about the RP2350

wouldn't your finger have acted as a heat sink, lowering the temp? sounds like the program may have worked correctly. could be worth trying again with a hot enough piece of metal instead of your finger

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

#199

Post by mstkllah »

dillydogg wrote: post #138
acedTrex wrote: post #121

Earlier quoted context omitted.

I have yet to get it to generate code past 10ish lines that I am willing to accept. I read stuff like this and wonder how low yall's standards are, or if you are working on projects that just do not matter in any real world sense.

Whenever I read comments from the people singing their praises of the technology, it's hard not to think of the study that found AI tools made developers slower in early 2025. >When developers are allowed to use AI tools, they take 19% longer to complete issues—a significant slowdown that goes against developer beliefs and expert forecasts. This gap between perception and reality is striking: developers expected AI t…

Ah, the very extensive study with 16 developers. Bulletproof results.

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

#200

Post by wahnfrieden »

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 are employed you should petition your employer for tools you want. Maybe you can use it to take the day off earlier or spend more time socializing. Or to get a promotion or performance bonus. Hopefully not just to meet rising productivity expectations without being handed the tools needed to achieve that. Having full-time access to these tools can also improve your own skills in using them, to profit from in a later career move or from contributing toward your own ends.
Post reply on HN