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

101–110 of 706 posts

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

#101

Post by revskill »

benterix wrote: post #29
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…

> 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.

Truth. To some extend, the agent doesn't know what it's doing at all, it lacks real brain, maybe we should just treat them as the hard worker.

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

#102

Post by OutOfHere »

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.

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

#103

Post by datadrivenangel »

irthomasthomas wrote: post #28
artursapek wrote: post #7

Eagerly waiting for them to do this with Opus

Imagine paying $20 a prompt?

Depending on how many prompts per hour you're looking at, that's probably same order of magnitude as expensive SAAS. A fancy CRM seat can be ~$2000 per month (or more), which assuming 50 hours per week x 4 weeks per month is $10 per hour ($2000/200 hours). A lot of money, but if it makes your sales people more productive, it's a good investment. Assuming that you're paying your sales people say 240K per year, ($20,000 per month), then the SAAS cost is 10% of their salary.

This explains DataDog pricing. Maybe it will give a future look at AI pricing.

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

#104

Post by rs186 »

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.

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 locating the correct file to edit is non trivial for a new (human) developer.

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

#106

Post by firasd »

A big problem with the chat apps (ChatGPT; Claude.ai) is the weird context window hijinks. Especially ChatGPT does wild stuff.. sudden truncation; summarization; reinjecting 'ghost snippets' etc

I was thinking this should be up to the user (do you want to continue this conversation with context rolling out of the window or start a new chat) but now I realized that this is inevitable given the way pricing tiers and limited computation works. Like the only way to have full context is use developer tools like Google AI Studio or use a chat app that wraps the API

With a custom chat app that wraps the API you can even inject the current timestamp into each message and just ask the LLM btw every 10 minutes just make a new row in a markdown table that summarizes every 10 min chunk

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

#107

Post by handfuloflight »

sdesol wrote: post #42
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 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?

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

#109

Post by sebzim4500 »

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.

I think it's the right approach, the cost of running these things as coding assistants is negligable compared to the benefit of even a slight model improvement.

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

#110

Post by photon_lines »

sdesol wrote: post #72
alexchamberlain wrote: post #35

Earlier quoted context omitted.

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.

LLMs (current implementation) are probabilistic so it really needs the actual code to predict the most likely next tokens. Now loading the whole code base can be a problem in itself, since other files may negatively affect the next token.

Sorry -- I keep seeing this being used but I'm not entirely sure how it differs from most of human thinking. Most human 'reasoning' is probabilistic as well and we rely on 'associative' networks to ingest information. In a similar manner - LLMs use association as well -- and not only that, but they are capable of figuring out patterns based on examples (just like humans are) -- read this paper for context: https://arxiv.org/pdf/2005.14165. In other words, they are capable of grokking patterns from simple data (just like humans are). I've given various LLMs my requirements and they produced working solutions for me by simply 1) including all of the requirements in my prompt and 2) asking them to think through and 'reason' through their suggestions and the products have always been superior to what most humans have produced. The 'LLMs are probabilistic predictors' comments though keep appearing on threads and I'm not quite sure I understand them -- yes, LLMs don't have 'human context' i.e. data needed to understand human beings since they have not directly been fed in human experiences, but for the most part -- LLMs are not simple 'statistical predictors' as everyone brands them to be. You can see a thorough write-up I did of what GPT is / was here if you're interested: https://photonlines.substack.com/p/intuitive-and-visual-guid...
Post reply on HN