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

531–540 of 706 posts

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

#531

Post by lfowles »

Gigachad wrote: post #436
gwd wrote: post #357

Earlier quoted context omitted.

> How do we reconcile these two comments? I think that's a core question of the industry right now. The question is, for those people who feel like things are going faster, what's the actual velocity? A month ago I showed it a basic query of one resource I'd rewritten to use a "query builder" API. Then I showed it the "legacy" query of another resource, and asked it to do something similar. It managed to get very clo…

Pretty much. We are in an era of vibe efficiency. If programmers really did get 3x faster. Why has software not improved any faster than it always has been.

Probably because we're attempting to make 3x more products

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

#532

Post by ehnto »

onion2k wrote: post #348
ants_everywhere wrote: post #322

Earlier quoted context omitted.

> I really desperately need LLMs to maintain extremely effective context The context is in the repo. An LLM will never have the context you need to solve all problems. Large enough repos don't fit on a single machine. There's a tradeoff just like in humans where getting a specific task done requires removing distractions. A context window that contains everything makes focus harder. For a long time context windows we…

Large enough repos don't fit on a single machine. I don't believe any human can understand a problem if they need to fit the entire problem blem domain in their head, and the scope of a domain that doesn't fit on a computer. You have to break it down into a manageable amount of information to tackle it in chunks. If a person can do that, so can an LLM prompted to do that by a person.

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 project at all times, and a deep understanding of the whole project stored, and I can recall that when required, this is not true of an LLM at any point.

We know this is a limitation and it's why we have various tools attempting to approximate memory and augment training on the fly, but they are approximations and they are in my opinion, not even close to real human memory and depth of understanding for data it was not trained on.

Even for mutations of scenarios it was trained on, which code is a great example of that. It is trained on billions of lines of code, yet still fails to understand my codebase intuitively. I have definitely not read billions of lines of code.

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

#533

Post by whalesalad »

simon_rider wrote: post #522

feels like we just traded "not enough context" for "too much noise." The million-token window is cool for marketing, but until retrieval and summarization get way better, it’s like dumping the entire repo on a junior dev’s desk and saying "figure it out." They’ll spend half their time paging through irrelevant crap, and the other half hallucinating connections. Bigger context is only a net win if the model can filter…

I can't tell you the number of times I had almost reached utopia only to hit compaction limits. Post-compaction I am usually dead in the water and the spiraling or repetition begins. Claude has a hard time compacting/remembering/flaggign a-ha moments from the session. Stuff that is important in the context of the task, but not appropriate for CLAUDE.md for instance. I have been thinking for months that if the context window was 2-3x larger, I would be unstoppable. So happy for this change, and excited to test it this week.

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

#534

Post by ehnto »

ehnto wrote: post #532
onion2k wrote: post #348

Earlier quoted context omitted.

Large enough repos don't fit on a single machine. I don't believe any human can understand a problem if they need to fit the entire problem blem domain in their head, and the scope of a domain that doesn't fit on a computer. You have to break it down into a manageable amount of information to tackle it in chunks. If a person can do that, so can an LLM prompted to do that by a person.

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…

Additionally, the more information you put into the context the more confused the LLM will get, if you did dump the whole codebase into the context it would not suddenly understand the whole thing. It is still an LLM, all you have done is polluted the context with a million lines of unrelated code, and some lines of related code, which it will struggle to find in the noise (in my experience of much smaller experiments)

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

#535

Post by spaceywilly »

ramshanker wrote: post #514
brulard wrote: post #476

Earlier quoted context omitted.

What do you mean by website? An HTML doc?

I mean the website of AI providers. chatgpt.com , gemini.google.com , claude.ai and so on.

I’ve had more success this way as well. I will use the model via web ui, paste in the relevant code, and ask it to implement something. It spits out the code, I copy it back into the ide, and build. I tried Claude Code but I find it goes off the rails too easily. I like the chat through the UI because it explains what it’s doing like a senior engineer would

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

#536

Post by nojs »

brulard wrote: post #482
imiric wrote: post #422

Earlier quoted context omitted.

This is a common workflow that most advanced users are familiar with. Yet even following it to a T, and being really careful with how you manage context, the LLM will still hallucinate, generate non-working code, steer you into wrong directions and dead ends, and just waste your time in most scenarios. There's no magical workflow or workaround for avoiding this. These issues are inherent to the technology, and have b…

> These issues are inherent to the technology That's simply false. Even if LLMs don't produce correct and valid code on first shot 100% times of the cases, if you use an agent, it's simply a matter of iterations. I have claude code connected to Playwright, context7 for docs and to Playwright, so it can iterate by itself if there are syntax errors, runtime errors or problems with the data on the backend side. Currentl…

Could you explain your exact playwright setup in more detail? I’ve found that claude really struggles to end-to-end test complex features that require browser use. It gets stuck for several minutes trying to find the right button to click for example.

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

#537

Post by krainboltgreene »

onion2k wrote: post #348
ants_everywhere wrote: post #322

Earlier quoted context omitted.

> I really desperately need LLMs to maintain extremely effective context The context is in the repo. An LLM will never have the context you need to solve all problems. Large enough repos don't fit on a single machine. There's a tradeoff just like in humans where getting a specific task done requires removing distractions. A context window that contains everything makes focus harder. For a long time context windows we…

Large enough repos don't fit on a single machine. I don't believe any human can understand a problem if they need to fit the entire problem blem domain in their head, and the scope of a domain that doesn't fit on a computer. You have to break it down into a manageable amount of information to tackle it in chunks. If a person can do that, so can an LLM prompted to do that by a person.

I have an entire life worth of context and I still remember projects I worked on 15 years ago.

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

#538

Post by throawaywpg »

phyzix5761 wrote: post #373

What I've found with LLMs is they're basically a better version of Google Search. If I need a quick "How do I do..." or if I need to find a quick answer to something its way more useful than Google and the fact that I can ask follow up questions is amazing. But for any serious deep work it has a long way to go.

Google always planned search to be just a stopgap

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

#540

Post by zaptrem »

MagicMoonlight wrote: post #539

It’s a stupid metric because nothing in the real world has half a million words of context. So all they’re doing is feeding it imagined slop, or sticking together random files.

It's useful for hours-long long-context debugging sessions in Claude Code, etc.
Post reply on HN