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

521–530 of 706 posts

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

#521

Post by coderenegade »

didibus wrote: post #129
photon_lines wrote: post #110

Earlier quoted context omitted.

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://ar…

You seem possibly more knowledgeable then me on the matter. My impression is that LLMs predict the next token based on the prior context. They do that by having learned a probability distribution from tokens -> next-token. Then as I understand, the models are never reasoning about the problem, but always about what the next token should be given the context. The chain of thought is just rewarding them so that the nex…

I think the intuitive leap (or at least, what I believe) is that meaning is encoded in the media. A given context and input encodes a particular meaning that the model is able to map to an output, and because the output is also in the same medium (tokens, text), it also has meaning. Even reasoning can fit in with this, because the model generates additional meaningful context that allows it to better map to an output.

How you find the function that does the mapping probably doesn't matter. We use probability theory and information theory, because they're the best tools for the job, but there's nothing to say you couldn't handcraft it from scratch if you were some transcendent creature.

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

#522

Post by simon_rider »

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, prioritize, and actually reason over it

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

#523

Post by sawjet »

mathiaspoint wrote: post #483
brulard wrote: post #482

Earlier quoted context omitted.

> 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…

It definitely isn't. LLMs often end up stuck in weird corners they just don't get and need someone familiar with the theory of what they're working on to unstick them. If the agent is the same model as the code generator it won't be able to on its own.

Skill issue

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

#524

Post by elcritch »

unshavedyak wrote: post #446
dboreham wrote: post #414

Earlier quoted context omitted.

Strong agree. Bash is so annoying that there have been many scripts that I wanted to have, but just didn't write (did the thing manually instead) rather than go down the rabbit hole of Bash nonsense. LLMs turn this on its head. I probably have LLMs write 1-2 bash scripts a week now, that I commit to git for use now and later.

Similarly my Nix[OS] env had a ton of annoyances and updates needed that i didn't care to do. My first week of Claude saw tons of Nix improvements for my environment across my three machines (desk, server, macbook) and it's a much more rich environment. Claude did great at Nix, something i struggled with due to lack of documentation. It was far from perfect, but it usually pointed me towards the answer that i could l…

Similarly I've been making Ansible Playbooks using LLMs of late, often by converting shell scripts. Play books are pretty great and easier to make idempotent than shell. But without Claude I'd forget the syntax or commands and it'd take forever to setup.

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

#525

Post by wraptile »

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.

Right, the LLM doesn't need to know all of the code under utils.parse_id to know that this call will parse the ID. The best LLM results I get is when I manually define the the relative code graph of my problem similar how I'd imagine it my head which seems to provide optimal context. So bigger isn't really better.

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

#526

Post by elcritch »

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.

Recently I realized you can add Github Copilot as a reviewer to a PR. It's surprisingly handy and found a few annoying typos and one legit bug mostly from me forgetting to update another field.

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

#527

Post by aurareturn »

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 do the same with Github Copilot after every change.

I work with a high stakes app and breaking changes cause a ton of customer headaches. LLMs have been excellent at catching potential little bugs.

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

#528

Post by NuclearPM »

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…

Problems

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

#529

Post by elcritch »

m13rar wrote: post #516

This is amazing. shout out to anthropic for doing this. I would like to have a CLAUDE Model which is not nerfed with ethics and values to please the users and write overtly large plans to impress the user.

I'm finding GPT5 to be more succinct and on par with Claude Code so far. They're really toned down the obsequiousness.

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

#530

Post by bamboozled »

nojs wrote: post #505
gdudeman wrote: post #83

A tip for those who both use Claude Code and are worried about token use (which you should be if you're stuffing 400k tokens into context even if you're on 20x Max): 1. Build context for the work you're doing. Put lots of your codebase into the context window. 2. Do work, but at each logical stopping point hit double escape to rewind to the context-filled checkpoint. You do not spend those tokens to rewind to that po…

In my experience jumping back like this is risky unless you explicitly tell it you made changes, otherwise they will get clobbered because it will update files based on the old context. Telling it to “re-read” xyz files before starting works though.

I always ask it to read the last 5 commits and anaylize and modified or staged files, works well...
Post reply on HN