Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

1M context is now generally available for Opus 4.6 and Sonnet 4.6

claude.com

Post reply on HN
Print view View original

371–380 of 565 posts

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#371

Post by ericpauley »

kiratp wrote: post #104
mattfrommars wrote: post #56

Earlier quoted context omitted.

Random: are you personally paying for Claude Code or is it paid by you employer? My employer only pays for GitHub copilot extension

GitHub Copilot CLI lets you use all these models (unless your employer disables them. https://github.com/features/copilot/cli Disclosure: work at Msft

Used Claude through copilot for so long before switching to CC. Even for the same model the difference is shocking. Copilot’s harness and the underlying Claude models are not well-matched compared to the vertically-integrated Claude Code harness.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#372

Post by Bombthecat »

reactordev wrote: post #368
Bombthecat wrote: post #363

Earlier quoted context omitted.

If it's not coding, even with 200k context it starts to write gibberish, even with the correct information in the context. I tried to ask questions about path of exile 2. And even with web research on it gave completely wrong information... Not only outdated. Wrong I think context decay is a bigger problem then we feel like.

That’s not context decay, that’s training data ambiguity. So much misinformation, nerfs, buffs, changes that an LLM can not keep up given the training time required. Do it for a game that has been stable and it knows its stuff.

It didnt gave outdated, on some cases it did, and with two tries telling it to search for updated information it got it right ( shouldn't need to do that though) but it also gave wrong information about sockets ( support skills) , which never existed or never were able to be socketed together in the first place. ( Ok maybe in 0.1, but that's what web search is for ... ) If it even can't handle easy versioned information from a game. How should it handle anything related to time, dates, news, science etc?

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#373

Post by borski »

jeremyjh wrote: post #322
necovek wrote: post #287

Earlier quoted context omitted.

As someone who did Python professionally from a software engineering perspective, I've actually found Python to be pretty crappy really: unaware of _good_ idioms living outside tutorials and likely 90% of Python code out there that was simply hacked together quickly. I have not tested, but I would expect more niche ecosystems like Rust or Haskell or Erlang to have better overall training set (developer who care about…

I think its pretty good at Elixir, so that tracks.

Came here to say this.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#374

Post by cubefox »

> Standard pricing now applies across the full 1M window for both models, with no long-context premium.

Does that mean it's likely not a Transformer with quadratic attention, but some other kind of architecture, with linear time complexity in sequence length? That would be pretty interesting.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#375

Post by dahart »

alecco wrote: post #340
MikeNotThePope wrote: post #20

Earlier quoted context omitted.

Is it ever useful to have a context window that full? I try to keep usage under 40%, or about 80k tokens, to avoid what Dex Horthy calls the dumb zone in his research-plan-implement approach. Works well for me so far. No vibes allowed: https://youtu.be/rmvDxxNubIg?is=adMmmKdVxraYO2yQ

Offtopic: I find it remarkable the shortened YT url has a tracking cost of 57% extra length. We live in stupid times.

I care about the privacy implications, but not the length. Out of curiosity, why do you care about the URL length at all? What is the cost to you?

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#376

Post by NanoWar »

ricardobeat wrote: post #349
syntaxing wrote: post #144

It’s interesting because my career went from doing higher level language (Python) to lower language (C++ and C). Opus and the like is amazing at Python, honestly sometimes better than me but it does do some really stupid architectural decisions occasionally. But when it comes to embedded stuff, it’s still like a junior engineer. Unsure if that will ever change but I wonder if it’s just the quality and availability of…

It is really good at writing C++ for Arduino, can one-shot most programs.

I'd say the chance of me one shotting C++ is veeeery low. Same for bash scripts etc. This is where the LLM really shines for me.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#377

Post by serial_dev »

Bombthecat wrote: post #372
reactordev wrote: post #368

Earlier quoted context omitted.

That’s not context decay, that’s training data ambiguity. So much misinformation, nerfs, buffs, changes that an LLM can not keep up given the training time required. Do it for a game that has been stable and it knows its stuff.

It didnt gave outdated, on some cases it did, and with two tries telling it to search for updated information it got it right ( shouldn't need to do that though) but it also gave wrong information about sockets ( support skills) , which never existed or never were able to be socketed together in the first place. ( Ok maybe in 0.1, but that's what web search is for ... ) If it even can't handle easy versioned informat…

Please don’t pop the AI bubble, bro. Stop asking questions, bro. Believe the hype, bro.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#378

Post by bob1029 »

cubefox wrote: post #374

> Standard pricing now applies across the full 1M window for both models, with no long-context premium. Does that mean it's likely not a Transformer with quadratic attention, but some other kind of architecture, with linear time complexity in sequence length? That would be pretty interesting.

It's almost certainly not quadratic at 1M. This would be wildly infeasible at scale. 10^6^2 = 10^12. That's a trillion things.

They are probably doing something like putting the original user prompt into the model's environment and providing special tools to the model, along with iterative execution, to fully process the entire context over multiple invokes.

I think the Recursive Language Model paper has a very good take on how this might go. I've seen really good outcomes in my local experimentation around this concept:

https://arxiv.org/abs/2512.24601

You can get exponential scaling with proper symbolic stack frames. Handling a gigabyte of context is feasible, assuming it fits the depth first search pattern.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#379

Post by blueblisters »

Bombthecat wrote: post #363
dimitri-vs wrote: post #3

The big change here is: > Standard pricing now applies across the full 1M window for both models, with no long-context premium. Media limits expand to 600 images or PDF pages. For Claude Code users this is huge - assuming coherence remains strong past 200k tok.

If it's not coding, even with 200k context it starts to write gibberish, even with the correct information in the context. I tried to ask questions about path of exile 2. And even with web research on it gave completely wrong information... Not only outdated. Wrong I think context decay is a bigger problem then we feel like.

I think ChatGPT has a huge advantage here. They have been collecting realistic multi-turn conversational data at a much larger scale. And generally their models appear to be more coherent with larger contexts for general purpose stuff.

Re: 1M context is now generally available for Opus 4.6 and Sonnet 4.6

#380

Post by eric_cc »

Bombthecat wrote: post #363
dimitri-vs wrote: post #3

The big change here is: > Standard pricing now applies across the full 1M window for both models, with no long-context premium. Media limits expand to 600 images or PDF pages. For Claude Code users this is huge - assuming coherence remains strong past 200k tok.

If it's not coding, even with 200k context it starts to write gibberish, even with the correct information in the context. I tried to ask questions about path of exile 2. And even with web research on it gave completely wrong information... Not only outdated. Wrong I think context decay is a bigger problem then we feel like.

It could also be a skill problem. It would be more helpful if when people made llm sucks claims they shared their prompt.

The people I work with who complain about this type of thing horribly communicate their ask to the llm and expect it to read their minds.

Post reply on HN