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

531–540 of 565 posts

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

#531

Post by cubefox »

FartyMcFarter wrote: post #397
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.

They're probably taking shortcuts such as taking advantage of sparsity. There are various tricks like that mentioned in some papers, although the big companies are getting more and more secretive about how their models work so you won't necessarily find proof.

The latest DeepSeek model has sparse attention. Though sparse attention is still not linear. Close enough perhaps.

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

#533

Post by staticassertion »

extr wrote: post #525
staticassertion wrote: post #366

Earlier quoted context omitted.

I absolutely have the hang of Claude and I still find that it can make those ridiculous mistakes, like replicating logic into a test rather than testing a function directly, talking to a local pg that was stale/ running, etc. I have a ton of skills and pre-written prompts for testing practices but, over longer contexts, it will forget and do these things, or get confused, etc. You can minimize these problems with TLC…

Don't know what to tell you. Sounds like you're holding it wrong. Based on the current state of things I would try to get better at holding it the right way.

I can't tell if you're joking?

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

#534

Post by tjoff »

jeremychone wrote: post #455
firemelt wrote: post #422

Earlier quoted context omitted.

whenever I see post like this i said well yeah, but its too sophiscated to be practical

Fair point, but because I spent a year building and refining my custom tool, this is now the reality for all of my AI requests. I prompt, press run, and then I get this flow: dev setup (dev-chat or plan) code-map (incremental 0s 2m for initial) auto-context (~20s to 40s) final AI query (~30s to 2m) For example, just now, in my Rust code (about 60k LOC), I wanted to change the data model and brainstorm with the AI to…

How do you re-evaluate your approach? I'm asking because the landscape, at least from my lens, was completely different a year ago. So I fear that as the foundation shifts whatever learnings, approaches and mental models I have risk being obsolete and starts to work against me.

The problem of evaluating is hard enough as it is without layers of indirection built on top of it.

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

#535

Post by geminiboy »

My companies brand guidelines document was 600 ish pages long and claude desktop couldnt handle it.

As soon as I saw the announcement , tried again and created a working design skill that can create design artifacts following the brand guidelines.

While these improvements seem incremental, they have a compounding effect on usefulness.

My AI doomsday calculator just got decremented by anothet 6 months.

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

#536

Post by sarchertech »

extr wrote: post #528
sarchertech wrote: post #231

Earlier quoted context omitted.

I mean I’ve been using AI close to 4 years now and I’ve been using agents off and on for over a year now. What you’re describing is exactly what I’m doing. I’m not seeing anyone at work either out of hundreds of devs who is regularly cranking out several thousand lines of pretty good working code in 30-45 minutes. What’s an example of something you built today like this?

Fair, that's optimistic, and it depends what you're doing. Looking at a personal project I had a PR from this week at +3000 -500 that I feel quite good about, took about 2 nights of about an hour each session to shape it into what I needed (a control plane for a polymarket trading engine). Though if I'm being fair, this was an outlier, only possible because I very carefully built the core of the engine to support thi…

Those numbers are much more believable, but now we’re well into maybe a 2-3x speed up. I can easily write 500 LOC in an hour if I know exactly what I’m building (ignoring that LOC is a terrible metric).

But now I have to spend more time understanding what it wrote, so best case scenario we’re talking maybe a 50% speed up to a part of my job that I spent maybe 10-20% on.

Making very big assumptions that this doesn’t add long term maintenance burdens or result in a reduction of skills that makes me worse at reviewing the output, it’s cool technology.

On par with switching to a memory managed language or maybe going from J2EE to Ruby on Rails.

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

#537

Post by hackyon1 »

zaptrem wrote: post #70
minimaxir wrote: post #4

Claude Code 2.1.75 now no longer delineates between base Opus and 1M Opus: it's the same model. Oddly, I have Pro where the change supposedly only for Max+ but am still seeing this to be case. EDIT: Don't think Pro has access to it, a typical prompt just hit the context limit. The removal of extra pricing beyond 200k tokens may be Anthropic's salvo in the agent wars against GPT 5.4's 1M window and extra pricing for t…

I have Max 20x and they're still separate on 2.1.75.

Mine took restarting. Is it still separate for you? Also might not work yet if you have CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 on

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

#538

Post by dahart »

alecco wrote: post #500
dahart wrote: post #482

Earlier quoted context omitted.

Then your point eludes me. You complained about the length. If you don’t want it shorter, then what do you want? To me, the fact that the tracking code is visible and separate from the video code is evidence of the complete opposite of your conclusion - it’s evidence the ad business does not get to override either engineering nor what’s left of privacy control. Ad execs would surely prefer that the tracking code is n…

I didn't complain about length per se. I pointed out Google's contradiction. As my previous comment clarified. Jesus.

It’s not a contradiction, as my previous comments clarified. You’re rationalizing, making assumptions, and jumping to a conclusion.

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

#539

Post by vlovich123 »

FartyMcFarter wrote: post #304
vlovich123 wrote: post #67

Earlier quoted context omitted.

Nope, there’s no tricks unless there’s been major architectural shifts I missed. The rot doesn’t come from inference tricks to try to bring down quadratic complexity of the KV cache. Task performance problems are generally a training problem - the longer and larger the data set, the fewer examples you have to train on it. So how do you train the model to behave well - that’s where the tricks are. I believe most of it…

A quick Google search reveals terms such as "sparse attention" that are used to avoid quadratic runtime. I don't know if Anthropic has revealed such details since AI research is getting more and more secretive, but the architectural tricks definitely exist.

Then you need to do a little bit deeper research. No one just applies sparse attention at inference time for a model not trained for it. They do this at training time because otherwise the task performance degrades too much.

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

#540

Post by saaaaaam »

coldtea wrote: post #146
saaaaaam wrote: post #62

Earlier quoted context omitted.

That video is bizarre. Such a heavy breather.

What a weird and inconsequential thing to focus on... He's just fucking closely miced with compression + speaking fast and anxious/excited speaking to an audience

Maybe. But that’s what I focused on, for better or worse. I couldn’t concentrate on what he was saying because of it. Maybe bad mic placement, but the end results was like some sort of old school phone sex pest.
Post reply on HN