The poor will realize that they can eat the rich

How do you eat a datacenter?

I think that monkey-wrenching at a critical level would do it.

seasoned with molotov cocktails

Unfortunately your attack plan was discovered when an AI system connected to speaker outside flagged a private conversation you were having as a domestic terroist risk and a swarm of Amazon Secuirty (tm) drones have to been dispatched to paint the concrete with your brain before you even get to the data center.

Also Contabo

Cursor also significantly upcharges compared to API pricing. Last I checked they were charging ~3X API prices for Anthropic models

The 1M context is not available via subscription - only via API usage

It says "subscription users do not have access to Opus 4.6 1M context at launch" so they are probably planning to roll it out to subscription users too.

Man I hope so - the context limit is hit really quickly in many of my use cases - and a compaction event inevitably means another round of corrections and fixes to the current task.

Though I'm wary about that being a magic bullet fix - already it can be pretty "selective" in what it actually seems to take into account documentation wise as the existing 200k context fills.

Hello,

I check context use percentage, and above ~70% I ask it to generate a prompt for continuation in a new chat session to avoid compaction.

It works fine, and saves me from using precious tokens for context compaction.

Maybe you should try it.

How is generating a continuation prompt materially different from compaction? Do you manually scrutinize the context handoff prompt? I've done that before but if not I do not see how it is very different from compaction.

I wonder if it's just: compact earlier, so there's less to compact, and more remaining context that can be used to create a more effective continuation

Is this a case of doing it wrong, or you think accuracy is good enough with the amount of context you need to stuff it with often?

In my example the Figma MCP takes ~300k per medium sized section of the page and it would be cool to enable it reading it and implementing Figma designs straight. Currently I have to split it which makes it annoying.

I mean the systems I work on have enough weird custom APIs and internal interfaces just getting them working seems to take a good chunk of the context. I've spent a long time trying to minimize every input document where I can, compact and terse references, and still keep hitting similar issues.

At this point I just think the "success" of many AI coding agents is extremely sector dependent.

Going forward I'd love to experiment with seeing if that's actually the problem, or just an easy explanation of failure. I'd like to play with more controls on context management than "slightly better models" - like being able to select/minimize/compact sections of context I feel would be relevant for the immediate task, to what "depth" of needed details, and those that aren't likely to be relevant so can be removed from consideration. Perhaps each chunk can be cached to save processing power. Who knows.

lmao what are you building that actually justify needing 1mm tokens on a task? People are spending all this money to do magic tricks on themselves.

The opus context window is 200k tokens not 1mm.

But I kinda see your point - assuming from you're name you're not just a single purpose troll - I'm still not sold on the cost effectiveness of the current generation, and can't see a clear and obvious change to that for the next generation - especially as they're still loss leaders. Only if you play silly games like "ignoring the training costs" - IE the majority of the costs - do you get even close to the current subscription costs being sufficient.

My personal experience is that AI generally doesn't actually do what it is being sold for right now, at least in the contexts I'm involved with. Especially by somewhat breathless comments on the internet - like why are they even trying to persuade me in the first place? If they don't want to sell me anything, just shut up and keep the advantage for yourselves rather than replying with the 500th "You're Holding It Wrong" comment with no actionable suggestions. But I still want to know, and am willing to put the time, effort and $$$ in to ensure I'm not deluding myself in ignoring real benefits.

I do not trust that, similar working was used when Sonnet 1M launched. Still not the case today.

They want the value of your labor and competency to be 1:1 correlated to the quality and quantity of tokens you can afford (or be loaned)??

Its a weapon who's target is the working class. How does no one realize this yet?

Don't give them money, code it yourself, you might be surprised how much quality work you can get done!

It's called the "Yeet" skill in the app

Have talked to engineers in atleast 5 more companies and they have the same issue, apparently its part of the deal Anthropic is giving to companies, and they are happily taking it. I have never seen companies so complaint to a external vendor.

xAI’s models are really not pioneering at all. They weren’t the first to do MoE. Not the first to do open weighting, not the first to have memory or multi-modal vision.

So no, I wouldn’t say Elon is a major player in the AI space. People use his models because they are cheap and are willing to undress people’s photos.

saying they aren't pioneering is very different than saying they aren't a major player in the space. There're only like 5-7 players with a foundational model that they can serve at scale. xAI is one of them

Perhaps worried about downloads being used for training music models

Can’t have competitors when they inevitably move in that direction themselves.

Well then you just have a very overpriced, extremely low power linux box that doesn't do what you want it to do

Helium likewise

And brave!

Its opt-in unlike most of firefox data selling like Google search.