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.
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
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.
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.
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
AI companies will continue to buy up all the RAM so you and I have to pay the cost for it.
They will also eat up all the energy so you and I have to pay more for energy.
They will also then try and put you and I out of a job.
And if they fail to do so, they will then get your and my tax dollars to bail them out.
There should be real AI research and technology development, but the way it’s being done right now is heads the AI hyperscalers win, tails, all of us lose.
It’s being run as a massive scam against the rest of us.
I think maybe long-term the effect of Korean companies no longer daring to reuse old machines to produce DDR4 because of US retribution is the bigger cause of that.
Repeating this weird claim won't make it true. DDR4 isn't going to come back into fashion, even during a DRAM shortage. Demand for DDR4 can't increase meaningfully when no current-generation processors can use it, and older-generation processors aren't seeing any increase in production or sales. DDR4 is not a substitute good for the RAM that's in short supply.
He's confused about the retribution thing. Korean manufacturers aren't afraid of US to restart DDR4 manufacturing. They don't want to restart it anyway. But I'm pretty sure I've recently read it somewhere credible that they'd normally sell their old machinery but now they can't because they're afraid China would be the eventual buyer (via proxies) and they'd be inadvertently in violation of US sanctions , so instead of selling they just locked down the old machinery to gather dust instead.
And about DDR4 not being relevant, even though DDR4 manufacturing stopped earlier this year and DDR4 prices have been slowly but steadily increasing long before this crisis, after the crisis DDR4 prices have also tripled just like DDR5 prices, even in the used market. So regardless of whether it's a real demand or panic response, the effect is still real on people wanting to upgrade their DDR4 systems. These people who probably just wants to update RAM in their systems in the hope that it'd help them delay their switch to DDR5 systems for a few years while bracing the impact. Had Chinese manufacturers continued to manufacture DDR4 at least this wouldn't be that bad for the existing system upgrades of DDR4 systems.
That said, I wonder if anyone is thinking about bringing back the RAM disk. I have 64GB of DDR4 just sitting here and would love to page to that instead of my SSDs.
> meaningfully when no current-generation processors can use it
... You don't seriously believe no one is using DDR4 today, right? Sure, they may no be developing new chipsets or whatever, but large swaths of the PC population will still be on DDR4 for the foreseeable future, especially now with these prices.
reply