We have decades upon decades of hardware getting dramatically cheaper year over year for the same performance, and ~1 year of the inverse due to dramatic buildout for AI.
It's a surprising example of the recency bias to me to assume anything other than the market returning to its historic norm, even if the AI buildout doesn't slow, producers will scale factories to meet that demand.
I've been using it for a week via opencode in a large, mature codebase for some moderately ambitious feature development, and a bit of debugging. Explicit purpose is evaluating if it may be a good substitute to save money for many tasks. For several tasks I've had both it and opus 4.8 attempt the same task and compared them.
In general, it's comparable across the board. Claude is less "verbose" -- GLM really likes to comment a ton. There were a few things where I think claude would have needed a little bit less back and forth. So opus still has an edge, but it's marginal, very much unlike previous open/competitor models where benchmarks looked good but actual day to day performance was pretty bad. I'm sure fable is "better" but it's so expensive + data retention policies are such that for the moment it was generally available I couldn't use it for work. This is still notably better performance than when claude code took the industry by storm.
I'm understanding why Dario is trying to regulate open weight models away.
> I honestly don't get the hostility against local models in this thread
Consider that there are literally trillions of dollars being wagered on this not being the future state of computing. Not even speculating that HN is being astroturfed (though I see no reason it wouldn't be by interested parties), but many of the US tech employees here have direct financial incentives in various forms to be rooting for the failure of open source and optionally local models.
I really think giving it a year for the hardware market to come back to earth and spending a fraction of that for API access to the same models is a better use of the money.
The open source models have gotten heavily conflated with local development. While that is cool and I'm excited about the future of local LLMs, it is not necessary to play around with these models. Without shilling for companies I don't have a relationship with, there are a number of companies who will give you an API just like Anthropic/OpenAI and you pay per token, albeit much cheaper than the frontier labs.
I've been using the full GLM 5.2 model this way (through opencode) at work for the past week. It's quite impressive.
> will likely be resale-able for what I paid for it for the next 7-10 years
There is not a period in the history of computing where this is true of consumer hardware over a decade for anything other than hardware already at the very bottom of its depreciation curve. It is surprising to me that you state that as an obvious assumption.
I suppose if your base case is Taiwan war that may be true, but there's a lot of folks who seem to be assuming the current hardware crunch will go on indefinitely when the natural state of hardware is getting cheaper over time.
I think we should go one level higher and question when having opinions and being a multi-dimensional human became a professional risk. That has certainly not always been the case.
Prices have gone down for the entire history of computing reliably with the past year being an extremely notable deviation from that trend line.
I'm pretty sure prices are going down. Maybe not complete builds in nominal dollars, but $/gb for things like RAM and SSDs will be lower in 5 years than it is today almost certainly.
US standards are bad at considering everyone outside the vehicle in general. Headlights are another great example. I've seen videos of headlight designers bragging about how they can put a dim spot in the exact place the regulators measure glare to cheat the test. Most pedestrian deaths are at night.
With many new vehicles on the road with their low beams on coming at me head-on I have no chance of seeing a pedestrian for hundreds of yards because I'm so blinded.
The times article goes very in depth on this. Yes, it is an issue, but it explains at most 10% of the increase in fatalities.
Getting hit by any vehicle over 20mph is going to be a very bad time, it is going to be somewhat worse if it's a large vehicle with a high bumper.
Americans are twice as likely to think it's fine to use a cell phone while driving than Canadians or Europeans, and while illegal in most places it's effectively unenforced - our cops spend half their shifts driving around messing around on a mounted laptop. If you want to improve outcomes, start holding American drivers to the standards that peer nations do.
I can't speak to Australia, and yeah, western Europe has a lot less big trucks, but Canada has as many large 4x4 trucks as anywhere in the US in my experience and has seen decreasing deaths. The times article touches on this but the most they can explain of the increase in deaths from vehicle size is 10%. It's a problem, but it's far from being able to explain the full issue.
The problem is that other countries have seen nearly identical trends in vehicle market share trending towards larger vehicles and have seen sustained declines in pedestrian fatalities. John Burn-Murdoch went deep on this in the FT a couple of years ago (archive link at bottom).
> Most of the explanations commonly put forward for why US roads remain so deadly focus on broad structural factors such as vehicle size or time spent on the road, but a review of the evidence suggests this may be mistaken. Last year’s improvement is a case in point. Two reasons often cited as key causes of poor US performance both worsened: the total number of miles driven by Americans increased, and US cars continued to grow larger. Yet fatal collisions still declined.
> Adding to the evidence that this is not a dominant factor, car sizes in Canada, Australia and New Zealand have traced similar paths to the US without resulting in a spike in fatalities.
> Another theory is that the rise of homelessness in the US may be pushing pedestrian deaths higher. A recent study found that there had indeed been a marked rise in traffic-related deaths among the homeless, but this, too, can only explain a small portion of the overall rise.
> Instead, an underrated factor seems to be not American cars but American drivers [...] The determining factor seems to be different attitudes to safety, with Americans twice as likely as Canadians or Europeans to say they find it acceptable to use a phone while driving.
The times article hand-waves away distracted driving by saying that other countries haven't seen a similarly large increase. The problem with that is that vehicle sizes in all other countries have also been increasing, and other countries like Canada and Australia have seen almost identical market shares of those large vehicles without the surge in pedestrian fatalities.
The large factors are phone use (more prevalent among american drivers and there's data to show this), and homelessness - the homeless are dramatically overrepresented in US pedestrian deaths and the population has increased dramatically in the US over the past decade. Even more so though it appears to be attitudes, Americans are twice as likely as Europeans or Canadians to say using a phone while driving is acceptable. Though no single factor is a smoking gun, vehicle size is one of the least convincing. Getting hit by a 4000lb car or an 8000lb truck matters much less than how fast the vehicle's going (let's all remember our high school physics class).
As people are correctly pointing out, WA is reclassifying certain e-motos as motorcycles, which is to say they'll require a license and insurance to be used on public roads - two things that are already required for all SUVs and trucks on public roads.
Being local to WA and spending a lot of time on bikes, the easiest thing we could do to improve the situation would be for law enforcement to aggressively enforce existing distracted driving laws. The number of drivers with their face buried in a phone during any kind of slow traffic is terrifying if one looks around.