> That is completely false. PTC does that, and we've had it for several decades.
I think you are misunderstanding the sentence you quoted.
It says something about the safety of self-driving cars. That is they don’t meet the standards required for railways. In other words the expected safety for a self-driving CAR is lower than the expected safety of a RAILWAY. (Caps for emphasis, sorry about the shouting.)
Your comment reads as if the quote claims that we cannot make “self-driving trains”. It does not say that.
> You keep pretending that avoiding train collisions is too magical to achieve with current tech
I don’t think that they do that. Definietly not in the comment you responded to.
Resin printers are very special type of printers. They are great at some things (tiny intricate details, surface quality). They are absolutely the worst in other ways (soo much faff with post curing). If you need their pros you can’t do much else but suffer the cons. But you should really think through what you want to print before getting one.
Your question is a bit like: “what if my first shovel were an excavator?” Having an excavator is great when you need one. But if you don’t need one it is a complete nightmare compared to other shoveling solutions.
> I don't have the ability to wash and cure
I don’t know what you mean by lacking the ability?
If it is not knowing how, then the simple answer is to buy the wash+cure formlabs sells with the printer and follow the instructions. Best if you watch a video tutorial first before you even buy the printer so you can decide if you have the space, want to bother with resin printing.
So much of the content around this printer is adressing what resin printing is, and comparing it to fdm printers. I already know what resin printers are and what their general pros and cons compared to a a fillament based one. But they don’t bother answering why should i choose this resin printer over an other one.
So i will just wait until the hype dies down and people who owned resin printers review it.
There are two reason why i’m cautiously optimistic about this printer though:
- i’m a member of a hackspace. And training new members on our elegoo resin printers is a pain. In particular explaining safe resin handling is a battle. In theory this model from Formlabs would require less contact with the resin. So that sounds great. Of course that promise is only good as long as things go well. But there might be benefit there.
- in my private practice i make jewellery. One of the techniques i use is lost-resin casting. The resins involved are tricky. The designs are intricate Because of that there are many print failures. In theory their printers and slicer should be much better engineered to minimise such failures. Does it work that way in practice? Only a review could tell.
> That people's beliefs about X vary is not evidence that X itself varies.
That works with things where "X" exists outside of people's beliefs.
Like where X is "gravity". It doesn't matter what you believe why an apple falls down, it will fall down the same.
But where X is "ethics" that doesn't exist outside of people's beliefs about it.
In one culture if you have a guinea pig, you kill it and then roast it that is just and proper. A sucullent meal. In an other culture if you do the same you will be forever known as the "monster who eat his guinea pig", will be harassed and likely even reported to authorities. Try it. Get a guinea pig from the pet store, roast it and serve it to your guests. See what they think of you in the Andes, or in California. The apple falls the same in both places, but the guinea pig doesn't taste the same in both places.
There is no "ethics as the ethicometer measures it". Just "ethics as the society around you recognises it".
So these are open weight models. You can run them on your own hardware. How would they have “access to literally everything”? Or what is the threat model you are thinking about here?
To be fair, it is possible that an open-weight model could still hose you by exfiltrating data in response to prompt injection. Whether or not it's abliterated doesn't change that fact.
Say I'm doing advanced semiconductor fabrication research. All of the papers in the field go straight into my local model for digestion. But a lot of those papers are from the same adversarial nation that provided my model weights, and the newest one from XXX University of YYY has a particular phrase in it that lights up some activations that I didn't know about. If that system has access to anything beyond a bunch of academic papers, there is a potential risk of exfiltration or even outright sabotage. The latter could range from providing intentional misinformation to bricking expensive hardware Stuxnet-style.
Imposing your own strict data-access guardrails will probably be the best you can do, at least for a while. But it's soooo tempting to just hand-wave it away and give the model the keys to your kingdom.
Yes! That is the danger. That the model is a “manchurian candidate”. It might be engineered to act against your best interest in some circumstances.
The circumstances can be very narrow. For example the code word you mentioned which activates a whole different personality with different objectives.
It can be also much more broad. Like a model which is engineered to be quite good at web dev but to slip in subtle buffer overflows into any driver code it writes, or to mess up when it is working on multi threaded syncronisation in a way which results in infrequent but serious lock-ups.
Or very broadly, like have correct sounding but dangerous advice about economics policy.
Or even broader. Engineer it to amplify the chanches of AI psychosis in users who are prone to it. Detect when someone went off the rails and push them even further. But perhaps only when prompted in English, not when prompted in Chinese.
Now. Is any of this happening? Eh. Probably not. Not yet at least. We can barelly make these work. But still, probably best to not risk it in sensitive applications, because it is hard to prove an AI is “safe” and “aligned” even when the creators work on your team.
Terafab profitability is really tough to get right, I'm open to ideas -- there's operating profit, operating profit net of amortization / depreciation, there's like six phases of the terafab specced out running through 203X (and as you say, slippage is inevitable there). I'd want to be considered a winner if the value of the EUV machines is up significantly, e.g. it was a balance sheet winner.
You've got to take Musk's forecasts with a massive grain (sack?) of salt. Pre-launch he was estimating making 250,000 Cybertrucks per year by 2025. So far, total sales over 3 years have actually been 60-70K.
I'd bet that in 5 years time Optimus total sales are in the 10's of thousands at best, with few to no large scale industrial users (other than self-use by Musk). Customers will be similar to what AgiBot and Unitree currently have - entertainment, hospitality, academic, small scale trials, plus a few Tesla fanboy sales that don't do anything actually productive.
On the cybertruck, I was going to suggest that's a function of demand, but actually I see there are substantial wait times for these. That might mean they cut factory capacity though, I haven't tracked it super carefully.
If Optimus is in use at factories in 2029 then it will absolutely be able to produce more than a thousand robots a month by the end of 2031, just using any sort of geometric production curve as a swag.
As to users, I think if it can provide home services, they're going to sell a ton of them.
As to Elon's forecasts, yes, double them at least. And, also, he's mostly right historically, if delayed substantially. I think there's near infinite demand for $1/hr robot labor in the US.
I think you are misunderstanding the sentence you quoted.
It says something about the safety of self-driving cars. That is they don’t meet the standards required for railways. In other words the expected safety for a self-driving CAR is lower than the expected safety of a RAILWAY. (Caps for emphasis, sorry about the shouting.)
Your comment reads as if the quote claims that we cannot make “self-driving trains”. It does not say that.
> You keep pretending that avoiding train collisions is too magical to achieve with current tech
I don’t think that they do that. Definietly not in the comment you responded to.
reply