Sure but the robots that extend our capabilities often start by replicating our current capabilities, even if those are as simple as folding clothes. It provides a baseline for the next generation of robots that can do more.
Is there evidence of any state-sponsored bots at all? It seems like this has become an accepted fact but I don’t see any data indicating it’s actually real.
HN has lots of hellbanned bots lately (I have showdead on [1]) but I never notice ones pushing a political slant. But I suppose nation states conducting a campaign on Hacker News would be much too cunning to make the bots obvious
[1] because many posts get wrongly flagged, apparently in part by trigger-happy users who will flag anything with incidental similarities to AI prose (everyone, PLEASE STOP DOING THAT), in part because HN's automoderation is severe for new users, and in part because plenty of people get hellbanned either unfairly or although they do still write plenty of worthwhile posts. I even rescued someone who it turned out had been hellbanned by a mod by accident.
Not just subsidised, but the supply chain is literally in the same block.
That's the thing Chinese do where other countries can't compete. If you're making product X, all of your suppliers are within walking distance around your assembly line.
Off topic, but how do you operate without email? Is it not essential for many government services and utilities where you are?
(Here, it is technically optional for utilities but is an additional $10/month to have your electricity bill posted to you instead of emailed. The tax office requires email as does my bank though - I just checked.)
>optional for utilities but is an additional $10/month
Our local utility offers a one-time $10 credit for opting-out of paperbilling... most similar signups do/will require in-person verification – which I consider a 'perk' at this point in my life (for identity protection reasons).
>how do you operate without email?
There're a few dozen million of us non-email users; granted most are infirm in some way (whether to age or insanity).
A civil court action several years ago required me to sign attensation to "no phone / email" – which at the time was still true. As I am not an attorney, they cannot refuse my access pro se to the legal system – this case eventually required me to seek representation, so this became moot.
Batch can take up to 24 hours (and often does) and may never complete if it gets cancelled so it’d be hard to build a user workflow around unless you kick off planning on Friday and come back Monday
> Preliminary trials with Claude Mythos Preview showed that it would not provide an apples-to-apples comparison with other models because of how we had set up the experiment and how the model was served.
What does this mean? My guess is they couldn’t co-locate Mythos close enough to reduce latency?
(I’m assuming this experiment pre-dates the export controls)
> My guess is they couldn’t co-locate Mythos close enough to reduce latency?
I doubt network latency is the reason. Even when connecting from literally across the world network latency is lost in the noise of overall response latency of even fast models.
The overall response latency of the model very well could have been the difference, though. AFAIK Mythos is structured to do relatively slow "deep thinking".
Depending on the timeline, it could be that they're not allowed to access Mythos because of something like non-US citizens on the team or the lack of some way for them to meet the constraint DOD has them under.
I strongly suspect if that was the case they would have just directly mentioned that Mythos couldn't be used because of that reason, it would be less confusing and less suspect messaging than saying it wasn't an "apples-to-apples comparsion".
Because this was a staged demo, not an experiment. Mythos performed more poorly but they don't want to admit it. The phrase "because of how we had set up the experiment" means "we didn't have experimental controls and got a bunch of bullshit noise that we cherry picked."
