They said that the current models could run a vending machine profitably, just not more complex things.

Bring back wheel covers!

Is this a proprietary harness? I feel like harnesses have a huge influence on how models behave

no. https://github.com/rails/lemans

I wonder if the inference acceleration companies will ever produce a consumer product

> But you can’t just set an agent loose in production. It can easily corrupt the database, and all it can do afterwards is apologize and promise not to do it again.

More and more, people are just gonna do it. After all, the same statement is true if employees, and they're rapidly becoming less trustworthy that frontier models.

I don't know why we're jumping to conspiracy when incompetence is right there

Perhaps we should start treating them as criminals instead of assuming that they are idiots.

Reckless and negligent idiots are criminals. They should be stopped be stopped before they get someone killed. Chernobyl happened because of massive negligence, not because someone thought a meltdown would make good PR.

That is a distinction without a practical difference.

Conspiracy and incompetence are very different.

Are the outcomes both crimes? I think that's the question to be answered.

If you consider these guys admitted they dont really have eyes on pre and post training, then incompetence really does seem more likely... especially with how fast they are moving. Its the SaaS playbook, move fast and break shit.

Laundry folding has become a doable demo for startups, and ChatGPT has been spitting out college essays for years.

> As an interviewer, I don't even know if the person I interview is a US citizen

I don't either, but my guess is almost none are

That seems like a bias you should work on.

Bring it back to Netflix

> The reason is structural, not incidental

It's almost insulting