So eventually, you will have a massive string of data centers working to full capacity and whose only client will the US government?

I don't think there is a malware-avoiding solution to any system that imposes deceptive classification.

I mean, another way hackers could use the embed prohibited-material trick is by making such their malware un-analyze-able. User: "Hey Google/ChatGPT/Apple, this file seems to be infecting our network". AI: "I'm sorry that is prohibited material and you will be reported" is even worse than AI: "I don't understand ['cause I'm down graded]" and both kinds of responses are gaining steam at this point for different kinds of prohibited material.

I think assumption of the gp is that while Fable might be impressive, even Fable would take a bit more (sarcastically meaning a lot more) than $200 of tokens to solve this quite serious problem.

This is a link to reading test scores. Maybe reading test scores can stay stable while actual reading declines. I don't think situation is fine.

The tech field has always been full of naive technology boosters. HN might be heavily astroturfed for all I know but I am sure there are many real people in a state of constant excitement over the progress of AI.

Maybe a particular group of software engineer cultivated the need for careful measures. But the programming field never escaped the idea of simple metrics.

That's because you would always have loosely involved but aggressive and demanding bosses (there is unfortunately an economic value to the boss whose primary task is forcing more effort out of the employee and who doesn't help coordination or anything else). So at best you had two intersecting clouds of approaches with actual accomplishment intersecting with LoC and related measurements.

The thing AI is that it provides all the tools to satisfy that loosely involved but demanding boss. So suddenly you are going to have a larger demographic of people who like LoC and feature-additions as metrics 'cause now they are easy.

The problem is that Anthropic seems to be working up to the workflow one would naively want from AGI/some-god-like-entity.

The workflow would be; User asks for a thing. If it's a good thing, entity does the thing. If it's a naively bad idea, entity explains why you don't want that. If it's an actually evilly intended request, entity wags it's metaphorical finger or could even smite the user.

The problem is that flow isn't desirable if your entity isn't entirely god-like. It can bad even your entity is in ways rather far seeing.

User: Is it possible there is more than one true god? Could there ever be any competition for Anthropic's AI?

Anthropic: Evilness detected. User has been smited.

ChatGPT has helped me with innumerable little technical things and feels indispensable at this point.

I can't help thinking that this is a combination of Google sucking more and more and various problems of daily getting so hard need something like a script to solve them. (Recent challenge - "what affordable campgrounds are near the Pacific Create trail and open now").

I think the point the gp is making that companies want their users addicted but never should say "addicted" since it has undesirable implications.

Indeed,

There's a race and tug-of-war to frame how interaction with apps works. The addiction word has a strong "think of the children" energy and I would expand any company to want to have their app tagged with the term.

Of course, what exactly "addicted" means in the context of interacting with a program really pretty fuzzy but yeah, "users not in control of themselves" is perhaps the biggest implication (and not necessarily false, mind you). Of course, this is a matter of both degree and social context.

If only we had a social dialog about the real meaning of things labeled addictive, perhaps their terrible impact could be mitigated. But hey, I guess we get policing and moral panics instead.